Flow channel cleaning machine cleanliness detection system based on image recognition

Abstract

The invention relates to the technical field of cleanliness detection, in particular to a runner cleaning machine cleanliness detection system based on image recognition, and the system comprises a runner cleaning machine which comprises a cleaning part and a water supply part, and the water supply part is used for providing high-pressure circulating water for the cleaning part; the data acquisition module is connected with the cleaning part and is used for acquiring the water outlet flow in the water outlet interface; the detection module is connected with the cleaning part and used for obtaining the particle concentration, the particle change rate and the particle number in the water return connector; and the control module is connected with the cleaning part, the data acquisition module and the detection module, and is used for determining a cleaning mode according to the particle change rate, changing the cleaning mode under the condition of judging that the cleaning mode is unqualified according to the particle concentration, and judging the qualification of cleaning according to whether particles exist in a backwater interface after the flow channel is blow-dried or not. According to the invention, the accuracy of cleanliness detection is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cleanliness detection, and in particular to a cleanliness detection system for a flow channel cleaning machine based on image recognition. Background Art

[0002] In modern industrial manufacturing, flow channel cleanliness directly impacts product performance, lifespan, and safety. For example, tiny particles in a car engine's fuel system can clog the injectors, while contaminants in semiconductor device cooling channels can reduce heat dissipation efficiency and even cause equipment failure. Therefore, flow channel cleaning is an essential and critical process in the production process. Traditional flow channel cleanliness inspection methods rely primarily on manual observation of the flow channel inner wall using the naked eye or an endoscope. However, this method is inefficient, highly subjective, and difficult to detect micron-sized particles.

[0003] Chinese patent application publication number: CN101482453A, discloses a cleaning machine detection system, including detection equipment, display instrument, setting computer, and alarm. The detection equipment is connected to the computer via a data cable, and the detected data can be automatically stored in the computer. The parameters are set in the computer. If the detection value is out of range or the machine fails, the alarm will automatically sound an alarm. The automatic detection system thus formed uses a computer to automatically record data with high efficiency and no reading error or recording error. The alarm is set to detect problems in time so that they can be solved in time. The present invention is applied to the detection of cleaning machines, and uses a computer to automatically record, avoiding manual recording and effectively improving work efficiency.

[0004] However, the prior art has the following problems: the prior art can only realize detection but cannot realize automatic control of detection and adjustment. Summary of the Invention

[0005] To this end, the present invention provides a flow channel cleaning machine cleanliness detection system based on image recognition to overcome the problem in the prior art that the detection system is not sufficiently automated, resulting in low detection accuracy and thus affecting the cleanliness of the cleaning machine.

[0006] To achieve the above objectives, the present invention provides a flow channel cleaning machine cleanliness detection system based on image recognition, comprising: The flow channel cleaning machine includes a cleaning unit and a water supply unit. The water supply unit is used to provide high-pressure circulating water to the cleaning unit. The cleaning unit is a box provided with a flip cover. Several layers of cleaning platforms are provided inside the box. Each cleaning platform includes several cleaning modules. Among them, each cleaning module is provided with an oscillating table for placing the mold to be cleaned, a water outlet interface and a water return interface. a data acquisition module connected to the cleaning unit and configured to collect the water flow rate in the water outlet interface; A detection module, connected to the cleaning unit, is used to collect images of the solution in the return water interface through image recognition technology and analyze and calculate the particle concentration, particle change rate and particle number in the solution; A control module is respectively connected to the cleaning part, the data acquisition module and the detection module, and is used to determine the cleaning mode according to the particle change rate under the first preset cleaning time, change the cleaning mode under the condition that the cleaning mode is unqualified according to the particle concentration under the second preset cleaning time, and determine the eligibility of the cleaning according to whether there are particles in the return water interface after the flow channel is blown dry, and optimize the cleaning mode threshold under the condition that the cleaning is unqualified.

[0007] Furthermore, the water supply unit includes a filter unit for filtering return water and a water storage unit, wherein the filter unit includes a filter water tank, an internal circulation water pump and several filters, and the water storage unit includes a flushing water tank and a centrifugal pump.

[0008] Furthermore, a vibration generator is provided at the center of the bottom of the oscillation table, and the four corners of the bottom of the oscillation table are connected to the cleaning platform through vibration springs.

[0009] Furthermore, the cleaning portion is further provided with an air supply unit, and the air supply unit is provided with an air source filter and a blowing air source filtering device.

[0010] Furthermore, the data acquisition module includes a flow sensor arranged in the water outlet interface, and a pressure sensor arranged in the air supply channel and the water outlet channel.

[0011] Furthermore, the control module determines a cleaning mode according to a particle change rate under a first preset cleaning time, wherein the cleaning modes are divided into levels one to four; If the particle change rate is less than the first preset change rate, the cleaning mode is determined to be a four-level cleaning mode, wherein the four-level cleaning mode adopts a pulse flushing combined with vibration method; If the particle change rate is greater than or equal to the first preset change rate and less than the second preset change rate, the cleaning mode is determined to be a three-level cleaning mode, and the three-level cleaning mode adopts a pulse flushing method; If the particle change rate is greater than or equal to the second preset change rate and less than the third preset change rate, the cleaning mode is determined to be a secondary cleaning mode, and the secondary cleaning mode adopts a forward flushing combined with a reverse flushing method; If the particle change rate is greater than or equal to the third preset change rate, the cleaning mode is determined to be a primary cleaning mode, and the primary cleaning mode adopts a forward flushing method.

[0012] Furthermore, the control module determines the eligibility of the cleaning mode according to the particle concentration under the second preset cleaning time, wherein, If the particle concentration is less than the first preset particle concentration, the cleaning mode is determined to be qualified, and the flow channel is blown dry after cleaning is completed in the current cleaning mode; If the particle concentration is greater than or equal to the first preset particle concentration and less than the second preset particle concentration, the cleaning mode is determined to be unqualified, and the water flow rate is increased according to the difference between the particle concentration and the first preset particle concentration; If the particle concentration is greater than or equal to the second preset particle concentration, the cleaning mode is determined to be unqualified and the cleaning mode level is increased by one level.

[0013] Furthermore, the water outlet flow rate is positively correlated with a particle concentration difference, wherein the particle concentration difference is a difference between the particle concentration and the first preset particle concentration.

[0014] Furthermore, the control module determines the eligibility of the cleaning based on whether there are particles in the return water interface after the flow channel is blown dry, wherein, if there are particles in the return water interface, the cleaning is determined to be unqualified, and the cleaning mode threshold is optimized according to the number of particles, and the cleaning mode threshold includes a first preset change rate and a second preset change rate; if there are no particles in the return water interface, the cleaning is determined to be qualified, and the cleanliness detection of the flow channel cleaning machine is completed.

[0015] Furthermore, several adjustment methods are provided for the cleaning mode threshold, and each adjustment method has a different adjustment range for the cleaning mode threshold.

[0016] Compared with the existing technology, the beneficial effect of the present invention is that the present invention monitors the water flow rate in real time through the data acquisition module, and combines the detection module with the multi-dimensional analysis of particle concentration, change rate and number, thereby realizing dynamic regulation of the cleaning process, significantly reducing the need for manual intervention, and improving the automation level of the detection system.

[0017] Furthermore, the present invention divides the cleaning modes into one to four levels, and determines the cleaning mode according to the particle change rate under the first preset cleaning time. It can determine the stain situation inside the mold flow channel to be cleaned according to the particle change rate in the return water interface, thereby determining the corresponding cleaning mode, thereby improving the cleaning efficiency and detection flexibility.

[0018] Furthermore, the present invention adjusts the mode or parameters in real time according to the particle concentration under the second preset time period, ensuring that the cleaning strategy is accurately matched with the pollution level, thereby improving the cleaning efficiency.

[0019] Furthermore, the present invention detects the returned water particles after drying, and automatically optimizes the cleaning mode threshold if it fails to meet the standards, forming a closed-loop feedback, so that the system can adapt to different pollution scenarios and maintain high detection accuracy for a long time.

[0020] Furthermore, the present invention integrates flow and pressure sensors and particle detection units, combines with an oscillation table vibration generator and an air supply filter device, and covers the entire process from physical cleaning to air drying, effectively avoiding residual contamination and ensuring the reliability of cleanliness determination.

[0021] Furthermore, the present invention is provided with a cleaning module with a layered layout, which supports parallel processing of multiple components, and the water supply filtration and water storage units are separated to facilitate maintenance and upgrades. The system can flexibly expand the detection dimension or adjust the threshold parameters according to needs, thereby improving applicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a schematic structural diagram of a flow channel cleaning machine according to an embodiment of the present invention; Figure 2 This is a schematic diagram of module connections of a flow channel cleaning machine cleanliness detection system based on image recognition according to an embodiment of the present invention; Figure 3 This is a schematic structural diagram of a water supply unit according to an embodiment of the present invention; Figure 4 This is a schematic structural diagram of a cleaning module according to an embodiment of the present invention; Figure 5 A flow chart of determining the eligibility of a cleaning mode according to an embodiment of the present invention; Figure 6 This is a schematic structural diagram of a mold runner according to an embodiment of the present invention; In the figure: 1. Box body; 11. Flip cover; 12. Gas spring; 13. Cleaning platform; 14. Cleaning module; 141. Oscillation table; 142. Water outlet interface; 143. Return water interface; 144. Vibration generator; 145. Vibration spring; 15. Air source filter; 16. Blowing air source filter device; 2. Water supply unit; 21. Filter; 22. Filter water tank; 23. Flushing water tank; 24. Centrifugal pump; 25. Internal circulation water pump. DETAILED DESCRIPTION

[0023] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should 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.

[0024] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0025] It should be pointed out that the data in this embodiment are obtained by comprehensive analysis and evaluation of the historical test data and the corresponding historical test results of the three months before this test. It can be understood by those skilled in the art that the present invention can determine the above parameters for a single item by selecting the value with the highest proportion as the preset standard parameter based on the data distribution, using weighted summation to use the obtained value as the preset standard parameter, substituting each historical data into a specific formula and using the value obtained by the formula as the preset standard parameter or other selection methods, as long as the present invention can clearly define the different specific situations in the single determination process through the obtained values.

[0026] See also Figures 1 to 6 As shown, they are respectively a structural schematic diagram of the flow channel cleaning machine according to an embodiment of the present invention; a module connection schematic diagram of the flow channel cleaning machine cleanliness detection system based on image recognition according to an embodiment of the present invention; a structural schematic diagram of the water supply part according to an embodiment of the present invention; a structural schematic diagram of the cleaning module according to an embodiment of the present invention; a flow chart for determining the eligibility of the cleaning mode according to an embodiment of the present invention; and a structural schematic diagram of the mold flow channel according to an embodiment of the present invention.

[0027] The cleanliness detection system of a flow channel cleaning machine based on image recognition in an embodiment of the present invention includes: The flow channel cleaning machine includes a cleaning section and a water supply section 2. The water supply section 2 is used to provide high-pressure circulating water to the cleaning section. The cleaning section is a box 1 provided with a flip cover 11. Several layers of cleaning platforms 13 are provided inside the box 1. Each layer of the cleaning platform 13 includes several cleaning modules 14. Among them, each cleaning module 14 is provided with an oscillating table 141 for placing the mold to be cleaned, a water outlet interface 142 and a water return interface 143. A data acquisition module connected to the cleaning unit for collecting the water flow rate in the water outlet interface 142; A detection module, connected to the cleaning unit, is used to collect images of the solution in the return water interface 143 using image recognition technology and analyze and calculate the particle concentration, particle change rate, and particle number in the solution; A control module is respectively connected to the cleaning part, the data acquisition module and the detection module, and is used to determine the cleaning mode according to the particle change rate under the first preset cleaning time, change the cleaning mode under the condition that the cleaning mode is unqualified according to the particle concentration under the second preset cleaning time, and determine the eligibility of the cleaning according to whether there are particles in the return water interface 143 after the dry flow channel, and optimize the cleaning mode threshold under the condition that the cleaning is unqualified.

[0028] Specifically, the flip cover 11 is opened and closed by a gas spring 12 connected to the box body 1 .

[0029] Specifically, the detection module is provided with a high-resolution industrial camera, a laser scattering sensor and a particle counter, which are combined with an image analysis algorithm to obtain the particle concentration, particle change rate and particle number in the return water interface 143.

[0030] Specifically, the water supply unit 2 includes a filter unit for filtering return water and a water storage unit, wherein the filter unit includes a filter water tank 22, an internal circulation water pump 25 and several filters 21, and the water storage unit includes a flushing water tank 23 and a centrifugal pump 24.

[0031] Specifically, a vibration generator 144 is provided at the center of the bottom of the oscillation table 141 , and the four corners of the bottom of the oscillation table 141 are connected to the cleaning platform 13 through vibration springs 145 .

[0032] Specifically, the cleaning portion is further provided with an air supply unit, and the air supply unit is provided with an air source filter 15 and a blowing air source filter device 16 .

[0033] In the embodiment of the present invention, the air supply pressure control range is 0-0.6 MPa.

[0034] Specifically, the data acquisition module includes a flow sensor disposed in the water outlet interface 142 and pressure sensors disposed in the air supply channel and the water outlet channel.

[0035] In an embodiment of the present invention, the flow sensor is a clamp-type flow meter.

[0036] Specifically, the control module determines a cleaning mode according to a particle change rate under a first preset cleaning time of 1 minute, wherein the cleaning modes are divided into levels one to four; If the particle change rate is less than a first preset change rate of 0.5 mg / (cm²•min), the cleaning mode is determined to be a four-level cleaning mode, which uses a pulse flushing combined with vibration method; If the particle change rate is greater than or equal to the first preset change rate and less than the second preset change rate of 1.0 mg / (cm²•min), the cleaning mode is determined to be the third-level cleaning mode, and the third-level cleaning mode adopts a pulse flushing method; If the particle change rate is greater than or equal to the second preset change rate and less than the third preset change rate of 1.8 mg / (cm²•min), the cleaning mode is determined to be a secondary cleaning mode, and the secondary cleaning mode adopts a forward flushing combined with a reverse flushing method; If the particle change rate is greater than or equal to the third preset change rate, the cleaning mode is determined to be a primary cleaning mode, and the primary cleaning mode adopts a forward flushing method.

[0037] Specifically, the forward flushing is that water is passed into the mold from the water outlet interface 142 and then flows out from the water return interface 143 ; the reverse flushing is that water is passed into the mold from the water return interface 143 and then flows out from the water outlet interface 142 .

[0038] Specifically, Figure 6 The flow direction of water for forward flushing or reverse flushing of the mold flow channel is shown, and is not specifically limited.

[0039] Specifically, the particle change rate refers to the amount of change in particle concentration over time.

[0040] In an embodiment of the present invention, the first preset cleaning time is 1 minute, the first preset change rate is 0.5 mg / (cm²•min), the second preset change rate is 1.0 mg / (cm²•min), and the third preset change rate is 1.8 mg / (cm²•min), but the above values ​​are not limited to these. Those skilled in the art can adjust the values ​​according to actual needs.

[0041] Specifically, the water outlet interface 142 and the water return interface 143 are connected to the flow channel inlet and outlet of the mold to be cleaned through a three-way valve. The control module switches the cleaning mode by adjusting the direction and opening and closing of the three-way valve. The four-level cleaning mode vibrates the oscillation table 141 by turning on the vibration generator 144.

[0042] Specifically, by cleaning the mold to be cleaned for a first preset time, the contamination condition inside the flow channel of the mold to be cleaned can be determined based on the particle change rate in the return water interface 143, thereby determining the corresponding cleaning mode, thereby improving cleaning efficiency and detection flexibility.

[0043] Specifically, the control module determines the eligibility of the cleaning mode according to the particle concentration under the second preset cleaning time of 5 minutes, wherein: If the particle concentration is less than the first preset particle concentration of 5 particles / mL, the cleaning mode is determined to be qualified, and the flow channel is blown dry after cleaning is completed in the current cleaning mode; If the particle concentration is greater than or equal to the first preset particle concentration and less than the second preset particle concentration of 10 particles / mL, the cleaning mode is determined to be unqualified, and the water flow rate is increased according to the difference between the particle concentration and the first preset particle concentration; If the particle concentration is greater than or equal to the second preset particle concentration, the cleaning mode is determined to be unqualified and the cleaning mode level is increased by one level.

[0044] In an embodiment of the present invention, the second preset cleaning time is 5 minutes, the first preset particle concentration is 5 particles / mL, and the second preset particle concentration is 10 particles / mL, but the above values ​​are not limited to these. Those skilled in the art can adjust the values ​​according to actual needs.

[0045] Specifically, the cleaning mode level is increased by one level, for example, from level one to level two. Based on the condition that the cleaning mode is unqualified and the cleaning mode is already level four, the upgrade is not performed, and the first preset cleaning time is extended to 5 minutes.

[0046] Specifically, the water flow rate is positively correlated with the particle concentration difference, wherein if the particle concentration difference is less than a first preset particle concentration difference of 2 particles / mL, the water flow rate is adjusted to the corresponding value using a first flow adjustment coefficient of 3; If the particle concentration difference is greater than or equal to the first preset particle concentration difference and less than the second preset particle concentration difference of 4 particles / mL, the outlet water flow rate is adjusted to the corresponding value using the second flow adjustment coefficient 5; If the particle concentration difference is greater than or equal to the second preset particle concentration difference, the outlet water flow rate is adjusted to a corresponding value using a third flow adjustment coefficient 7; The particle concentration difference is a difference between the particle concentration and the first preset particle concentration.

[0047] In an embodiment of the present invention, the initial water outlet flow rate is set to 1 L / min, the flow rate control range is 0.5 to 10 L / min, the first preset particle concentration difference is 2 particles / mL, and the second preset particle concentration difference is 4 particles / mL, but the above values ​​are not limited to this. Those skilled in the art can adjust the value according to actual needs.

[0048] Specifically, the control module determines the eligibility of the cleaning based on whether there are particles in the return water interface 143 after the flow channel is blown dry. If there are particles in the return water interface 143, the cleaning is determined to be unqualified, and the cleaning mode threshold is optimized according to the number of particles. The cleaning mode threshold includes a first preset change rate and a second preset change rate. If there are no particles in the return water interface 143, the cleaning is determined to be qualified, and the cleanliness detection of the flow channel cleaning machine is completed.

[0049] Specifically, by detecting whether there are particles in the return water interface 143 after the flow channel is blown dry, it can be inferred whether the flow channel is cleaned. If particles exist, it means that there are stains in the flow channel that have not been flushed away, but have been blown out by drying. Therefore, the cleaning mode threshold needs to be optimized.

[0050] Specifically, several adjustment methods are provided for the cleaning mode threshold, and each adjustment method has a different adjustment range for the cleaning mode threshold. If the number of particles is less than a first preset number of particles of 100, the first threshold adjustment coefficient of 0.85 is used to reduce the cleaning mode threshold to the corresponding value. If the number of particles is greater than or equal to the first preset number of particles and less than 200 second preset number of particles, the cleaning mode threshold is reduced to a corresponding value using a second threshold adjustment coefficient of 0.80; If the number of particles is greater than or equal to the second preset number of particles, the cleaning mode threshold is reduced to a corresponding value using a third threshold adjustment coefficient of 0.75.

[0051] In the embodiment of the present invention, the first preset number of particles is 100, and the second preset number of particles is 200, but the above values ​​are not limited thereto, and those skilled in the art may adjust the values ​​according to actual needs.

[0052] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

[0053] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A flow channel cleaning machine cleanliness detection system based on image recognition, characterized in that: include: A flow channel cleaning machine includes a cleaning section and a water supply section, wherein the water supply section is used to provide high-pressure circulating water to the cleaning section. The cleaning section is a box provided with a flip cover, and several layers of cleaning platforms are provided inside the box. Each cleaning platform includes several cleaning modules, wherein a single cleaning module is provided with an oscillating table for placing the mold to be cleaned, a water outlet interface, and a water return interface; a data acquisition module connected to the cleaning unit and configured to collect the water flow rate in the water outlet interface; A detection module, connected to the cleaning unit, is used to collect images of the solution in the return water interface through image recognition technology and analyze and calculate the particle concentration, particle change rate and particle number in the solution; A control module is respectively connected to the cleaning part, the data acquisition module and the detection module, and is used to determine the cleaning mode according to the particle change rate under the first preset cleaning time, change the cleaning mode when the cleaning mode is judged to be unqualified according to the particle concentration under the second preset cleaning time, and judge the eligibility of the cleaning according to whether there are particles in the return water interface after the flow channel is blown dry, and optimize the corresponding cleaning mode threshold under the condition of unqualified cleaning.

2. The cleanliness detection system for a flow channel cleaning machine based on image recognition according to claim 1, characterized in that: The water supply unit includes a filter unit for filtering return water and a water storage unit, wherein the filter unit includes a filter water tank, an internal circulation water pump and several filters, and the water storage unit includes a flushing water tank and a centrifugal pump.

3. The cleanliness detection system for a flow channel cleaning machine based on image recognition according to claim 1, characterized in that: A vibration generator is provided at the center of the bottom of the oscillating table, and the four corners of the bottom of the oscillating table are connected to the cleaning platform through vibration springs.

4. The cleanliness detection system for a flow channel cleaning machine based on image recognition according to claim 1, characterized in that: The cleaning part is further provided with an air supply unit, and the air supply unit is provided with an air source filter and a blowing air source filtering device.

5. The cleanliness detection system for a flow channel cleaning machine based on image recognition according to claim 1, characterized in that: The data acquisition module includes a flow sensor arranged in the water outlet interface, and pressure sensors arranged in the air supply channel and the water outlet channel.

6. The cleanliness detection system for a flow channel cleaning machine based on image recognition according to claim 1, characterized in that: The control module determines a cleaning mode according to a particle change rate under a first preset cleaning time, wherein the cleaning modes are divided into levels one to four; If the particle change rate is less than the first preset change rate, the cleaning mode is determined to be a four-level cleaning mode, wherein the four-level cleaning mode adopts a pulse flushing combined with vibration method; If the particle change rate is greater than or equal to the first preset change rate and less than the second preset change rate, the cleaning mode is determined to be the third-level cleaning mode, and the third-level cleaning mode adopts a pulse flushing method; If the particle change rate is greater than or equal to the second preset change rate and less than the third preset change rate, the cleaning mode is determined to be a secondary cleaning mode, and the secondary cleaning mode adopts a forward flushing combined with a reverse flushing method; If the particle change rate is greater than or equal to the third preset change rate, the cleaning mode is determined to be a primary cleaning mode, and the primary cleaning mode adopts a forward flushing method.

7. The cleanliness detection system for a flow channel cleaning machine based on image recognition according to claim 1, characterized in that: The control module determines whether the cleaning mode is qualified based on the particle concentration under the second preset cleaning time, wherein if the particle concentration is less than the first preset particle concentration, the cleaning mode is determined to be qualified, and the flow channel is blown dry after cleaning is completed in the current cleaning mode; If the particle concentration is greater than or equal to the first preset particle concentration and less than the second preset particle concentration, the cleaning mode is determined to be unqualified, and the water flow rate is increased according to the difference between the particle concentration and the first preset particle concentration; If the particle concentration is greater than or equal to the second preset particle concentration, the cleaning mode is determined to be unqualified and the cleaning mode level is increased by one level.

8. The cleanliness detection system for a flow channel cleaning machine based on image recognition according to claim 7, characterized in that: The water outlet flow rate is positively correlated with the particle concentration difference, wherein the particle concentration difference is the difference between the particle concentration and the first preset particle concentration.

9. The cleanliness detection system for a flow channel cleaning machine based on image recognition according to claim 1, characterized in that: The control module determines the eligibility of the cleaning based on whether there are particles in the return water interface after the flow channel is blown dry. If there are particles in the return water interface, the cleaning is determined to be unqualified, and the cleaning mode threshold is optimized according to the number of particles. The cleaning mode threshold includes a first preset change rate and a second preset change rate. If there are no particles in the return water interface, the cleaning is determined to be qualified.

10. The cleanliness detection system for a flow channel cleaning machine based on image recognition according to claim 9, characterized in that: Several adjustment methods are provided for the cleaning mode threshold, and each adjustment method has a different adjustment range for the cleaning mode threshold.

Images