CN111495633B - Coating closed-loop supply system based on Faster-rcnn and control method - Google Patents
Coating closed-loop supply system based on Faster-rcnn and control method Download PDFInfo
- Publication number
- CN111495633B CN111495633B CN202010340588.0A CN202010340588A CN111495633B CN 111495633 B CN111495633 B CN 111495633B CN 202010340588 A CN202010340588 A CN 202010340588A CN 111495633 B CN111495633 B CN 111495633B
- Authority
- CN
- China
- Prior art keywords
- coating
- mass flow
- paint
- characteristic data
- pressure tank
- 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.)
- Active
Links
- 238000000576 coating method Methods 0.000 title claims abstract description 148
- 239000011248 coating agent Substances 0.000 title claims abstract description 143
- 238000000034 method Methods 0.000 title claims abstract description 27
- 239000003973 paint Substances 0.000 claims abstract description 114
- 238000005507 spraying Methods 0.000 claims abstract description 41
- 239000007788 liquid Substances 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 18
- 239000000463 material Substances 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 10
- 230000005484 gravity Effects 0.000 claims description 9
- 230000001133 acceleration Effects 0.000 claims description 8
- 238000006073 displacement reaction Methods 0.000 claims description 8
- 230000009471 action Effects 0.000 claims description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 3
- 238000013019 agitation Methods 0.000 claims 1
- 230000005693 optoelectronics Effects 0.000 claims 1
- 238000009428 plumbing Methods 0.000 claims 1
- 230000004044 response Effects 0.000 abstract description 7
- 239000007921 spray Substances 0.000 description 8
- 239000012530 fluid Substances 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000002156 mixing Methods 0.000 description 5
- 238000003756 stirring Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000010438 heat treatment Methods 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000004043 responsiveness Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 238000005352 clarification Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002542 deteriorative effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010422 painting Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000007665 sagging Methods 0.000 description 1
- 229910001220 stainless steel Inorganic materials 0.000 description 1
- 239000010935 stainless steel Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05B—SPRAYING APPARATUS; ATOMISING APPARATUS; NOZZLES
- B05B12/00—Arrangements for controlling delivery; Arrangements for controlling the spray area
- B05B12/08—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means
- B05B12/085—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means responsive to flow or pressure of liquid or other fluent material to be discharged
- B05B12/087—Flow or presssure regulators, i.e. non-electric unitary devices comprising a sensing element, e.g. a piston or a membrane, and a controlling element, e.g. a valve
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05B—SPRAYING APPARATUS; ATOMISING APPARATUS; NOZZLES
- B05B12/00—Arrangements for controlling delivery; Arrangements for controlling the spray area
- B05B12/08—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means
- B05B12/081—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means responsive to the weight of a reservoir or container for liquid or other fluent material; responsive to level or volume of liquid or other fluent material in a reservoir or container
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05B—SPRAYING APPARATUS; ATOMISING APPARATUS; NOZZLES
- B05B12/00—Arrangements for controlling delivery; Arrangements for controlling the spray area
- B05B12/08—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means
- B05B12/10—Arrangements for controlling delivery; Arrangements for controlling the spray area responsive to condition of liquid or other fluent material to be discharged, of ambient medium or of target ; responsive to condition of spray devices or of supply means, e.g. pipes, pumps or their drive means responsive to temperature or viscosity of liquid or other fluent material discharged
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B05—SPRAYING OR ATOMISING IN GENERAL; APPLYING FLUENT MATERIALS TO SURFACES, IN GENERAL
- B05B—SPRAYING APPARATUS; ATOMISING APPARATUS; NOZZLES
- B05B15/00—Details of spraying plant or spraying apparatus not otherwise provided for; Accessories
- B05B15/20—Arrangements for agitating the material to be sprayed, e.g. for stirring, mixing or homogenising
- B05B15/25—Arrangements for agitating the material to be sprayed, e.g. for stirring, mixing or homogenising using moving elements, e.g. rotating blades
Landscapes
- Nozzles (AREA)
Abstract
The invention provides a coating closed-loop supply system based on Faster-rcnn, which comprises a coating pressure tank, an air supply pipeline, a proportional valve, a pressure sensor, a liquid level sensor, a coating delivery pipe, a spraying device, a mass flowmeter, a fuzzy controller and a PI controller, wherein the fuzzy controller is used for extracting characteristic data from a mass flow expected value to perform model training to obtain an optimal solution of the characteristic data, constructing an output control table according to the characteristic data and a corresponding mass flow value, obtaining corresponding target characteristic data according to a given mass flow expected value to obtain the opening degree of the corresponding proportional valve, and the PI controller is used for adjusting the opening degree of the proportional valve. The invention combines the fuzzy controller and the PI controller to form a double closed-loop paint supply system, improves the response speed of the system and simultaneously keeps the high precision of the paint supply control of the system. Correspondingly, the invention also provides a coating closed-loop supply system control method based on fast-rcnn.
Description
Technical Field
The invention relates to the technical field of automation, in particular to a coating closed-loop supply system based on Faster-rcnn and a control method.
Background
At present, the existing automatic coating supply system mainly uses a screw pump as a micro-driving source, controls the supply amount of the coating through different rotating speeds, and controls the supply amount through the feedback of an outlet mass flow meter, and the adopted control mode is mostly semi-closed loop or common PID, so that the problem of low response of the whole system is existed.
After a lot of search, some typical prior arts have found that, as shown in fig. 3, patent application No. 201721709944.1 discloses a dosing and mixing system for high viscosity two-component paint, which can precisely control the paint spraying thickness on the surface of the object to be sprayed, avoid the problems of sagging and uneven spraying, and improve the product yield. As shown in fig. 4, patent application No. 201210237982.7 discloses a paint supply system and a paint supply method that can significantly reduce paint loss during cleaning when changing colors of paint, thereby reducing painting costs. As shown in fig. 5, the patent application No. 201910404435.5 discloses a high viscosity liquid paint precise dosing system which can achieve precise dosing of each high viscosity liquid paint before mixing and complete and uniform mixing before spraying.
As can be seen, many practical problems to be solved (such as improvement of system responsiveness) in practical applications of paint supply systems have not been proposed.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a coating closed-loop supply system and a control method based on Faster-rcnn, and the specific technical scheme of the invention is as follows:
a fast-rcnn based closed-loop paint supply system comprising:
a paint pressure tank for storing paint;
the air supply pipeline is used for conveying the compressed air output by the air supply device to the paint pressure tank;
a proportional valve provided above the air supply pipe for controlling the air pressure inputted into the paint pressure tank;
the pressure sensor is arranged on an air supply pipeline between the proportional valve and the coating pressure tank and used for detecting the air pressure borne by the coating in the coating pressure tank;
the liquid level sensor is arranged in the coating pressure tank and used for detecting the liquid level of the coating in the coating pressure tank;
the coating conveying pipe is used for conveying the coating to the spraying device;
the spraying device is used for spraying a workpiece;
a mass flowmeter arranged on the paint delivery pipe for detecting the output mass flow value of the paint in the paint delivery pipeZh；
The coating closed-loop supply system also comprises a fuzzy controller and a PI controller;
the fuzzy controller is used for obtaining the desired value of mass flow by the slave
Extracted characteristic data Δ H and ptPerforming model training to obtain the optimal solution of the characteristic data corresponding to different expected mass flow values, constructing an output control table according to the characteristic data and the mass flow values corresponding to the characteristic data, obtaining target characteristic data corresponding to the given expected mass flow values according to the given expected mass flow values, and obtaining the opening U of the corresponding proportional valve according to the target characteristic data and the output control tablef；
The PI controller is used for adjusting the opening of the proportional valve to output a mass flow value ZhEqual to the desired value of mass flow Zm；
Where ρ is0The density of the coating at standard atmospheric pressure, g is the acceleration of gravity, SdIs the cross-sectional area of the paint delivery pipe, ptIs the air pressure to which the coating is subjected in the coating pressure tank, and Δ H is the air pressure p of the coatingtThe amount of change in displacement under action.
Optionally, a water heating layer is arranged on the outer side of the coating pressure tank.
Optionally, a temperature sensor is arranged in the paint pressure tank.
Optionally, the liquid level sensor is a photoelectric liquid level sensor.
Optionally, the closed-loop paint supply system further comprises a paint feed pipe for delivering paint to the paint pressure tank.
And a stirring device is arranged in the coating pressure tank.
Accordingly, the present invention also provides a method for controlling a coating closed-loop feeding system based on fast-rcnn, which is applied to the coating closed-loop feeding system according to any one of claims 1 to 6, comprising the steps of:
Optionally, in step 2, feature data Δ H and p are extracted from the expected mass flow valuetAnd then, performing model training by using a convolutional neural network.
Optionally, in step 4, after the expected mass flow value is given, target detection is performed on the characteristic data through the fast-rcnn algorithm to obtain target characteristic data.
The beneficial effects obtained by the invention comprise:
1. the air supply device is used for replacing the original screw pump as a coating supply driver, so that the cost of the whole system is reduced, and the high-precision coating supply quantity of the system is also kept.
2. The fuzzy controller and the PI controller are combined to form a double closed-loop paint supply system, so that the response speed of the system is improved, and the high precision of the paint supply control of the system is also kept.
3. The constructed mass flow expected value is subjected to model training by using a convolutional neural network, after the mass flow expected value is given, target characteristic data is obtained by performing target detection on the characteristic data through a Faster-rcnn algorithm, and the corresponding opening degree of the proportional valve is obtained according to the target characteristic data and an output control table, so that the system has strong interference capability on nonlinear influence, has strong expandability and can adapt to different spraying devices and coatings with different characteristics.
Drawings
The present invention will be further understood from the following description taken in conjunction with the accompanying drawings, the emphasis instead being placed upon illustrating the principles of the embodiments.
FIG. 1 is a schematic diagram of the overall structure of a fast-rcnn-based closed-loop paint supply system in accordance with an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a method for controlling a closed-loop coating supply system based on Faster-rcnn in accordance with an embodiment of the present invention;
FIG. 3 is a schematic diagram of a prior art metering and mixing system for high viscosity two-component coatings;
FIG. 4 is a schematic diagram of a prior art paint delivery system and method;
fig. 5 is a schematic diagram showing a prior art system for accurately metering a high viscosity liquid coating material.
Description of reference numerals:
1. a paint pressure tank; 2. an air supply duct; 3. a proportional valve; 4. a pressure sensor; 5. a liquid level sensor; 6. a paint delivery pipe; 7. a spraying device; 8. a mass flow meter; 9. a temperature sensor; 10. a water heating layer; 11. adjusting a valve; 12. and (4) a stirring device.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to embodiments thereof; it should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. Other systems, methods, and/or features of the present embodiments will become apparent to those skilled in the art upon review of the following detailed description. It is intended that all such additional systems, methods, features and advantages be included within this description, be within the scope of the invention, and be protected by the accompanying claims. Additional features of the disclosed embodiments are described in, and will be apparent from, the detailed description that follows.
The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if there is an orientation or positional relationship indicated by the terms "upper", "lower", "left", "right", etc. based on the orientation or positional relationship shown in the drawings, it is only for convenience of describing the present invention and simplifying the description, but it is not intended to indicate or imply that the device or component referred to must have a specific orientation, be constructed in a specific orientation, and be operated, and therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes and are not to be construed as limiting the present patent, and the specific meaning of the terms described above will be understood by those of ordinary skill in the art according to the specific circumstances.
The paint (paint, paint vehicle, etc.) used for spraying is generally prepared by mixing a plurality of raw materials according to a certain proportion, and the stability of the paint has certain timeliness. In addition, the coating has high requirements on the surrounding environment (such as temperature, humidity and the like), and if the quality guarantee time or the environment is not properly treated, the coating will deteriorate, so that the later spraying quality is affected. Moreover, the coating does not have uniform proportioning requirements or production quality requirements in the mass spraying process, and belongs to non-Newtonian fluid, so that uniform management and control are more difficult.
In the face of the problems, the manual spraying production process does not have the problems, and people can automatically control the spraying mode and quality according to production requirements. However, under the conditions of mass production, especially in the fully automatic production environment mainly for special-shaped parts, such as automatic robot spraying for special-shaped parts (e.g. toilet, chair, etc.), the different spraying curved surfaces and requirements, the variable and difficult-to-control environment, and the different spraying requirements of different spraying curved surfaces make the storage and real-time quantitative supply of the coating very important
At present, the existing automatic coating supply system mainly uses a screw pump as a micro-drive source, controls the supply amount of coating through different rotating speeds, and controls the supply amount through the feedback of an outlet mass flow meter, and the adopted control mode is mostly semi-closed loop or common PID, so that the problems of low whole system responsiveness, strong dependence on the accurate supply of the screw pump and the like exist. Meanwhile, as the screw pump depends on a ceramic piece of a quick-wear part and the nature of the coating is variable, the responsiveness and the accuracy of the current system are not strong, and the existing automatic coating supply system is more difficult to meet when the requirement on the supply amount of the coating in the spraying process is variable.
The invention provides a closed-loop paint supply system and a control method based on Faster-rcnn, which utilize an air supply device to replace an original screw pump as a paint supply driver, are based on a Faster-rcnn target detection algorithm and combined with a fuzzy controller and a PI controller, can realize accurate paint supply, accelerate the response time of the system, enable the paint supply to reach a set value more quickly and accurately according to different paint supply quantity requirements and current paint properties, still meet the control requirements for fluid paints with different properties, realize effective spraying of paint change or special-shaped surfaces, and improve the utilization rate of the paint in the spraying process.
The invention will be described with reference to the following examples, which are illustrated in the accompanying drawings:
the first embodiment is as follows:
as shown in fig. 1, a coating closed-loop supply system based on fast-rcnn includes a coating pressure tank 1, an air supply pipe 2, a proportional valve 3, a pressure sensor 4, a liquid level sensor 5, a coating delivery pipe 6, a spray coating device 7, and a mass flow meter 8.
The coating pressure tank 1For storing paint, the air supply line 2 is used to deliver compressed air from an air supply device, which may be an air pump, to the paint pressure tank 1. The proportional valve 3 is provided above the air supply line 2 for controlling the air pressure fed into the paint pressure tank 1. And the pressure sensor 4 is arranged on the air supply pipeline 2 between the proportional valve 3 and the coating pressure tank 1 and is used for detecting the air pressure borne by the coating in the coating pressure tank 1. The liquid level sensor 5 is arranged in the coating pressure tank 1 and used for detecting the liquid level of the coating in the coating pressure tank 1. The coating material conveying pipe 6 is used for conveying coating material to the spraying device 7, and the spraying device 7 is used for spraying workpieces. The mass flowmeter 8 is arranged on the paint conveying pipe 6 and used for detecting the output mass flow value Z of the paint in the paint conveying pipe 6h。
The air pump, namely the air supply device is used as a coating material supply driver to replace the original screw pump, so that the cost of the whole system is reduced, and the high-precision coating material supply amount of the system is also kept.
The output paint flow value can be measured by the mass flow meter 8 and can be converted into a corresponding electrical signal. Where the flow velocity of the flow tube is higher, the density of the fluid will be lower, and where the flow velocity is lower, the density will be higher. Alternatively, the density of the fluid is variable and not constant. Therefore, in order to ensure that the output mass flow value of the coating is controlled to be close to the given mass flow expected value, the pressure of the compressed air delivered to the coating pressure tank 1 by the air supply device needs to be controlled well to achieve high-precision control.
Setting rho0The density of the coating at standard atmospheric pressure, g is the acceleration of gravity, SdIs the cross-sectional area of the paint delivery pipe, ptIs the air pressure to which the coating is subjected in the coating pressure tank 1, and Δ H is the air pressure p of the coatingtThe displacement variation under the action can know that the total pressure of the coating under the compressed air is Pz＝pt+ρ0gΔH＝ρGeneral assemblyg Δ H, density of the coating after compressed air supply from the air supply device
The flow rate of the dope is
According to Pz＝pt+ρ0gΔH＝ρGeneral assemblygΔH、
And
the expected mass flow of the coating can be obtained
The coating closed-loop supply system also comprises a fuzzy controller and a PI controller. The fuzzy controller is used for obtaining the desired value of mass flow by the slave
Extracted characteristic data Δ H and ptPerforming model training to obtain the optimal solution of the characteristic data corresponding to different expected mass flow values, constructing an output control table according to the characteristic data and the mass flow values corresponding to the characteristic data, obtaining target characteristic data corresponding to the given expected mass flow values according to the given expected mass flow values, and obtaining the corresponding opening U of the proportional valve 3 according to the target characteristic data and the output control tablef. The PI controller is used for adjusting the opening of the proportional valve 3 to output a mass flow value ZhEqual to the desired value of mass flow Zm。
The invention combines the fuzzy controller and the PI controller to form a double closed-loop paint supply system, improves the response speed of the system and simultaneously keeps the high precision of the paint supply control of the system.
Accordingly, as shown in fig. 2, the present invention also provides a method for controlling a coating closed-loop feeding system based on Faster-rcnn, comprising the steps of:
In step 2, the characteristic data Δ H and p are extracted from the expected mass flowtAnd then, performing model training by using a convolutional neural network. In step 4, after the expected value of the mass flow is given, target characteristic data are obtained by performing target detection on the characteristic data through a Faster-rcnn algorithm.
Performing model training on the constructed mass flow expected value by using a convolutional neural network, giving the mass flow expected value,target characteristic data are obtained by carrying out target detection on the characteristic data through a fast-rcnn algorithm, and the corresponding opening U of the proportional valve 3 is obtained according to the target characteristic data and an output control tablefThe system has strong interference capability to nonlinear influence and strong expandability, and can adapt to different spraying devices 7 and coatings with different characteristics.
Example two:
as shown in fig. 1, a coating closed-loop supply system based on fast-rcnn includes a coating pressure tank 1, an air supply pipe 2, a proportional valve 3, a pressure sensor 4, a liquid level sensor 5, a coating delivery pipe 6, a spray coating device 7, and a mass flow meter 8.
The paint pressure tank 1 is used for storing paint, and the air supply pipeline 2 is used for conveying compressed air output by an air supply device, which can be an air pump, to the paint pressure tank 1. The proportional valve 3 is provided above the air supply line 2 for controlling the air pressure fed into the paint pressure tank 1. And the pressure sensor 4 is arranged on the air supply pipeline 2 between the proportional valve 3 and the coating pressure tank 1 and is used for detecting the air pressure borne by the coating in the coating pressure tank 1. The liquid level sensor 5 is arranged in the coating pressure tank 1 and used for detecting the liquid level of the coating in the coating pressure tank 1. The coating material conveying pipe 6 is used for conveying coating material to the spraying device 7, and the spraying device 7 is used for spraying workpieces. The mass flowmeter 8 is arranged on the paint conveying pipe 6 and used for detecting the output mass flow value Z of the paint in the paint conveying pipe 6h。
The spray device 7 includes, but is not limited to, a spray gun or a nozzle, which may have different calibers and control modes. As a preferred technical solution, for the spraying devices 7 with different calibers, different pressures and control modes, by establishing different mass flow models and training the mass flow models, a corresponding output control table can be established, and then a mass flow library corresponding to the type of the spray gun device and the spraying pressure is established by using the different output control tables.
The air pump, namely the air supply device is used as a coating material supply driver to replace the original screw pump, so that the cost of the whole system is reduced, and the high-precision coating material supply amount of the system is also kept.
The output paint flow value can be measured by the mass flow meter 8 and can be converted into a corresponding electrical signal. Where the flow velocity of the flow tube is higher, the density of the fluid will be lower, and where the flow velocity is lower, the density will be higher. Alternatively, the density of the fluid is variable and not constant. Therefore, in order to ensure that the output mass flow value of the coating is controlled to be close to the given mass flow expected value, the pressure of the compressed air delivered to the coating pressure tank 1 by the air supply device needs to be controlled well to achieve high-precision control.
Setting rho0The density of the coating at standard atmospheric pressure, g is the acceleration of gravity, SdIs the cross-sectional area of the paint delivery pipe, ptIs the air pressure to which the coating is subjected in the coating pressure tank 1, and Δ H is the air pressure p of the coatingtThe displacement variation under the action can know that the total pressure of the coating under the compressed air is Pz＝pt+ρ0gΔH＝ρGeneral assemblyg Δ H, density of the coating after compressed air supply from the air supply device
The flow rate of the dope is
According to Pz＝pt+ρ0gΔH＝ρGeneral assemblygΔH、
And
the expected mass flow of the coating can be obtained
The coating closed-loop supply system also comprises a fuzzy controller and a PI controller. The fuzzy controller is used for obtaining the desired value of mass flow by the slave
Extracted characteristic data Δ H and ptPerforming model training to obtain the optimal solution of the characteristic data corresponding to different expected mass flow values, constructing an output control table according to the characteristic data and the mass flow values corresponding to the characteristic data, obtaining target characteristic data corresponding to the given expected mass flow values according to the given expected mass flow values, and obtaining the corresponding opening U of the proportional valve 3 according to the target characteristic data and the output control tablef. The PI controller is used for adjusting the opening of the proportional valve 3 to output a mass flow value ZhEqual to the desired value of mass flow Zm。
The invention combines the fuzzy controller and the PI controller to form a double closed-loop paint supply system, improves the response speed of the system and simultaneously keeps the high precision of the paint supply control of the system.
The coating pressure tank 1 is made of stainless steel material, and a water heating layer 10 is arranged on the outer side of the coating pressure tank. The water heating layer 10 can stably maintain the paint stored in the paint pressure tank 1 in a certain temperature range, and further stabilize the fluid performance, inflow viscosity, flow rate and the like of the paint.
And an automatic pressure relief device is further arranged on the air supply pipeline 2 so as to conveniently and quickly adjust the air pressure in the coating pressure tank 1.
The paint pressure tank 1 is provided with a temperature sensor 9 which is a thermistor temperature sensor 9 to monitor the temperature of the paint and reduce the influence of the paint property on the supply flow rate. The liquid level sensor 5 is a photoelectric liquid level sensor 5 and is used for monitoring the liquid level of the coating in the coating pressure tank 1 in real time and reducing the influence of the gravity of the coating on the supply amount of the coating.
The closed-loop paint supply system also includes a paint feed tube for delivering paint to the paint pressure tank 1. The coating pressure tank 1 is provided with a variable-frequency speed-regulating stirring device 12, and the stirring device 12 is used for stirring the coating so as to increase the activity of the coating and maintain the properties of the coating, such as viscosity, temperature and the like.
As a preferred technical scheme, an adjusting valve 11 and a filter are further arranged in the air supply pipeline 2 and are respectively used for controlling the air inflow and filtering out impurities in the air so as to prevent the paint from deteriorating.
Accordingly, as shown in fig. 2, the present invention also provides a method for controlling a coating closed-loop feeding system based on Faster-rcnn, comprising the steps of:
In step 2, the characteristic data Δ H and p are extracted from the expected mass flowtThen, convolution is appliedAnd carrying out model training by the neural network. In step 4, after the expected value of the mass flow is given, target characteristic data are obtained by performing target detection on the characteristic data through a Faster-rcnn algorithm.
Performing model training on the constructed mass flow expected value by using a convolutional neural network, after the mass flow expected value is given, performing target detection on the characteristic data by using a Faster-rcnn algorithm to obtain target characteristic data, and obtaining the corresponding opening U of the proportional valve 3 according to the target characteristic data and an output control tablefThe system has strong interference capability to nonlinear influence and strong expandability, and can adapt to different spraying devices 7 and coatings with different characteristics.
In this embodiment, the spraying device 7 is a spraying spray gun, and the closed-loop paint supply system further includes a spray gun library, and the spray gun library is composed of output control tables corresponding to different types of spraying spray guns. By constructing a spray gun magazine, the flexibility and range of applicability of a closed loop paint supply system can be improved.
And selecting NB, NS, ZO, PS and PM by fuzzy language of the fuzzy controller. The characteristic data Δ H and ptAs input, proportional valve 3UfAnd as an output control quantity, after the fuzzy controller is converted into a fuzzy quantity through a quantization factor, a scale factor and a fuzzy language, a rule table is constructed according to spraying experience, then an output decision table is obtained, and finally, the output accurate quantity, namely the required paint supply quantity, can be obtained through fuzzy clarification.
By adjusting the air pressure of the air supply device and the opening of the proportional valve 3, the air pressure in the paint pressure tank 1 can be adjusted, and the required paint supply amount can be adjusted. In the process, the mass flowmeter 8 detects whether the mass flow value of the coating in the coating conveying pipe 6 is matched with a given mass flow expected value, if the mass flow value and the given mass flow expected value are deviated, errors can be eliminated through the PI controller, and the control precision is improved.
In summary, the coating closed-loop supply system and the control method based on fast-rcnn disclosed by the invention have the following beneficial technical effects:
1. the air supply device is used for replacing the original screw pump as a coating supply driver, so that the cost of the whole system is reduced, and the high-precision coating supply quantity of the system is also kept.
2. The fuzzy controller and the PI controller are combined to form a double closed-loop paint supply system, so that the response speed of the system is improved, and the high precision of the paint supply control of the system is also kept.
3. The constructed mass flow expected value is subjected to model training by using a convolutional neural network, after the mass flow expected value is given, target characteristic data is obtained by performing target detection on the characteristic data through a Faster-rcnn algorithm, and the corresponding opening degree of the proportional valve is obtained according to the target characteristic data and an output control table, so that the system has strong interference capability on nonlinear influence, has strong expandability and can adapt to different spraying devices and coatings with different characteristics.
Although the invention has been described above with reference to various embodiments, it should be understood that many changes and modifications may be made without departing from the scope of the invention. That is, the methods, systems, and devices discussed above are examples, and various configurations may omit, replace, or add various processes or components as appropriate. For example, in alternative configurations, the methods may be performed in an order different than that described and/or various components may be added, omitted, and/or combined. Moreover, features described with respect to certain configurations may be combined in various other configurations, as different aspects and elements of the configurations may be combined in a similar manner. Further, elements therein may be updated as technology evolves, i.e., many of the elements are examples and do not limit the scope of the disclosure or claims.
Specific details are given in the description to provide a thorough understanding of the exemplary configurations including implementations. However, configurations may be practiced without these specific details, such as well-known circuits, processes, algorithms, structures, and techniques, which have been shown without unnecessary detail in order to avoid obscuring the configurations. This description provides example configurations only, and does not limit the scope, applicability, or configuration of the claims. Rather, the foregoing description of the configurations will provide those skilled in the art with an enabling description for implementing the described techniques. Various changes may be made in the function and arrangement of elements without departing from the spirit or scope of the disclosure.
It is intended that the foregoing detailed description be regarded as illustrative rather than limiting, and that it be understood that it is the following claims, including all equivalents, that are intended to define the spirit and scope of this invention. The above examples are to be construed as merely illustrative and not limitative of the remainder of the disclosure. After reading the description of the invention, the skilled person can make various changes or modifications to the invention, and these equivalent changes and modifications also fall into the scope of the invention defined by the claims.
Claims (8)
1. A fast-rcnn based closed-loop paint supply system comprising:
a paint pressure tank for storing paint;
the air supply pipeline is used for conveying the compressed air output by the air supply device to the paint pressure tank;
a proportional valve provided above the air supply pipe for controlling the air pressure inputted into the paint pressure tank;
the pressure sensor is arranged on an air supply pipeline between the proportional valve and the coating pressure tank and used for detecting the air pressure borne by the coating in the coating pressure tank;
the liquid level sensor is arranged in the coating pressure tank and used for detecting the liquid level of the coating in the coating pressure tank;
the coating conveying pipe is used for conveying the coating to the spraying device;
the spraying device is used for spraying a workpiece;
a mass flowmeter arranged on the paint delivery pipe for detecting the output mass flow value Z of the paint in the paint delivery pipeh；
The system is characterized by also comprising a fuzzy controller and a PI controller;
the fuzzy controller is used for obtaining the desired value of mass flow by the slave
Extracted characteristic data Δ H and ptPerforming model training to obtain the optimal solution of the characteristic data corresponding to different expected mass flow values, constructing an output control table according to the characteristic data and the mass flow values corresponding to the characteristic data, performing target detection on the characteristic data through a fast-rcnn algorithm according to the expected mass flow values to obtain target characteristic data corresponding to the expected mass flow values, and obtaining the corresponding opening U of the proportional valve according to the target characteristic data and the output control tablef；
The PI controller is used for adjusting the opening of the proportional valve to output a mass flow value ZhEqual to the desired value of mass flow Zm；
Where ρ is0The density of the coating at standard atmospheric pressure, g is the acceleration of gravity, SdIs the cross-sectional area of the paint delivery pipe, ptIs the air pressure to which the coating is subjected in the coating pressure tank, and Δ H is the air pressure p of the coatingtAmount of change in displacement under influence, pGeneral assemblyThe compressed density of the compressed air supplied to the coating material in the air supply device,
is the flow rate of the dope.
2. The fast-rcnn-based closed-loop paint supply system as claimed in claim 1, wherein the outside of the paint pressure tank is provided with a plumbing layer.
3. The fast-rcnn-based closed-loop paint supply system of claim 2, wherein the paint pressure tank is provided with a temperature sensor.
4. The fast-rcnn-based closed-loop paint supply system of claim 3, wherein the level sensor is an opto-electronic level sensor.
5. The fast-rcnn-based closed-loop paint supply system of claim 4, further comprising a paint feed tube for delivering paint to the paint pressure tank.
6. The fast-rcnn-based closed-loop paint supply system of claim 5, wherein the paint pressure tank is provided with an agitation device.
7. A method for controlling a closed-loop paint supply system based on fast-rcnn, applied to the closed-loop paint supply system according to any one of claims 1 to 6, comprising the steps of:
step 1, constructing the expected value of mass flow of the coating
Where ρ is0The density of the coating at standard atmospheric pressure, g is the acceleration of gravity, SdIs the cross-sectional area, p, of the paint delivery pipeGeneral assemblyThe compressed density of the compressed air supplied to the coating material in the air supply device,
flow rate of the dope, ptThe air pressure to which the paint in the paint pressure tank is subjected;
step 2, extracting characteristic data delta H and p from the expected value of mass flowtModel training is carried out to obtain the optimal solution of the characteristic data corresponding to different mass flow expected values, wherein delta H is the air pressure p of the coatingtDisplacement variation under action;
step 3, constructing an output control table according to the characteristic data and the mass flow value corresponding to the characteristic data;
step 4, giving a mass flow expected value, carrying out target detection on the characteristic data through a Faster-rcnn algorithm to obtain target characteristic data corresponding to the given mass flow expected value, and outputting the target characteristic data according to the target characteristic dataThe control table is obtained to obtain the corresponding opening U of the proportional valvef；
Step 5, measuring the output mass flow value Z of the coating in the coating conveying pipehComparing the output mass flow value ZhWith desired value of mass flow ZmIf the mass flow value Z is outputhWith desired value of mass flow ZmIf there is deviation, the opening of the proportional valve is adjusted by the PI controller until the mass flow value Z is outputhEqual to the desired value of mass flow Zm。
8. The fast-rcnn-based closed-loop paint supply system control method as claimed in claim 7, wherein in step 2, the characteristic data Δ H and p are extracted from the desired mass flow ratetAnd then, performing model training by using a convolutional neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010340588.0A CN111495633B (en) | 2020-04-26 | 2020-04-26 | Coating closed-loop supply system based on Faster-rcnn and control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010340588.0A CN111495633B (en) | 2020-04-26 | 2020-04-26 | Coating closed-loop supply system based on Faster-rcnn and control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111495633A CN111495633A (en) | 2020-08-07 |
| CN111495633B true CN111495633B (en) | 2021-04-27 |
Family
ID=71866293
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010340588.0A Active CN111495633B (en) | 2020-04-26 | 2020-04-26 | Coating closed-loop supply system based on Faster-rcnn and control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111495633B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114377874B (en) * | 2022-01-11 | 2024-01-12 | 孙文英 | Flow monitoring method and device for spraying equipment and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1034009A1 (en) * | 1997-11-25 | 2000-09-13 | The Technology Partnership Public Limited Company | Aerosol delivery method and apparatus |
| US6517891B1 (en) * | 2000-10-31 | 2003-02-11 | Nordson Corporation | Control system for metering pump and method |
| CN1592844A (en) * | 2001-11-26 | 2005-03-09 | 美国艾默生电气公司 | High purity fluid delivery system |
| CN101454735A (en) * | 2006-04-28 | 2009-06-10 | 先进能源工业公司 | Adaptive response time closed loop control algorithm |
| CN107206407A (en) * | 2015-01-07 | 2017-09-26 | 诺信公司 | Fuid distribution system |
-
2020
- 2020-04-26 CN CN202010340588.0A patent/CN111495633B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1034009A1 (en) * | 1997-11-25 | 2000-09-13 | The Technology Partnership Public Limited Company | Aerosol delivery method and apparatus |
| US6517891B1 (en) * | 2000-10-31 | 2003-02-11 | Nordson Corporation | Control system for metering pump and method |
| CN1592844A (en) * | 2001-11-26 | 2005-03-09 | 美国艾默生电气公司 | High purity fluid delivery system |
| CN101454735A (en) * | 2006-04-28 | 2009-06-10 | 先进能源工业公司 | Adaptive response time closed loop control algorithm |
| CN107206407A (en) * | 2015-01-07 | 2017-09-26 | 诺信公司 | Fuid distribution system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111495633A (en) | 2020-08-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103826760B (en) | Coating cyclic device and coating cyclic method | |
| US5330783A (en) | Method and apparatus for forming and dispensing single and multiple phase coating material containing fluid diluent | |
| CN107649079B (en) | A kind of carbon fiber production polymerization reactor control device and method | |
| US11492786B2 (en) | Method for fluid pressure control in a closed system | |
| CN107512754B (en) | Automatic powder activated carbon dosing control system for water treatment | |
| CN111495633B (en) | Coating closed-loop supply system based on Faster-rcnn and control method | |
| CN102641803A (en) | Single flowmeter type digital spraying system for robot | |
| JP6636945B2 (en) | Correction method for flow control in transient system. | |
| CN102632003A (en) | Dual-flow-meter type digital spraying system for robot | |
| CN111515054A (en) | High-precision spraying double-closed-loop supply system | |
| JP2002523216A (en) | Powder spray coating equipment | |
| CN113157010B (en) | Method and device for regulating and controlling thrust of deep variable thrust engine and electronic equipment | |
| CN201086055Y (en) | Spray coating control system for mineral wool acoustic board surface | |
| KR101722405B1 (en) | Method and apparatus for controlling acid concentration for pickling in cold rolling | |
| CN111468326B (en) | PID control method and coating closed-loop supply system | |
| CN114061891A (en) | Downward-blowing injection type static pressure matching control method for large-size open jet wind tunnel | |
| CN112172129A (en) | Operation method of 3D printer nozzle temperature self-adaptive Fuzzy-PID control system | |
| CN106944307A (en) | A kind of ultrasonic wave coating fluid temperature regulating device and method | |
| CN212702776U (en) | Liquid supply device for intermittent coating | |
| CN108554669A (en) | A kind of nozzle, coating machine and coating method | |
| CN202667047U (en) | Double-flowmeter digitization spraying system for robot | |
| CN207699239U (en) | A kind of Powdered Activated Carbon Automatic Dosage Control of Additives system for water process | |
| CN202538993U (en) | Single-flowmeter type digital spray system for robot | |
| CN206897759U (en) | A kind of fully-automatic paint replenishment system | |
| CN113935243A (en) | Real-time optimization control method and system for granularity of sintering mixture |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20200807 Assignee: Xinlisheng Environmental Protection Technology (Yunfu) Co.,Ltd. Assignor: FOSHAN University Contract record no.: X2023980033052 Denomination of invention: A Closed-loop Coating Supply System and Control Method Based on Faster-rcnn Granted publication date: 20210427 License type: Common License Record date: 20230301 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230808 Address after: No.33, Guangyun Road, Nanhai District, Foshan City, Guangdong Province, 528200 Patentee after: FOSHAN University Patentee after: SHENZHEN POLYTECHNIC Patentee after: Jiangsu Peipu Polymer Technology Co.,Ltd. Address before: No.33 Guangyun Road, Nanhai District, Foshan City, Guangdong Province Patentee before: FOSHAN University |
|
| TR01 | Transfer of patent right | ||
| CP03 | Change of name, title or address |
Address after: No.33, Guangyun Road, Nanhai District, Foshan City, Guangdong Province, 528200 Patentee after: Foshan University Country or region after: China Patentee after: SHENZHEN POLYTECHNIC Patentee after: Jiangsu Peipu Polymer Technology Co.,Ltd. Address before: No.33, Guangyun Road, Nanhai District, Foshan City, Guangdong Province, 528200 Patentee before: FOSHAN University Country or region before: China Patentee before: SHENZHEN POLYTECHNIC Patentee before: Jiangsu Peipu Polymer Technology Co.,Ltd. |
|
| CP03 | Change of name, title or address |