CN119571242B

CN119571242B - Laser shock thermal imaging composite coating spraying method based on vision guidance

Info

Publication number: CN119571242B
Application number: CN202411760509.6A
Authority: CN
Inventors: 王文瑞; 谢璐; 张佳明; 秦军伟
Original assignee: University of Science and Technology Beijing USTB
Current assignee: University of Science and Technology Beijing USTB
Priority date: 2024-12-03
Filing date: 2024-12-03
Publication date: 2025-09-23
Anticipated expiration: 2044-12-03
Also published as: CN119571242A

Abstract

The application provides a laser impact thermal imaging composite coating spraying method and device based on visual guidance, wherein the method comprises the steps of generating transient thermal response on the surface of a coating through laser impact, acquiring temperature field distribution of the surface of the coating in real time by using a high-speed thermal infrared imager, identifying crack positions according to the temperature field distribution of the surface of the coating, acquiring thermal response characteristics of crack areas of the surface of the coating, wherein the thermal response characteristics comprise real-time temperature and temperature gradient data of the crack areas, establishing a nonlinear mapping model between the thermal response characteristics of the crack and crack sizes, training by adopting a deep neural network, inputting the thermal response characteristics after data pretreatment into the trained deep neural network, predicting the sizes and the spatial positions of the cracks in real time, setting target spraying parameters based on predicted crack size information, adjusting spraying process parameters in real time by using a self-feedback PID control system, and dynamically adjusting material proportions by adopting a multichannel powder feeding system, so as to form the gradient composite coating.

Description

Laser impact thermal imaging composite coating spraying method based on visual guidance

Technical Field

The application relates to the technical field of plasma spraying of high-entropy ceramic coatings, in particular to a laser impact thermal imaging composite coating spraying method and device based on visual guidance.

Background

In the prior art, the control of crack generation and propagation is always a difficult problem in the plasma spraying process of the high-entropy ceramic coating. Due to the complex interactions between thermal stress, material properties and spray parameters, cracks are easily generated on the surface of the coating, and the formation of such cracks not only affects the mechanical properties of the coating, such as strength and toughness, but also severely reduces the overall performance of the coating, limiting its application under high temperature and complex conditions.

In addition, conventional spray techniques generally lack effective real-time monitoring and feedback mechanisms. Most spraying processes rely on preset spraying parameters (such as current, gas flow and powder feeding speed), and the formation of cracks cannot be monitored in real time during the spraying process. Therefore, cracks cannot be found in time and measures are taken to control, so that problems cannot be effectively solved at the source, and the cracks in the spraying process often expand to influence the quality of a final coating.

Furthermore, the coating properties of the prior art are often limited, mainly because most spray techniques use a single material for the coating spray. The use of the single material can not realize gradient optimization of the coating, so that the strength and toughness of the coating can not reach the optimal balance when the coating faces complex working conditions such as high temperature, high pressure and the like, thereby limiting the effect of the coating in practical application.

In summary, the prior art has the following defects that firstly, the coating cracks cannot be found and treated in time after being generated due to the lack of real-time monitoring, secondly, the cracks are detected and repaired after being regulated and sprayed, the problem of effective control at the initial stage of the coating cannot be solved, thirdly, the coating performance is single, the coating performance is difficult to optimize according to the requirements of different parts, and the comprehensive requirements of the coating under complex working conditions cannot be met. .

Disclosure of Invention

The present application aims to solve at least one of the technical problems in the related art to some extent.

To this end, a first object of the present application is to propose a laser shock thermal imaging composite coating spraying method based on visual guidance.

The second aim of the application is to provide a laser impact thermal imaging composite coating spraying device based on visual guidance.

A third object of the present application is to propose an electronic device.

A fourth object of the present application is to propose a computer readable storage medium.

A fifth object of the application is to propose a computer programme product.

To achieve the above object, an embodiment of the first aspect of the present application provides a laser impact thermal imaging composite coating spraying method based on visual guidance, including:

Generating transient thermal response on the surface of the coating by laser impact, and acquiring the temperature field distribution of the surface of the coating in real time by using a high-speed thermal infrared imager;

Identifying crack positions according to the temperature field distribution of the surface of the coating, and acquiring thermal response characteristics of crack areas of the surface of the coating, wherein the thermal response characteristics comprise real-time temperature and temperature gradient data of the crack areas;

Establishing a nonlinear mapping model between the thermal response characteristics of the crack and the size of the crack, training by adopting a deep neural network, inputting the thermal response characteristics subjected to data pretreatment into the trained deep neural network, and predicting the size and the spatial position of the crack in real time;

and setting target spraying parameters based on predicted crack size information, adjusting spraying process parameters in real time through a self-feedback PID control system, and dynamically adjusting material proportion by adopting a multi-channel powder feeding system to form the gradient composite coating.

Optionally, the crack position is identified according to the temperature field distribution of the coating surface, and the thermal response characteristic of the crack area of the coating surface is obtained, wherein the thermal response characteristic comprises real-time temperature and temperature gradient data of the crack area, and the method comprises the following steps:

Based on the temperature field distribution of the coating surface, the temperature data on the time sequence are averaged to obtain an average temperature field, and the calculation expression is as follows:

in the formula, For the average temperature field at location (x, y), T (x, y, T _i) is the temperature value at location (x, y) and time point T _i, N is the total time point in the time series;

Finding the area with the highest temperature in the average temperature field as a heat source area, and removing the heat source area from the original temperature field;

Performing gradient calculation on the processed temperature field, and performing threshold segmentation on the gradient image by using a threshold A to segment the image into a crack region and a non-crack region;

Checking whether the area of the crack area after threshold segmentation is within a preset range, if not, adjusting the threshold A to A+/-0.02, and re-carrying out threshold segmentation until the area of the crack area after threshold segmentation is within the preset range, and determining the position of the crack;

For each frame of thermal image at the crack location, subtracting the ambient temperature from it, and obtaining real-time temperature and temperature gradient data for the crack region.

Optionally, the data preprocessing process of the thermal response feature includes:

and carrying out normalization processing and noise filtering on the thermal response characteristics.

Optionally, the spraying process parameters include spraying current, gas flow, feeding speed and multi-channel powder feeding speed.

Optionally, the dynamically adjusting the material ratio by using the multi-channel powder feeding system includes:

A plurality of powder feeding channels are adopted to respectively feed high-entropy alloy powder and ceramic powder;

According to the coating performance requirement and the real-time crack information, dynamically adjusting the powder feeding rate of each channel;

and adding high-entropy alloy as a toughening phase material in a region easy to generate cracks.

Optionally, the method further comprises:

After each round of spraying, the spraying strategy is automatically adjusted according to the working condition change and the coating quality feedback, and the next round of spraying is carried out according to the adjusted spraying strategy, so that the performance optimization of the coating at different positions is ensured.

To achieve the above object, a second aspect of the present application provides a laser impact thermal imaging composite coating spraying device based on visual guidance, including:

The acquisition module is used for generating transient thermal response on the surface of the coating through laser impact and acquiring the temperature field distribution of the surface of the coating in real time by using a high-speed thermal infrared imager;

The acquisition module is used for identifying crack positions according to the temperature field distribution of the surface of the coating and acquiring thermal response characteristics of crack areas of the surface of the coating, wherein the thermal response characteristics comprise real-time temperature and temperature gradient data of the crack areas;

The prediction module is used for establishing a nonlinear mapping model between the thermal response characteristics of the crack and the size of the crack, training the nonlinear mapping model by adopting a deep neural network, inputting the thermal response characteristics subjected to data pretreatment into the trained deep neural network, and predicting the size and the spatial position of the crack in real time;

And the spraying module is used for setting target spraying parameters based on predicted crack size information, adjusting spraying technological parameters in real time through a self-feedback PID control system, and dynamically adjusting material proportion by adopting a multi-channel powder feeding system to realize the formation of the gradient composite coating.

To achieve the above object, an embodiment of a third aspect of the present application provides an electronic device, including a processor, and a memory communicatively connected to the processor;

the memory stores computer-executable instructions;

the processor executes computer-executable instructions stored by the memory to implement the method of any one of the first aspects.

To achieve the above object, an embodiment of a fourth aspect of the present application proposes a computer-readable storage medium having stored therein computer-executable instructions for implementing the method according to any of the first aspects when being executed by a processor.

To achieve the above object, an embodiment of a fifth aspect of the present application proposes a computer program product implementing the method of any one of the first aspects when being executed by a processor.

The technical scheme provided by the embodiment of the application at least has the following beneficial effects:

According to the application, by integrating the laser impact thermal imaging technology, the neural network model and the self-feedback PID control system, the real-time monitoring and control of the coating cracks in the plasma spraying process are realized, and the crack size is detected and predicted in real time, so that the expansion of the cracks and the influence on the coating performance are avoided, the strength and the toughness of the coating are improved, and the gradient performance requirement of the coating under the complex working condition is met. In addition, through closed-loop control and self-adaptive spraying, the accuracy and stability of the spraying process are further improved, and the consistency and the optimality of the coating quality are ensured.

Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.

Drawings

The foregoing and/or additional aspects and advantages of the application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:

Fig. 1 is a schematic flow chart of a laser impact thermal imaging composite coating spraying method based on visual guidance according to an embodiment of the present application;

FIG. 2 is a flow chart of a laser shock thermal imaging composite coating spraying method based on visual guidance provided by an embodiment of the application;

FIG. 3 is a flow chart of a thermal response feature acquisition process according to an embodiment of the present application;

FIG. 4 is a schematic illustration of a gradient composite coating provided by an embodiment of the present application;

Fig. 5 is a schematic structural diagram of a laser impact thermal imaging composite coating spraying device based on visual guidance according to an embodiment of the present application.

Detailed Description

Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present application and should not be construed as limiting the application.

Aiming at the problems of crack generation and expansion in the current high-entropy ceramic coating preparation process, the embodiment of the application provides a laser impact thermal imaging composite coating spraying method based on visual guidance, and a closed loop feedback system is formed by detecting coating cracks in real time, predicting crack sizes and automatically adjusting spraying parameters, so that optimal control of coating quality is realized.

Fig. 1 is a schematic flow chart of a laser impact thermal imaging composite coating spraying method based on visual guidance according to an embodiment of the present application.

In the embodiment of the application, the laser impact thermal imaging composite coating spraying method based on visual guidance is realized through a system architecture shown in fig. 2.

As shown in fig. 1, the method comprises the steps of:

And step 101, generating transient thermal response on the surface of the coating by laser impact, and acquiring the temperature field distribution of the surface of the coating in real time by using a high-speed thermal infrared imager.

In embodiments of the present application, laser shock techniques are used to produce a transient thermal response at the surface of the coating. Specifically, when a laser beam is irradiated to the coating surface, the coating surface is rapidly heated due to the high energy density of the laser beam, and temperature fluctuation occurs in a short time. This thermal response is transient and is closely related to the physical properties of the coating surface (e.g., thickness, thermal conductivity, etc.) and the presence of cracks. Cracks or discontinuities often lead to anomalies in heat flow, manifesting as different temperature gradients.

To accurately capture this process, a high-speed thermal infrared imager is used to acquire the temperature field distribution of the coating surface in real time. The thermal infrared imager can measure the temperature distribution of the surface with high precision by sensing the infrared radiation emitted by the surface of the coating, and a complete temperature field image is obtained by rapid scanning. Due to its high-speed imaging capability, thermal infrared imagers are capable of capturing temperature changes in a very short period of time, even on the order of milliseconds to microseconds, which is critical for monitoring crack initiation and propagation in real-time.

It can be appreciated that by acquiring temperature data of the coating surface, the temperature gradients of the different regions can be analyzed, and the location, size and possible propagation trend of the crack can be deduced. The thermal response data provides basic data for subsequent crack size prediction and adaptive adjustment of the spraying process, so that the whole spraying process can be controlled more accurately and in real time, crack propagation is avoided, and coating performance is optimized.

And 102, identifying crack positions according to the temperature field distribution of the coating surface, and acquiring thermal response characteristics of crack areas of the coating surface, wherein the thermal response characteristics comprise real-time temperature and temperature gradient data of the crack areas.

In the embodiment of the application, the thermal response characteristics of the crack area on the surface of the coating are obtained through a thermal response data acquisition unit shown in fig. 2.

Fig. 3 is a flow chart of a thermal response feature acquisition process according to an embodiment of the present application.

Referring to fig. 3, first, based on the temperature field distribution of the coating surface, the temperature data over the time series is averaged to obtain a smoothed temperature field, which is obtained by summing and averaging the temperature values at different positions of the coating surface at a plurality of time points, and the calculation expression of the average temperature field is:

in the formula, For the average temperature field at location (x, y), T (x, y, T _i) is the temperature value at location (x, y) and time point T _i, N is the total time point in the time series.

After the average temperature field is obtained, the area of highest temperature is found, which is typically the heat source area, which corresponds to where the crack or other coating discontinuity is located, and by removing the heat source area from the original temperature field, errors due to heat source disturbances can be eliminated.

Next, gradient calculation is performed on the temperature field after the heat source region is removed. The temperature gradient reflects the rate of temperature change and the crack region will typically exhibit a gradient profile that is different from that of the normal region.

Then, dividing the temperature gradient image by using a preset threshold A, dividing the image into a crack area and a non-crack area, checking whether the area of the crack area after threshold division is within a preset range, if not, adjusting the threshold A to A+/-0.02, and carrying out threshold division again until the area of the crack area after threshold division is within the preset range, and determining the position of the crack.

Once the location of the crack is determined, the thermal image of each frame at the crack location is processed, and the ambient temperature is subtracted to obtain real-time temperature and temperature gradient data for the crack region. The data can accurately reflect the temperature change of the crack and the thermal response characteristics of the crack, and provide key information for the subsequent crack size prediction and adjustment of the spraying process.

And 103, establishing a nonlinear mapping model between the thermal response characteristics of the crack and the size of the crack, training by adopting a deep neural network, inputting the thermal response characteristics subjected to data pretreatment into the trained deep neural network, and predicting the size and the spatial position of the crack in real time.

In the embodiment of the application, the data are required to be preprocessed before the thermal response characteristics are input into the deep neural network, so that the prediction precision and stability of the model are improved. The pretreatment mainly comprises two aspects:

(1) And normalization processing, namely converting feature data of different scales into a uniform range through normalization, and avoiding the influence of large-value features on the training of the neural network. The normalization method generally adopted is to scale the data to the [0,1] interval or normalize the data using the mean and standard deviation so that the distribution of each feature is more uniform, helping to speed up the convergence of the network.

(2) Noise filtering-thermal response data may contain noise due to various interference factors in the acquisition process. Noise is removed by using a filtering algorithm (such as median filtering or Gaussian filtering), so that the real crack characteristics can be extracted clearly, and unnecessary interference to model training is avoided.

In the embodiment of the application, the thermal response characteristic sample after data preprocessing is input into a deep neural network, and the deep neural network is trained to learn the nonlinear relation between the thermal response characteristic of the crack and the crack size (such as width and depth). The deep neural network can automatically extract complex features and patterns from a large amount of training data, thereby establishing an effective mapping model. This model enables accurate mapping of the thermal response data of the coating to the size and location of the crack.

In particular, the deep neural network is trained using annotated training data sets (including known crack sizes and thermal response characteristics). During the training process, the deep neural network continuously adjusts its internal parameters to minimize the error between the predicted result and the actual value. The common optimization algorithm has a gradient descent method, and the aim is to continuously optimize the network weight through a back propagation algorithm, so that the prediction accuracy of the network on new data is gradually improved. The application is not particularly limited or illustrated herein.

The trained deep neural network can receive new thermal response characteristic data in real time, and deduce through a model, predict the size (width and depth) of the crack and its position on the coating surface. The process can be performed in real time in the spraying process, so that the generation of cracks can be timely found and controlled, and the quality of the coating is ensured.

And finally, inputting the thermal response characteristics subjected to data pretreatment into a trained deep neural network, and predicting the size and the spatial position of the crack in real time.

And 104, setting target spraying parameters based on predicted crack size information, adjusting spraying process parameters in real time through a self-feedback PID control system, and dynamically adjusting material proportion by adopting a multi-channel powder feeding system to realize the formation of the gradient composite coating.

In the embodiment of the application, the target spraying parameters (such as spraying current, gas flow, feeding speed and multi-channel powder feeding speed) are further set according to the crack size information predicted by the deep neural network, and the spraying parameters are dynamically adjusted according to the real-time crack data through the self-feedback PID control system, so that the accuracy and stability of the spraying process are ensured.

The spraying current is used for controlling the energy density of the plasma, is a key parameter affecting the molten state of the sprayed particles, can enable the particles to be sufficiently melted by a higher current, improves the bonding strength of the coating, and is suitable for spraying thin coatings or fine features. The gas flow is used to adjust the morphology and stability of the plasma jet. The high flow rate enhances the penetrability of jet flow, is favorable for spraying thick coating or high-melting point material, and the low flow rate is suitable for spraying thin coating with higher requirement on uniformity. The feed rate is used to adjust the speed of movement of the spray gun relative to the workpiece, directly affecting the thickness and uniformity of the coating. Faster speeds are suitable for large area fast spraying, while slower speeds can enhance the thickness and strength of the coating locally. The multi-channel powder feed rate is used to precisely control the feed ratio of different powders, such as high entropy alloys and ceramic powders. By dynamically adjusting the powder feed rate of each channel, gradient optimization can be achieved in different areas of the coating, for example, increasing high-entropy alloy to improve toughness, or increasing ceramic powder to improve wear resistance.

After the spray process parameters are adjusted, a plurality of powder feeding channels are adopted in the spray process, high-entropy alloy powder and ceramic powder are respectively supplied, a plurality of material sources are provided for the formation of the coating, and the speed of each powder feeding channel is dynamically adjusted according to the performance requirement of the coating and real-time crack information.

In addition, the embodiment of the application also increases the high-entropy alloy as a toughening phase material in the area easy to generate cracks, thereby improving the toughness of the coating and preventing the crack from expanding and further damaging.

It should be noted that, after each round of spraying is completed, the embodiment of the application adjusts the spraying strategy according to the working condition change and the real-time feedback of the coating quality. Such feedback information may include variations in crack areas, uniformity of coating thickness, and assessment of performance metrics. And then, based on the adjusted spraying strategy, entering the next round of spraying process to ensure that the performance of the coating in different areas is optimally configured. For example, the proportion of ductile material may be increased at the locations where the forces are greater, while ceramic powder may be increased at the locations where the wear resistance requirements are higher.

Therefore, the whole process forms a closed loop system, and the spraying parameters are continuously optimized through the process of real-time crack detection, size prediction and parameter adjustment, so that the coating quality and the dynamic adaptability of crack control are ensured.

In one possible embodiment, the gradient composite coating is schematically shown in FIG. 5, where HEC is a ceramic, HEA high entropy alloy. The schematic shows the composition and performance grading characteristics of the coating from the surface to the substrate.

In order to realize the embodiment, the application also provides a laser impact thermal imaging composite coating spraying device based on visual guidance. Fig. 5 is a schematic structural diagram of a laser impact thermal imaging composite coating spraying device 10 based on visual guidance according to an embodiment of the present application. As shown in fig. 5, the apparatus includes:

The acquisition module 100 is used for generating transient thermal response on the surface of the coating through laser impact, and acquiring the temperature field distribution of the surface of the coating in real time by using a high-speed thermal infrared imager;

an acquisition module 200, configured to identify a crack location according to a temperature field distribution of the coating surface, and acquire a thermal response characteristic of a crack region of the coating surface, where the thermal response characteristic includes real-time temperature and temperature gradient data of the crack region;

The prediction module 300 is configured to establish a nonlinear mapping model between the thermal response characteristics of the crack and the size of the crack, train the nonlinear mapping model by using a deep neural network, input the thermal response characteristics after data preprocessing into the trained deep neural network, and predict the size and the spatial position of the crack in real time;

The spraying module 400 is used for setting target spraying parameters based on predicted crack size information, adjusting spraying process parameters in real time through a self-feedback PID control system, and dynamically adjusting material proportion by adopting a multi-channel powder feeding system to realize the formation of the gradient composite coating.

In order to realize the embodiment, the application also provides electronic equipment which comprises a processor and a memory which is in communication connection with the processor, wherein the memory stores computer execution instructions, and the processor executes the computer execution instructions stored in the memory so as to realize the method for executing the embodiment.

In order to implement the above-described embodiments, the present application also proposes a computer-readable storage medium having stored therein computer-executable instructions that, when executed by a processor, are adapted to implement the methods provided by the foregoing embodiments.

In order to implement the above embodiments, the present application also proposes a computer program product comprising a computer program which, when executed by a processor, implements the method provided by the above embodiments.

The processing of collecting, storing, using, processing, transmitting, providing, disclosing and the like of the personal information of the user in the application accords with the regulations of related laws and regulations and does not violate the popular regulations of the public order.

It should be noted that personal information from users should be collected for legitimate and reasonable uses and not shared or sold outside of these legitimate uses. In addition, such collection/sharing should be performed after receiving user informed consent, including but not limited to informing the user to read user agreements/user notifications and signing agreements/authorizations including authorization-related user information before the user uses the functionality. In addition, any necessary steps are taken to safeguard and ensure access to such personal information data and to ensure that other persons having access to the personal information data adhere to their privacy policies and procedures.

The present application contemplates embodiments that may provide a user with selective prevention of use or access to personal information data. That is, the present disclosure contemplates that hardware and/or software may be provided to prevent or block access to such personal information data. Once personal information data is no longer needed, risk can be minimized by limiting data collection and deleting data. In addition, personal identification is removed from such personal information, as applicable, to protect the privacy of the user.

In the foregoing description of embodiments, reference has been made to the terms "one embodiment," "some embodiments," "example," "a particular example," or "some examples," etc., meaning that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.

Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include an electrical connection (an electronic device) having one or more wires, a portable computer diskette (a magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.

It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware as in another embodiment, may be implemented using any one or combination of techniques known in the art, discrete logic circuits with logic gates for implementing logic functions on data signals, application specific integrated circuits with appropriate combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), etc.

Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.

The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. While embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present application may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present application are achieved, and the present application is not limited herein.

The above embodiments do not limit the scope of the present application. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the scope of the present application.

Claims

1. A method for spraying a composite coating using laser shock thermography based on vision guidance, comprising the following steps:

The laser shock generates transient thermal response on the coating surface, and a high-speed infrared thermal imager is used to collect the temperature field distribution on the coating surface in real time.

Identifying the crack location based on the temperature field distribution on the coating surface and obtaining thermal response characteristics of the crack area on the coating surface, wherein the thermal response characteristics include real-time temperature and temperature gradient data of the crack area;

A nonlinear mapping model between crack thermal response characteristics and crack size is established and trained using a deep neural network. The thermal response characteristics after data preprocessing are input into the trained deep neural network to predict the size and spatial position of the crack in real time.

The target spraying parameters are set based on the predicted crack size information. The spraying process parameters are adjusted in real time through a self-feedback PID control system. The material ratio is dynamically adjusted using a multi-channel powder feeding system to achieve the formation of a gradient composite coating.

The method of identifying the crack location based on the temperature field distribution on the coating surface and obtaining the thermal response characteristics of the crack area on the coating surface, wherein the thermal response characteristics include real-time temperature and temperature gradient data of the crack area, includes:

Based on the temperature field distribution of the coating surface, the temperature data in the time series are averaged to obtain the average temperature field. The calculation expression is:

Where, For the location The average temperature field, For the location and time point The temperature value, is the total time points in the time series;

The gradient of the processed temperature field is calculated and the threshold is used Perform threshold segmentation on the gradient image to divide the image into crack area and non-crack area;

Check whether the crack area after threshold segmentation is within the preset range. If not, adjust the threshold. to Then, the threshold segmentation is performed again until the crack area after the threshold segmentation is within the preset range, and the crack location is determined;

For each frame of the thermal image at the crack location, the ambient temperature is subtracted to obtain the real-time temperature and temperature gradient data of the crack area.

2. The method according to claim 1, wherein the data preprocessing process of the thermal response characteristics comprises:

The thermal response characteristics are normalized and noise filtered.

3. The method according to claim 2, characterized in that the spraying process parameters include spraying current, gas flow rate, feed speed and multi-channel powder feeding rate.

4. The method according to claim 3, wherein the dynamically adjusting the material ratio using a multi-channel powder feeding system comprises:

Multiple powder feeding channels are used to supply high entropy alloy powder and ceramic powder respectively;

Dynamically adjust the powder feeding rate of each channel according to coating performance requirements and real-time crack information;

In areas prone to cracking, high entropy alloy is added as a toughening phase material.

5. The method according to any one of claims 1 to 4, further comprising:

After each round of spraying, the spraying strategy is automatically adjusted according to the working condition changes and coating quality feedback, and the next round of spraying is carried out according to the adjusted spraying strategy to ensure the optimal performance of the coating at different locations.

6. An electronic device, comprising: a processor, and a memory communicatively connected to the processor;

The memory stores computer-executable instructions;

The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 5.

7. A computer-readable storage medium, characterized in that the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method according to any one of claims 1 to 5.

8. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.