An Adaptive Multi-Robot Collaborative Spraying Control Method for Large Castings

Abstract

The present invention relates to the field of automatic control, and in particular to a method for controlling the collaborative spraying of large castings by multiple robots based on self-adaptation, comprising obtaining data information related to castings and spraying processes, and establishing a spraying task analysis model; after the multiple robots have completed preliminary spraying of the castings, the spraying effects are analyzed and evaluated by various parameters of the castings after spraying obtained by intelligent sensors, and a neural network model for evaluating the spraying effects is established; and in combination with the surface curvature of the castings, a spraying speed correction parameter is calculated; by comparing the spraying speed correction parameter with a preset spraying speed correction parameter, the spraying speed is adjusted according to the comparison result; according to the obtained nozzle size, coating viscosity and adjusted or optimized spraying speed, a spraying liquid flow control parameter is calculated, and the spraying liquid flow is controlled; according to the fluctuation of the regulated spraying speed and the spraying liquid flow, the stability of the spraying quality is judged, and the spraying process of the large castings by multiple robots is adjusted.

Description

Technical Field

[0001] The invention relates to the field of automatic control, and in particular to an adaptive large casting multi-robot collaborative spraying control method. Background Art

[0002] In the surface spraying operation of large castings, due to the large size and complex shape of the castings, it is often difficult for a single robot to complete the spraying task efficiently and with high quality. Therefore, multi-robot collaborative spraying becomes an effective solution. However, there are some problems with the existing multi-robot collaborative spraying control methods. For example, during the spraying process, it is difficult to make adaptive adjustments based on the actual shape of the casting, surface characteristics, and changes in the spraying environment, resulting in problems such as uneven spraying thickness and unstable coating quality. In addition, the collaborative collaboration between robots is not flexible and efficient enough, and interference and collision are prone to occur, affecting the efficiency and safety of spraying.

[0003] The existing technology still cannot efficiently control the collaborative spraying of multiple robots for large castings, resulting in inaccurate control parameters, large and numerous defects in the spraying process, and certain cost losses; and it is impossible to monitor the spraying process in real time to reduce the error rate and fault rate; and the spraying process for large casting production cannot be flexibly changed.

[0004] Therefore, an adaptive multi-robot collaborative spraying control method for large castings is needed. Summary of the invention

[0005] The present invention provides an adaptive large casting multi-robot collaborative spraying control method, which aims to achieve real-time adjustment of spraying parameters through an adaptive control method to optimize coating quality, ensure coating uniformity and adhesion; reduce manpower input, reduce production costs, improve production efficiency, and avoid human errors; make the production process more flexible to adapt to different castings and spraying requirements.

[0006] The technical solution of the present invention is specifically as follows:

[0007] A large casting multi-robot collaborative spraying control method based on self-adaptation comprises the following steps:

[0008] Step S1. Acquire casting and spraying process related data information according to different monitoring equipment and sensors, establish a spraying task analysis model, and obtain the output result of the casting task analysis model, that is, the evaluation parameter set of the spraying task process;

[0009] Step S2. After the multi-robots have completed the preliminary spraying of the casting, the spraying effect is analyzed and detected by the parameters of the casting after spraying obtained by the intelligent sensor, and a comprehensive evaluation is performed to establish a neural network model for spraying effect evaluation and output the spraying evaluation results;

[0010] Step S3. Calculate the spraying speed correction parameter according to the output result of the spraying effect evaluation model and the curvature of the casting surface; and adjust the spraying speed according to the comparison result by comparing the spraying speed correction parameter with the preset spraying speed correction parameter;

[0011] Step S4. Calculate the spraying liquid flow control parameters according to the obtained nozzle size, coating viscosity and adjusted or optimized spraying speed, and control the spraying liquid flow;

[0012] Step S5. Monitor the fluctuation of the spraying speed and the spraying liquid flow rate after adjustment to determine the stability of the spraying quality and adjust the multi-robot spraying process of large castings.

[0013] Step S1 specifically includes:

[0014] Calculate the evaluation parameters of the spraying task process in the evaluation parameter set of the spraying task process , the assessment scores of different tasks in different sub-parts of large castings are graded;

[0015] in, Indicates casting The sub-part Assessment parameters for each task; represents the evaluation coefficient; Indicates The operational difficulty coefficient of the task; Indicates The urgency of the time requirements for the task;

[0016] definition Indicates the threshold between easy and medium tasks; Indicates the threshold between medium tasks and complex tasks, and grades the scores of different tasks in different sub-parts of large castings. The specific process is as follows:

[0017] when When the casting The sub-part The spraying task is classified as a simple task, with level 1;

[0018] when When the casting The sub-part The spraying task is classified as a medium task, with a level of 2;

[0019] when When the casting The sub-part The spraying task is classified as a complex task with a level of 3.

[0020] Step S1 specifically includes:

[0021] The spraying speed is adjusted according to the different spraying task levels of different casting parts. , spraying liquid flow Preset the base spraying speed to , the reference spraying liquid flow rate is ;

[0022] When level is 1, the preset first spraying speed is , , Indicates the corresponding first spraying speed adjustment coefficient;

[0023] When level is 2, the preset first spraying speed is , , Indicates the corresponding second spraying speed adjustment coefficient;

[0024] When level is 3, the preset first spraying speed is , , Indicates the corresponding third spraying speed adjustment coefficient.

[0025] Step S2 specifically includes:

[0026] The neural network model for spraying effect evaluation includes input layer, analysis layer, evaluation layer and output layer;

[0027] In the analysis layer, the input spraying result information of the casting part is analyzed. The specific process is as follows:

[0028] in, Represents the output of the analysis layer; Represents the input of the analysis layer; represents the learning factor; represents the attenuation coefficient; Indicates the casting sub-part Standard case for class attributes; Indicates the standard conditions of different parts of the casting spray information; Indicates The actual feature information of the class attributes; Influencing parameters representing the properties of casting part information; Indicates The spraying result information of each casting part.

[0029] Step S3: Calculate spraying speed correction parameters , as shown below:

[0030] in, Represents the overall control coefficient, which is used to control the amplitude of change; It represents the benchmark value of the output result of the spraying effect evaluation model; represents a constant coefficient; Indicates the coefficient of variation of casting surface curvature.

[0031] In step S3, the spraying speed correction parameter Comparison with preset spray speed correction parameters Compare and adjust the spraying speed according to the comparison results Make adjustments, ; The specific process is as follows:

[0032] if , then adjust the spraying speed to , then define ;

[0033] if , then adjust the spraying speed to , then define ;

[0034] if , then adjust the spraying speed to , then define .

[0035] Step S3 specifically includes:

[0036] The obtained spraying pressure of different parts and different tasks of the casting Preset spray pressure for different parts and tasks of castings Compare and decide whether to adjust the spraying speed according to the comparison results. The specific process is as follows:

[0037] if , it means that the spraying pressure of large castings meets the requirements of spraying work, and there is no need to optimize the spraying speed;

[0038] if , it means that the spraying pressure of large castings does not meet the requirements of spraying work, and the spraying speed needs to be optimized.

[0039] In step S4, an index related to the coating properties and flow characteristics is introduced , calculate the spray liquid flow control parameters The process is as follows:

[0040] , ,in, Indicates the nozzle size, Indicates the viscosity of the paint. Indicates the adjusted or optimized spraying speed.

[0041] Step S5 specifically includes:

[0042] When the standard deviation of the spraying speed Less than the preset spray speed threshold , and the standard deviation of the spraying liquid flow rate Less than the preset spraying liquid flow threshold When the spraying quality is stable, it means that the spraying process is in normal state, but it still needs to be monitored; otherwise, it means that the spraying process may be abnormal and timely measures need to be taken to adjust it.

[0043] Beneficial effects: 1. The present invention acquires data in real time through monitoring equipment and sensors. The spraying task analysis model can monitor the spraying process in real time, promptly discover problems in the implementation process and make adjustments, and comprehensively evaluate the tasks in the spraying process and accurately classify them into grades, thereby improving the accuracy and reliability of the evaluation, and helping to achieve more accurate quality control, thereby improving production efficiency and quality.

[0044] 2. The present invention can realize the automatic analysis and evaluation of various parameters of the casting after spraying through the spraying effect evaluation neural network model, without human intervention, thus improving the evaluation efficiency, and making accurate evaluation based on a large amount of data training to help discover subtle changes in the spraying effect; at the same time, it provides data support for production, helps make data-based judgments, and promotes continuous optimization of the production process; and the automated spraying effect evaluation can reduce the possibility of human error and improve the accuracy and reliability of the evaluation.

[0045] 3. The present invention combines the spraying effect evaluation and the casting surface curvature, and the calculated spraying speed correction parameters can optimize the spraying process more accurately and improve the quality and uniformity of the coating; by comparing the correction parameters, the difference between the actual spraying speed and the expected speed can be accurately understood, and more accurate speed control can be achieved. The spraying speed can be adjusted according to the comparison results, which helps to optimize the spraying process, improve production efficiency and product quality, and continuously improve the production process. At the same time, by comparing the actual spraying pressure with the preset value, the pressure changes during the spraying process can be more accurately understood, and it can be determined whether the spraying pressure meets the requirements, which helps to accurately control the spraying speed to achieve a more ideal spraying effect.

[0046] 4. The present invention calculates the spraying liquid flow control parameters according to the nozzle size, coating viscosity and spraying speed, can be adjusted according to different process requirements and coating characteristics, adapt to different production conditions, and can achieve precise control of the liquid flow, ensuring the stability and consistency of the spraying process, avoiding excessively thick or thin coating, and improving the coating quality; by adjusting the liquid flow, the spraying effect can be optimized, the adhesion, glossiness and durability of the coating can be improved, and the product quality can be more stable and excellent.

[0047] 5. The present invention can reduce the need for human intervention by monitoring fluctuations, automatically adjust parameters, reduce the possibility of human error, improve work accuracy, help optimize the multi-robot spraying process of large castings, improve production efficiency and product quality, and reduce scrap rate; at the same time, it can help improve production stability, reduce the impact of changes on product quality, and ensure the stability and reliability of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a flow chart of a method for controlling large casting multi-robot collaborative spraying based on self-adaptation according to the present invention;

[0049] Figure 2 It is a module diagram of a large casting multi-robot collaborative spraying control system based on self-adaptation of the present invention;

[0050] Figure 3 It is a schematic diagram of the central control module of the present invention. DETAILED DESCRIPTION

[0051] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should also be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0052] See attached Figure 1 This embodiment provides a large casting multi-robot collaborative spraying control method based on self-adaptation, comprising the following steps:

[0053] S1.Acquire relevant data information of castings and spraying process according to different monitoring equipment and sensors, establish spraying task analysis model, and obtain the output result of casting task analysis model, namely: the evaluation parameter set of spraying task process; according to the evaluation parameters of calculated spraying task process, grade the evaluation scores of different tasks in different sub-parts of large castings.

[0054] The large casting is fully scanned by 3D scanning equipment to obtain the 3D geometry, surface roughness and other information of the casting; based on the scanning data, computer-aided design, such as CAD software, is used to build an accurate 3D model of the casting and import the model into the control system. According to the 3D model of the casting, the spraying area is divided into multiple sub-areas, and each sub-area is assigned a corresponding robot responsible for work. At the same time, monitoring equipment is installed in the spraying environment, and visual sensors, force sensors, distance sensors and other equipment are installed at the end of the robot during the robot spraying of large castings to monitor the spraying status in real time.

[0055] In the embodiment of the present invention, a spraying task plan is formulated according to the spraying requirements of each part and the working function of the robot, a casting task analysis model is established, and the evaluation score of the spraying task process is calculated; the specific process is as follows:

[0056] in, Represents the parameter set of the spraying robot; Represents a set of casting features; Represents the set of environmental parameters when the spraying task is in progress; Represents a set of spray resource constraint parameters; It represents the output result of the casting task analysis model, that is, the set of evaluation parameters of the spraying task process;

[0057] Specifically, the robot parameter set is , ,in, Indicates the number of spraying robots, Indicates Robot parameter information; casting part feature set , , Indicates the number of casting sub-parts, Indicates The environmental parameter set during the spraying task includes temperature, humidity, air cleanliness or air quality (obtained according to the specific spraying environment), among which, , Respectively represent temperature, humidity, air cleanliness or air quality parameter set, Respectively represent the number of elements corresponding to the temperature, humidity, and air cleanliness (or air quality parameter) sets; the spray resource constraint parameter set is , , Indicates the number of spray resource constraints, Indicates The spraying resource constraint parameters include the paint supply, the maintenance time of the spraying robot, the process connection time, etc. In the embodiment of the present invention, , represents the set of paint supply quantities, Represents the maintenance duration of the spraying robot. Represents the duration of process connection.

[0058] in, , , They represent the corresponding weights respectively, indicating the influence of spraying resource constraints on the process analysis of spraying tasks; Indicates the maximum value of coating supply during the casting spraying process; Indicates the average maintenance time of the spraying robot; Indicates the upper limit of the duration of process connection; Indicates the balance of robot parameters during the spraying task; Indicates the influence of fusion casting characteristics on the spraying task process; represents the analysis parameters; Indicated in The temperature obtained at Indicated in Normal standard temperature; , Respectively represent the influence coefficient of temperature on humidity and air cleanliness (or air quality parameters); Indicates Humidity information obtained by each monitoring device; Indicates Air cleanliness (or air quality parameter) information obtained by each monitoring device; Indicates the total monitoring time.

[0059] Thus, the evaluation parameter set of the spraying task process is obtained Each element is defined by the comprehensive evaluation score of each part of the casting :

[0060] in, Indicates casting The sub-part The assessment parameters of the task; specifically,

[0061] in, represents the evaluation coefficient; Indicates The operational difficulty coefficient of the task; Indicates The urgency of the time requirement for the task.

[0062] Now according to The value range of Indicates the threshold between easy and medium tasks; Indicates the threshold between medium tasks and complex tasks, and grades the scores of different tasks in different sub-parts of large castings. The specific process is as follows:

[0063] when When the casting The sub-part The spraying task is classified as a simple task, with level 1;

[0064] when When the casting The sub-part The spraying task is classified as a medium task, with a level of 2;

[0065] when When the casting The sub-part The spraying task is classified as a complex task with a level of 3.

[0066] At the same time, the spraying speed is adjusted according to the different spraying task levels of different casting parts. , spraying liquid flow Preset the base spraying speed to , the reference spraying liquid flow rate is , the specific process is as follows:

[0067] When level is 1, the preset first spraying speed is , , Indicates the corresponding first spraying speed adjustment coefficient;

[0068] When level is 2, the preset first spraying speed is , , Indicates the corresponding second spraying speed adjustment coefficient;

[0069] When level is 3, the preset first spraying speed is , , Indicates the corresponding third spraying speed adjustment coefficient.

[0070] The present invention acquires data in real time through monitoring equipment and sensors. The spraying task analysis model can monitor the spraying process in real time, promptly discover problems in the implementation process and make adjustments. It can also comprehensively evaluate the tasks in the spraying process and accurately classify them into grades, thereby improving the accuracy and reliability of the evaluation, and helping to achieve more precise quality control, thereby improving production efficiency and quality.

[0071] S2. After the multi-robots have completed the preliminary spraying of the castings, the parameters of the castings after spraying are obtained by the intelligent sensors to further analyze and detect the spraying effect, and a comprehensive evaluation is conducted to establish a neural network model for spraying effect evaluation and output the spraying evaluation results.

[0072] A neural network model for spraying effect evaluation is established through deep learning. The specific spraying result information of each sub-part of the casting is used as a training sample and as the input of the neural network model for spraying effect evaluation, which is expressed as , express The spraying result information of each casting part is used to express, The spraying effect evaluation neural network model includes input layer, analysis layer, evaluation layer and output layer.

[0073] The input layer will Passed to the analysis layer, the transmission process is as follows:

[0074] in, Represents the input of the analysis layer; Represents the connection weight between the input layer and the analysis layer; Represents the output of the input layer; Represents the bias of the analysis layer.

[0075] In the analysis layer, the input spraying result information of the casting part is analyzed. The specific process is as follows:

[0076] in, Represents the output of the analysis layer; represents the learning factor; represents the attenuation coefficient; Indicates the casting sub-part Standard case for class attributes; Indicates the standard conditions of different parts of the casting spray information; Indicates The actual feature information of the class attributes; Influencing parameters that represent the properties of casting part information.

[0077] The analysis layer passes the output results to the evaluation layer, and the evaluation layer optimizes the output results of the analysis layer. The specific process is as follows:

[0078] in, represents the output of the evaluation layer; represents the evaluation coefficient; Represents the connection weight between the analysis layer and the evaluation layer; Represents the bias of the evaluation layer. Finally, the output layer outputs the final analysis result. ,in, represents the output result of the output layer, represents the connection weight between the evaluation layer and the output layer, Represents the bias of the output layer.

[0079] The present invention uses a spraying effect evaluation neural network model to realize automatic analysis and evaluation of various parameters of castings after spraying, without human intervention, thus improving evaluation efficiency, and making accurate evaluations based on a large amount of data training to help discover subtle changes in spraying effects; at the same time, it provides data support for production, helps make data-based judgments, and promotes continuous optimization of the production process; and automated spraying effect evaluation can reduce the possibility of human errors and improve the accuracy and reliability of the evaluation.

[0080] S3. In the first control unit, a spraying speed correction parameter is calculated according to the output result of the spraying effect evaluation model and in combination with the surface curvature of the casting; the spraying speed correction parameter is compared with the preset spraying speed correction parameter, and the spraying speed is adjusted according to the comparison result.

[0081] In the first control unit, the output of the spraying effect evaluation model is used Combined with the casting surface curvature , calculate the spray speed correction parameters , as shown below:

[0082] in, Represents the overall control coefficient, which is used to control the amplitude of change; It represents the benchmark value of the output result of the spraying effect evaluation model; represents a constant coefficient; Indicates the coefficient of variation of casting surface curvature.

[0083] By setting the spray speed correction parameter Comparison value with preset spray speed correction parameters Compare and adjust the spraying speed according to the comparison results Make adjustments, ; The specific process is as follows:

[0084] if , then adjust the spraying speed to , then define ;

[0085] if , then adjust the spraying speed to , then define ;

[0086] if , then adjust the spraying speed to , then define .

[0087] In the second control unit, the spray pressure of different parts and different tasks of the casting is obtained Preset spray pressure for different parts and tasks of castings Compare and decide whether to adjust the spraying speed according to the comparison results. The specific process is as follows:

[0088] if , it means that the spraying pressure of large castings meets the requirements of spraying work, and there is no need to optimize the spraying speed;

[0089] if , it means that the spraying pressure of large castings does not meet the requirements of spraying work, and the spraying speed needs to be optimized; the specific optimization process is as follows:

[0090] set up and The difference, that is: , and define the first spraying speed difference and the second spray speed difference ,and ,according to Respectively and Make a comparison and optimize the spraying speed according to the comparison results, as shown below:

[0091] if , then optimize the spraying speed to , , represents the first optimization coefficient;

[0092] if , then optimize the spraying speed to , , represents the second optimization coefficient;

[0093] if , then optimize the spraying speed to , , Represents the third optimization coefficient.

[0094] The present invention combines the spraying effect evaluation and the casting surface curvature, and the calculated spraying speed correction parameters can optimize the spraying process more accurately and improve the quality and uniformity of the coating; by comparing the correction parameters, the difference between the actual spraying speed and the expected speed can be accurately understood, and more accurate speed control can be achieved. The spraying speed can be adjusted according to the comparison results, which helps to optimize the spraying process, improve production efficiency and product quality, and continuously improve the production process. At the same time, by comparing the actual spraying pressure with the preset value, the pressure change during the spraying process can be more accurately understood, and it can be determined whether the spraying pressure meets the regulations, which helps to accurately control the spraying speed to achieve a more ideal spraying effect.

[0095] S4. In the third control unit, according to the obtained nozzle size (diameter) , coating viscosity and the adjusted or optimized spraying speed, calculate the spraying liquid flow control parameters , for spraying liquid flow To regulate.

[0096] Specifically, in the third control unit, according to the obtained nozzle size (diameter) , coating viscosity and spraying speed (Because this may involve whether to optimize the spraying speed, express or ), calculate the spraying liquid flow control parameters , for spraying liquid flow To regulate.

[0097] In the embodiment of the present invention, an index related to the coating properties and flow characteristics is introduced , determined by experiments, the value is generally between 0.5-1, and the spray liquid flow control parameters are calculated The process is as follows: , .

[0098] The first spraying liquid flow control parameter is set , Second spraying liquid flow control parameters ,and , the spraying liquid flow control parameter Compare parameters with the first calibration , the second calibration comparison parameter Compare them respectively, and adjust the spraying liquid flow rate according to the comparison results; the specific process is as follows:

[0099] if , the spraying liquid flow rate is regulated and adjusted to , ;

[0100] if , the spraying liquid flow rate is regulated and adjusted to , ;

[0101] if , the spraying liquid flow rate is regulated and adjusted to , .

[0102] The present invention calculates the spraying liquid flow control parameters according to the nozzle size, coating viscosity and spraying speed, can be adjusted according to different process requirements and coating characteristics, adapts to different production conditions, can achieve precise control of the liquid flow, ensures the stability and consistency of the spraying process, avoids over-thickness or over-thinness of the coating, and improves the coating quality; by adjusting the liquid flow, the spraying effect can be optimized, the adhesion, glossiness and durability of the coating can be improved, and the product quality can be more stable and excellent.

[0103] S5. According to the optimized spraying speed and spraying liquid flow The fluctuations can be monitored to determine the stability of the spraying quality and to adjust the multi-robot spraying process for large castings.

[0104] In the embodiment of the present invention, a time interval is set The time series data of spraying speed is , the time series data of spraying liquid flow rate is ; Define the standard deviation of spraying speed as , the standard deviation of the spraying liquid flow rate is , the specific process is as follows:

[0105] , in, and Respectively represent the spraying speed and spraying liquid flow rate in the time interval The calculation process is as follows:

[0106] , When the standard deviation of the spraying speed Less than the preset spray speed threshold , and the standard deviation of the spraying liquid flow rate Less than the preset spraying liquid flow threshold When the spraying quality is stable, it means that the spraying process is in normal state, but it still needs to be monitored to ensure the stability of the spraying quality; otherwise, it means that the spraying process may be abnormal, and timely measures need to be taken to adjust it to ensure the stability of the spraying quality.

[0107] By monitoring fluctuations, the present invention can reduce the need for human intervention, automatically adjust parameters, reduce the possibility of human error, improve work accuracy, help optimize the multi-robot spraying process of large castings, improve production efficiency and product quality, and reduce scrap rate; at the same time, it can help improve production stability, reduce the impact of changes on product quality, and ensure the stability and reliability of the production process.

[0108] See attached Figure 2 This embodiment provides an adaptive large casting multi-robot collaborative spraying control system, including the following contents:

[0109] Data information acquisition module, casting task analysis module, spraying effect evaluation module, spraying central control module, real-time monitoring module;

[0110] See attached Figure 3 , the spraying central control module includes a first control unit, a second control unit, and a third control unit;

[0111] A data information acquisition module, which is used to collect data information related to the spraying process through sensors, scanners or other devices;

[0112] The casting task analysis module obtains data information related to castings and spraying processes based on different monitoring equipment and sensors, establishes a spraying task analysis model, and obtains the output results of the casting task analysis model;

[0113] The spraying effect evaluation module uses the intelligent sensor to obtain the parameters of the casting after spraying, analyze and detect the spraying effect, and monitor and evaluate the spraying effect;

[0114] The spraying central control module adaptively adjusts the spraying parameters according to the results of casting task analysis and spraying effect evaluation to ensure coating quality;

[0115] A first control unit calculates a spraying speed correction parameter, compares the spraying speed correction parameter with a preset spraying speed correction parameter, and adjusts the spraying speed according to the comparison result;

[0116] The second control unit compares the acquired spraying pressures of different parts and different tasks of the casting with the preset spraying pressures of different parts and different tasks of the casting, and determines whether to optimize the spraying speed according to the comparison result;

[0117] A third control unit, in which the spraying liquid flow rate control parameters are calculated according to the obtained nozzle size (diameter), coating viscosity and adjusted or optimized spraying speed, and the spraying liquid flow rate is controlled;

[0118] The real-time monitoring module monitors the fluctuation of the regulated spraying speed and the spraying liquid flow rate to determine the stability of the spraying quality.

[0119] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0120] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0121] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0122] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0123] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A multi-robot collaborative spraying control method for large castings based on self-adaptation, characterized in that: The following steps are involved: Step S1. Acquire casting and spraying process related data information according to different monitoring equipment and sensors, establish a spraying task analysis model, and obtain the output result of the casting task analysis model, that is, the evaluation parameter set of the spraying task process; Step S2. After the multi-robots have completed the preliminary spraying of the casting, the spraying effect is analyzed and detected by the parameters of the casting after spraying obtained by the intelligent sensor, and a comprehensive evaluation is performed to establish a neural network model for spraying effect evaluation and output the spraying evaluation results; Step S3. Calculate the spray speed correction parameter according to the output result of the spray effect evaluation model and the curvature of the casting surface; compare the spray speed correction parameter with the preset spray speed correction parameter, and adjust the spray speed according to the comparison result; compare the spray pressure of different parts and different tasks of the casting with the preset spray pressure of different parts and different tasks of the casting, and determine whether to optimize the adjusted spray speed; Step S4. Calculate the spraying liquid flow control parameters according to the obtained nozzle size, coating viscosity and adjusted or optimized spraying speed, and control the spraying liquid flow; Step S5. Monitor the fluctuation of the spraying speed and the spraying liquid flow rate after adjustment to determine the stability of the spraying quality and adjust the multi-robot spraying process of large castings.

2. The adaptive large casting multi-robot collaborative spraying control method according to claim 1 is characterized in that: The step S1 specifically includes: Calculate the evaluation parameters of the spraying task process in the evaluation parameter set of the spraying task process , the assessment scores of different tasks in different sub-parts of large castings are graded; in, Indicates casting The sub-part Assessment parameters for each task; represents the evaluation coefficient; Indicates The operational difficulty coefficient of the task; Indicates The urgency of the time requirements for the task; Indicates sub-part characteristic parameters; definition Indicates the threshold between easy and medium tasks; Indicates the threshold between medium tasks and complex tasks, and grades the scores of different tasks in different sub-parts of large castings. The specific process is as follows: when When the casting The sub-part The spraying task is classified as a simple task, with level 1; when When the casting The sub-part The spraying task is classified as a medium task, with a level of 2; when When the casting The sub-part The spraying task is classified as a complex task with a level of 3.

3. The adaptive large casting multi-robot collaborative spraying control method according to claim 2 is characterized in that: The step S1 specifically includes: The spraying speed is adjusted according to the different spraying task levels of different casting parts. , spraying liquid flow Preset the base spraying speed to , the reference spraying liquid flow rate is ; When the level is 1, the preset first spraying speed is , , Indicates the corresponding first spraying speed adjustment coefficient; When level is 2, the preset first spraying speed is , , Indicates the corresponding second spraying speed adjustment coefficient; When level is 3, the preset first spraying speed is , , Indicates the corresponding third spraying speed adjustment coefficient.

4. The adaptive large casting multi-robot collaborative spraying control method according to claim 1 is characterized in that: The step S2 specifically includes: The spraying effect evaluation neural network model includes input layer, analysis layer, evaluation layer and output layer; In the analysis layer, the input spraying result information of the casting part is analyzed. The specific process is as follows: in, Represents the output of the analysis layer; Represents the input of the analysis layer; represents the learning factor; represents the attenuation coefficient; Indicates the casting sub-part Standard case for class attributes; Indicates The actual characteristic information of the class attributes; Influencing parameters representing the properties of casting part information; Indicates The spraying result information of each casting part.

5. The adaptive large casting multi-robot collaborative spraying control method according to claim 3 is characterized in that: The step S3 calculates the spraying speed correction parameter , as shown below: in, Represents the overall control coefficient, which is used to control the amplitude of change; It represents the benchmark value of the output result of the spraying effect evaluation model; represents a constant coefficient; Indicates the coefficient of variation of casting surface curvature; represents the output result of the spraying effect evaluation model; Indicates the curvature of the casting surface.

6. The adaptive large casting multi-robot collaborative spraying control method according to claim 5 is characterized in that: In step S3, the spraying speed correction parameter Comparison value with preset spray speed correction parameters Compare and adjust the spraying speed according to the comparison results Make adjustments, ; Indicates the first spraying speed, the specific process is as follows: if , then adjust the spraying speed to , then define ; if , then adjust the spraying speed to , then define ; if , then adjust the spraying speed to , then define .

7. The adaptive large casting multi-robot collaborative spraying control method according to claim 6 is characterized in that: The step S3 specifically includes: The obtained spraying pressure of different parts and different tasks of the casting Preset spray pressure for different parts and tasks of castings Compare and decide whether to adjust the spraying speed according to the comparison results. The specific process is as follows: if , it means that the spraying pressure of large castings meets the requirements of spraying work, and there is no need to optimize the spraying speed; if , it means that the spraying pressure of large castings does not meet the requirements of spraying work, and the spraying speed needs to be optimized.

8. The adaptive large casting multi-robot collaborative spraying control method according to claim 1 is characterized in that: In step S4, an index related to the coating properties and flow characteristics is introduced. , calculate the spray liquid flow control parameters The process is as follows: , ,in, Indicates the nozzle size, Indicates the viscosity of the paint. Indicates the adjusted or optimized spraying speed.

9. The adaptive large casting multi-robot collaborative spraying control method according to claim 1 is characterized in that: The step S5 specifically includes: When the standard deviation of the spraying speed Less than the preset spray speed threshold , and the standard deviation of the spraying liquid flow rate Less than the preset spraying liquid flow threshold When the spraying quality is stable, it means that the spraying process is in normal state, but it still needs to be monitored; otherwise, it means that the spraying process may be abnormal and timely measures need to be taken to adjust it.

Images