Automatic bowl cleaning system

Abstract

The present invention relates to the technical field of automatic cleaning, and discloses an automatic bowl body cleaning system for solving the problem that cleaning parameters cannot be automatically adjusted according to the dirt problem of the bowl body itself when cleaning the bowl body, including: detecting the dirt on the bowl body, evaluating and obtaining a dirt accumulation index, adjusting the water flow rate according to the dirt accumulation index to obtain the actually required water flow rate, adjusting the cleaning time according to the dirt accumulation index to obtain the actually required cleaning time, storing the steam condensed water generated by the sterilizing kettle in a condensed water storage tank, and then conveying the condensed water in the condensed water storage tank by a water pump, spraying the bowl body according to the actually required water flow rate and the actually required cleaning time, and returning the sprayed condensed water to the condensed water storage tank for heating after precise filtration, thereby effectively improving the efficiency of bowl body cleaning and improving the utilization rate of water resources.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic cleaning, and more specifically to an automatic bowl cleaning system. Background Art

[0002] Automatic bowl cleaning is an intelligent cleaning system designed specifically for canned food production lines. During the canning process, the can may be contaminated with impurities such as dust, oil, and water stains. These impurities will not only affect the appearance of the can, but may also pose a hidden danger to the sealing and hygiene standards of the food.

[0003] After the cans are sealed, in order to ensure that the cans will not cause secondary contamination before sterilization, the bowl of the can is usually rinsed with water. In the prior art, the time of the cleaning process is usually fixed, without considering the actual dirt on the bowl, resulting in different cleaning effects. For some bowls with heavy dirt, fixed-time rinsing often cannot achieve the ideal cleaning effect, while for some relatively clean bowls, too long rinsing time wastes water resources and may have an adverse effect on production efficiency.

[0004] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides an automatic bowl cleaning system to solve the problems existing in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The bowl body automatic cleaning system includes: a dirt detection module: used to detect dirt on the bowl body, evaluate the dirt accumulation index, and transmit the dirt accumulation index to the water flow control module and the cleaning time control module; a water flow control module: used to adjust the water flow by the dirt accumulation index to obtain the actual required water flow, and transmit the actual required water flow to the spray module; a cleaning time control module: used to adjust the cleaning time by the dirt accumulation index to obtain the actual required cleaning time, and transmit the actual required cleaning time to the spray module; a spray module: used to store the steam condensate generated by the sterilizing kettle in a condensate storage tank, and then transport the condensate in the condensate storage tank through a water pump, and spray the bowl body according to the actual required water flow and the actual required cleaning time; a condensate filtration module: used to return the sprayed condensate to the condensate storage tank for heating after fine filtration.

[0008] Preferably, the dirt accumulation index acquisition step is: scanning the surface of the bowl body by an infrared sensor to obtain an infrared signal intensity image of the bowl body, and obtaining a dirt coverage coefficient based on the infrared signal intensity image of the bowl body; using a laser ranging method to obtain dirt thickness data on the surface of the bowl body, dividing the bowl body into n parts, recorded as sub-measurement areas, and obtaining an average dirt thickness of each sub-measurement area based on the dirt thickness data on the surface of the bowl body, clustering the average dirt thickness of each sub-measurement area, and evaluating the dirt thickness coefficient based on the clustering processing result; evaluating the dirt distribution uniformity coefficient based on the infrared signal intensity image of the bowl body; normalizing the dirt coverage coefficient, the dirt thickness coefficient, and the dirt distribution uniformity coefficient, and evaluating the dirt accumulation index based on the normalized dirt coverage coefficient, the dirt thickness coefficient, and the dirt distribution uniformity coefficient. The specific acquisition steps are: , where AD represents the dirt accumulation index, DC represents the dirt coverage coefficient, TD represents the dirt thickness coefficient, and HD represents the dirt distribution uniformity coefficient. , , It is expressed as the weight coefficient of dirt coverage coefficient, dirt thickness coefficient and dirt distribution uniformity coefficient.

[0009] Preferably, the steps for obtaining the dirt coverage coefficient are: rotating the infrared sensor to perform a full coverage scan of the bowl body, recording the infrared signal strength at different positions, obtaining an infrared signal strength image of the bowl body, and obtaining the total number of image pixels through the infrared signal strength image of the bowl body; analyzing the surface temperature or reflected light intensity distribution through the infrared signal strength image of the bowl body, identifying the dirt coverage area, and obtaining the total number of dirt pixels; calculating the dirt coverage area ratio through an image processing algorithm, and recording the dirt coverage area ratio as the dirt coverage coefficient

[0010] Preferably, the steps of analyzing the surface temperature or reflected light intensity distribution through the infrared signal intensity image of the bowl body, identifying the dirt-covered area, and obtaining the total number of dirt pixels are as follows: converting the infrared signal intensity image of the bowl body into a grayscale image, applying an image filtering algorithm to remove noise points in the image, and performing histogram equalization or stretching the dynamic range; using a threshold segmentation method, selecting a segmentation threshold, and marking the area in the infrared signal intensity image of the bowl body with a signal intensity higher than the segmentation threshold as dirt; using a connectivity algorithm to mark adjacent white pixel blocks as dirt-covered areas, and obtaining the total number of dirt pixels.

[0011] Preferably, the steps of clustering the average dirt thickness of each sub-measurement area are as follows: Step 1: taking the average dirt thickness as a clustering feature, taking the average dirt thickness of all sub-measurement areas as a data set, and each average dirt thickness in the data set as a data point; Step 2: using the elbow method to determine the optimal clustering number K of the data set; Step 3: randomly selecting K data points in the data set as initial clustering centers, for each data point, calculating its Euclidean distance to each initial clustering center, for each data point, traversing the K initial clustering centers, and assigning it to the clustering cluster corresponding to the nearest initial clustering center; Step 4: traversing all data points to obtain initial clustering clusters, for each initial clustering cluster, calculating the mean of the data points in it to obtain a new clustering center; Step 5: repeating steps 3 and 4 until the clustering center no longer changes, and obtaining the final clustering cluster and the final clustering center.

[0012] Preferably, the step of evaluating the dirt thickness coefficient based on the clustering processing results is: calculating the ratio of the number of data points in each final cluster to the total number in the data set to obtain the weight of each final cluster; and performing weighted summation of the weight of each final cluster and the final cluster center to obtain the dirt thickness coefficient.

[0013] Preferably, the steps for obtaining the dirt distribution uniformity coefficient are: matching the infrared signal intensity image of the bowl body with the sub-measurement area, and for each sub-measurement area, calculating the ratio of the total number of dirt pixels in the sub-measurement area to the total number of pixels in the sub-measurement area, which is recorded as the dirt density; calculating the average dirt density of the bowl body according to the dirt density of each sub-measurement area, and calculating the standard deviation of the dirt density of the bowl body according to the average dirt density of the bowl body; and calculating the dirt distribution uniformity coefficient according to the standard deviation of the dirt density of the bowl body. The specific acquisition steps are: , where HD is the dirt distribution uniformity coefficient, Expressed as the standard deviation of the dirt density on the bowl.

[0014] Preferably, the step of obtaining the actually required water flow rate is: setting a dirt accumulation threshold, calculating the ratio of the dirt accumulation index to the dirt accumulation threshold to obtain an adjustment factor; setting an initial water flow rate, calculating the product of the initial water flow rate and the adjustment factor to obtain the actually required water flow rate. The specific obtaining steps are: , where Expressed as the actual required water flow, Expressed as the adjustment factor, Expressed as the initial water flow rate.

[0015] Preferably, the step of obtaining the actually required cleaning time is: setting an initial cleaning time, multiplying the initial cleaning time by an adjustment factor, and obtaining the actually required cleaning time.

[0016] Technical effects and advantages of the present invention:

[0017] The dirt on the bowl body is detected and the dirt accumulation index is evaluated. The water flow rate is adjusted according to the dirt accumulation index to obtain the actual required water flow rate. The cleaning time is adjusted according to the dirt accumulation index to obtain the actual required cleaning time. The steam condensate produced by the sterilizer is stored in the condensate storage tank, and the condensate in the condensate storage tank is transported by a water pump. The bowl body is sprayed according to the actual required water flow rate and the actual required cleaning time. The condensed water after spraying is returned to the condensate storage tank for heating after precision filtration, which effectively improves the efficiency of bowl cleaning and improves the utilization rate of water resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is the overall structure diagram of the present invention. DETAILED DESCRIPTION

[0019] The technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. In addition, the forms of the various structures recorded in the following embodiments are merely illustrative, and the automatic bowl body cleaning system involved in the present invention is not limited to the various structures recorded in the following embodiments. All other embodiments obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0020] The present invention provides an automatic bowl cleaning system, such as Figure 1 As shown, the system includes:

[0021] Dirt detection module: used to detect the dirt on the bowl, evaluate the dirt accumulation index, and transmit the dirt accumulation index to the water flow control module and the cleaning time control module;

[0022] In this embodiment, it should be specifically explained that the steps for obtaining the dirt accumulation index are:

[0023] The surface of the bowl body is scanned by an infrared sensor to obtain an infrared signal intensity image of the bowl body, and the dirt coverage coefficient is obtained according to the infrared signal intensity image of the bowl body;

[0024] The dirt thickness data on the bowl body surface is obtained by using the laser ranging method, and the bowl body is evenly divided into n parts, which are recorded as sub-measurement areas. The average dirt thickness of each sub-measurement area is obtained according to the dirt thickness data on the bowl body surface, and the average dirt thickness of each sub-measurement area is clustered. The dirt thickness coefficient is obtained according to the clustering processing result.

[0025] Extracting representative values ​​of different thickness characteristics through clustering helps to classify and integrate complex data, and classify the dirt thickness of each sub-measurement area on the bowl surface into groups with common characteristics, thereby extracting representative values ​​of each type of dirt thickness. This method can effectively reduce noise interference in the data, avoid the impact of individual abnormal areas or extreme values ​​on the overall evaluation, and significantly improve the accuracy and reliability of the dirt thickness coefficient;

[0026] It can fully reflect the overall characteristics of the dirt thickness distribution and serve as an important basis for adjusting cleaning parameters, making the cleaning process more accurate and efficient. In addition, the clustering results can also help the system intelligently identify specific dirt patterns and provide data support for further optimization of cleaning equipment and processes.

[0027] The dirt distribution uniformity coefficient is obtained by evaluating the infrared signal intensity image of the bowl body;

[0028] The dirt coverage coefficient, dirt thickness coefficient and dirt distribution uniformity coefficient are normalized, and the dirt accumulation index is obtained by evaluating the normalized dirt coverage coefficient, dirt thickness coefficient and dirt distribution uniformity coefficient. The specific acquisition steps are as follows: , where AD is expressed as the dirt accumulation index, DC is expressed as the dirt coverage coefficient, and the proportion of the tank surface area covered by dirt has a direct impact on the overall dirt accumulation degree. The higher the coverage coefficient, the wider the dirt is distributed on the surface, and the cleaning difficulty and energy required increase accordingly, making the dirt accumulation index larger. This relationship reflects that the coverage area is an important measure of the degree of accumulation, which can intuitively evaluate the cleaning needs. TD is expressed as the dirt thickness coefficient. The thickness of the dirt accumulated on the tank surface has a significant impact on the overall accumulation degree, that is, the thicker the dirt, the higher the accumulation index, reflecting the increase in cleaning difficulty and resource requirements. Dirt thickness is a direct reflection of the accumulation volume. Thicker dirt usually means higher cleaning resistance, stronger adhesion, and possible hidden multi-layer dirt structure. In addition, excessively thick dirt may also cause problems such as poor heat dissipation of equipment, accelerated corrosion, or reduced operating efficiency. Therefore, the proportional relationship between the thickness coefficient and the accumulation index reflects the importance of thickness as a key parameter, which can be used to dynamically evaluate the difficulty of cleaning and optimize the cleaning strategy. HD is expressed as the coefficient of uniformity of dirt distribution. The more uniform the dirt distribution on the surface of the bowl body, the lower the accumulation index, that is, the complexity and difficulty of cleaning are relatively reduced. Evenly distributed dirt usually presents a more consistent thickness and coverage, allowing cleaning equipment to complete cleaning stably, with higher efficiency and lower energy consumption. However, when the dirt is unevenly distributed, local dirt will accumulate thicker or form high adhesion areas, resulting in increased cleaning difficulty. At this time, in order to remove local accumulation, it may be necessary to increase the overall cleaning intensity or extend the time, which not only wastes resources, but may also cause unnecessary energy consumption and equipment wear. , , is expressed as the weight coefficient of the dirt coverage coefficient, dirt thickness coefficient and dirt distribution uniformity coefficient, and , , , The specific value is determined by professionals according to the actual situation, for example, , , It can be 0.4, 0.4, 0.2.

[0029] Laser ranging is a non-contact measurement technology based on the principle of laser beam reflection, which is used to accurately measure the distance between the surface of an object and the measuring device. Its working principle is to emit a laser beam to the target surface through a laser emitting device. The beam is captured by the receiver after being reflected on the surface. The distance of the reflection point is calculated based on the laser flight time or phase difference. When measuring the thickness of dirt on the bowl body, the reference distance of the clean surface is first measured by laser, and then the total distance of the dirt-covered surface is measured. The difference between the two is the thickness of the dirt. Laser ranging has the advantages of high precision, fast response and non-contact measurement, and is suitable for accurate detection of dirt on smooth surfaces.

[0030] In this embodiment, it should be specifically explained that the steps for obtaining the dirt coverage factor are:

[0031] The infrared sensor is rotated to scan the entire bowl body, and the infrared signal strength at different positions is recorded to obtain an infrared signal strength image of the bowl body, and the total number of pixels of the image is obtained through the infrared signal strength image of the bowl body;

[0032] Analyze the surface temperature or reflected light intensity distribution through the infrared signal intensity image of the bowl body, identify the dirt coverage area, and obtain the total number of dirt pixels;

[0033] The coverage area ratio of dirt is calculated by image processing algorithm. The specific acquisition steps are as follows: , and the coverage area ratio of dirt is recorded as the dirt coverage coefficient, where DC represents the dirt coverage coefficient, Expressed as the total number of dirt pixels, Expressed as the total number of pixels in the image.

[0034] In this embodiment, it should be specifically explained that the steps of analyzing the surface temperature or the reflected light intensity distribution through the infrared signal intensity image of the bowl body, identifying the dirt covered area, and obtaining the total number of dirt pixels are as follows:

[0035] Convert the infrared signal intensity image of the bowl body into a grayscale image to simplify the data structure. The higher the grayscale value, the higher the signal intensity or surface temperature.

[0036] Apply image filtering algorithms to remove possible noise points in the image and reduce misjudgment;

[0037] Enhance the signal intensity difference between the dirt area and the background by histogram equalization or stretching the dynamic range;

[0038] Using the threshold segmentation method, a segmentation threshold is selected, and the area in the infrared signal intensity image of the bowl body with a signal intensity higher than the segmentation threshold is marked as dirt;

[0039] The connectivity algorithm is used to mark adjacent white pixel blocks as a dirt-covered area and obtain the total number of dirt pixels. Connectivity analysis helps to identify and filter isolated small areas or count the areas of multiple independent dirt areas.

[0040] Image filtering algorithm is an image processing technique used to smooth images, remove noise, and retain or enhance target features. Common image filtering algorithms include mean filtering, median filtering, and Gaussian filtering.

[0041] Threshold segmentation is a simple and commonly used image segmentation technique, which is used to separate the target area from the background area in the image. The core idea is to select a threshold value and divide the pixels of the image into two categories according to the relationship between the pixel value and the threshold value: one is the area with signal strength higher than the threshold value (such as the dirt area), and the other is the area with signal strength lower than the threshold value (such as the background or clean area).

[0042] The connectivity algorithm is a technique used to mark and identify connected regions in image segmentation, aiming to group adjacent pixels into regions with specific characteristics. In a binary image, the connectivity algorithm classifies adjacent white pixels (value 1) into a connected region by checking the relationship between the pixel and its surrounding neighbors (usually 4-connected or 8-connected). The 4-connected algorithm only considers pixel connections in the top, bottom, left, and right directions, while the 8-connected algorithm also includes connections in the diagonal direction. The connectivity algorithm assigns a unique label to each connected region, allowing statistical analysis of the region, such as calculating area, shape, or position.

[0043] In this embodiment, it should be specifically explained that the steps of clustering the average dirt thickness of each sub-measurement area are:

[0044] Step 1: Take the average dirt thickness as the clustering feature, take the average dirt thickness of all sub-measurement areas as the data set, and each average dirt thickness in the data set as a data point;

[0045] Step 2: Use the elbow method to determine the optimal number of clusters K for the data set;

[0046] The elbow method is a method for determining the optimal number of clusters K for a data set. It finds the optimal number of clusters by evaluating the trend of the clustering effect of the clustering model as the number of clusters changes. Specifically, the elbow method groups data points according to different numbers of clusters, calculates the clustering quality index of each clustering result, and draws a curve that changes with the number of clusters. As the number of clusters increases, the density within the cluster usually decreases gradually. When a certain number of clusters is reached, the rate of decrease of the density within the cluster slows down significantly, forming an "elbow" point. The number of clusters corresponding to this "elbow" point is the optimal number of clusters for the data;

[0047] Step 3: Randomly select K data points in the data set as the initial cluster centers. For each data point, calculate the Euclidean distance from each initial cluster center. The specific acquisition steps are: ,in It is expressed as the Euclidean distance from the data point to the cluster center, where Represented as data points, Represented as the initial cluster center, for each data point, traverse the K initial cluster centers and assign it to the cluster corresponding to the nearest initial cluster center;

[0048] Euclidean distance is a commonly used distance measurement method that is used to calculate the straight-line distance between a data point and a cluster center. It evaluates the similarity between two points by measuring the differences in various dimensions. The smaller the distance, the closer the data point is to a cluster center and the more likely it is to be assigned to that cluster.

[0049] Step 4: After traversing all data points, the initial clusters are obtained. For each initial cluster, the mean of the data points in it is calculated to obtain a new cluster center.

[0050] Step 5: Repeat steps 3 and 4 until the cluster center no longer changes, and obtain the final cluster and the final cluster center.

[0051] In this embodiment, it should be specifically explained that the steps of evaluating and obtaining the dirt thickness coefficient according to the clustering processing result are as follows:

[0052] The weight of each final cluster is calculated by calculating the ratio of the number of data points in each final cluster to the total number of data points in the data set;

[0053] The weight of each final cluster is weighted and summed with the final cluster center to obtain the dirt thickness coefficient. The specific acquisition steps are as follows: , where TD is the dirt thickness factor, Represented as the weight of the i-th final cluster, It is represented as the i-th final cluster center, and K is the optimal number of clusters of the data set.

[0054] In this embodiment, it should be specifically explained that the steps for obtaining the dirt distribution uniformity coefficient are:

[0055] The infrared signal intensity image of the bowl body is matched with the sub-measurement area. For each sub-measurement area, the ratio of the total number of dirt pixels to the total number of pixels in the sub-measurement area is calculated, which is recorded as the dirt density.

[0056] The average dirt density of the bowl body is calculated according to the dirt density of each sub-measurement area, and the standard deviation of the dirt density of the bowl body is calculated according to the average dirt density of the bowl body;

[0057] The dirt distribution uniformity coefficient is calculated based on the standard deviation of the dirt density of the bowl body. The specific steps for obtaining it are: , where HD is the dirt distribution uniformity coefficient, Expressed as the standard deviation of the dirt density on the bowl.

[0058] Water flow control module: used to adjust the water flow by the dirt accumulation index, obtain the actual required water flow, and transmit the actual required water flow to the spray module;

[0059] In this embodiment, it should be specifically explained that the steps for obtaining the actually required water flow are:

[0060] A dirt accumulation threshold is set, and the adjustment factor is calculated by calculating the ratio of the dirt accumulation index to the dirt accumulation threshold;

[0061] Set the initial water flow rate, multiply the initial water flow rate by the adjustment factor to obtain the actual required water flow rate. The specific steps are as follows: , where Expressed as the actual required water flow, Expressed as the adjustment factor, Expressed as the initial water flow rate.

[0062] By adjusting the water flow rate through the dirt accumulation index, the amount of cleaning water can be dynamically adjusted according to the actual situation of dirt on the bowl surface to achieve precise cleaning. The main function of this method is to optimize resource utilization, avoid excessive water use or insufficient cleaning, ensure the cleaning effect while saving water resources and energy consumption to the greatest extent. The benefit is that it improves cleaning efficiency, reduces operating costs, and meets environmental protection needs.

[0063] Cleaning time control module: used to adjust the cleaning time according to the dirt accumulation index, obtain the actual required cleaning time, and transmit the actual required cleaning time to the spray module;

[0064] In this embodiment, it should be specifically explained that the steps for obtaining the actual required cleaning time are:

[0065] Set the initial cleaning time, multiply the initial cleaning time by the adjustment factor to get the actual required cleaning time. The specific steps are as follows: , where Indicates the actual cleaning time required. Indicated as initial cleaning time.

[0066] By adjusting the cleaning time through the dirt accumulation index, the cleaning duration can be dynamically adjusted according to the actual situation of the bowl body dirt to ensure the accuracy and efficiency of the cleaning effect. The purpose of this method is to avoid the waste of water resources and energy due to too long cleaning time, or incomplete cleaning due to insufficient cleaning time. The benefit is that it significantly improves the cleaning efficiency and resource utilization, and reduces production costs.

[0067] Spray module: used to store the steam condensed water generated by the sterilizer in the condensed water storage tank, and then transport the condensed water in the condensed water storage tank through a water pump to spray the bowl body according to the actual required water flow and the actual required cleaning time;

[0068] The steam condensate produced by the sterilization kettle is used as cleaning water to fully recycle industrial waste heat, reduce dependence on additional cleaning water sources in the production process, save water resources and reduce emissions; the condensate itself has a high temperature, and when used for cleaning, it can reduce the energy consumption of additional heating, reduce production costs, and comply with the concept of green environmental protection; the spray module can dynamically adjust the water flow and cleaning time according to the dirt condition of the bowl body, avoiding excessive or insufficient cleaning, and improving the efficiency of the production line and product quality; through the storage function of the condensate storage tank, the spray module can provide continuous and stable cleaning water during the peak cleaning period, ensuring that the cleaning process is not interrupted and improving the reliability of the system.

[0069] Condensate filtration module: used to return the condensed water after spraying to the condensed water storage tank for heating after precise filtration.

[0070] This module precisely filters the condensed water after spraying to remove impurities, dirt particles and other possible pollutants, so that the water quality is restored to cleanliness and meets the standards for recycling. By recycling the condensed water and sending it back into the water storage tank for heating, effective utilization of thermal energy is achieved, avoiding the waste of direct discharge of condensed water, and reducing the demand for fresh water sources. The condensed water itself has a high degree of cleanliness, and the two precise filtrations at the inlet and outlet ensure the quality of the circulating water, with minimal impact on the bowl body and product during the cleaning process.

[0071] By recycling condensed water, the extra energy consumption of the electric heating link is saved. Condensed water originally has a high temperature, and reuse it greatly reduces the energy consumption of the production line; the condensed water that originally needed to be discharged directly is collected, filtered and recycled, reducing the consumption of fresh water resources and optimizing resource utilization efficiency; the precision filtration design of the secondary cycle ensures that the cleaning water meets the process requirements, and the water resource utilization rate is significantly improved; the condensed water itself has a high degree of cleanliness, and the precision filtration ensures the circulating water quality, which not only guarantees the cleaning effect, but also reduces product quality risks; the module operation is highly automated, and no frequent manual intervention is required, which further improves the efficiency of the system.

[0072] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0073] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. Bowl body automatic cleaning system, characterized by: The system comprises: Dirt detection module: used to detect the dirt on the bowl, evaluate the dirt accumulation index, and transmit the dirt accumulation index to the water flow control module and the cleaning time control module; Water flow control module: used to adjust the water flow by the dirt accumulation index, obtain the actual required water flow, and transmit the actual required water flow to the spray module; Cleaning time control module: used to adjust the cleaning time according to the dirt accumulation index, obtain the actual required cleaning time, and transmit the actual required cleaning time to the spray module; Spray module: used to store the steam condensed water generated by the sterilizer in the condensed water storage tank, and then transport the condensed water in the condensed water storage tank through a water pump to spray the bowl body according to the actual required water flow and the actual required cleaning time; Condensate filtration module: used to filter the condensed water after spraying and then return it to the condensed water storage tank for heating; The steps for obtaining the dirt accumulation index are: The surface of the bowl body is scanned by an infrared sensor to obtain an infrared signal intensity image of the bowl body, and the dirt coverage coefficient is obtained according to the infrared signal intensity image of the bowl body; The dirt thickness data on the bowl body surface is obtained by using the laser ranging method, and the bowl body is evenly divided into n parts, which are recorded as sub-measurement areas. The average dirt thickness of each sub-measurement area is obtained according to the dirt thickness data on the bowl body surface, and the average dirt thickness of each sub-measurement area is clustered. The dirt thickness coefficient is obtained according to the clustering processing result. The dirt distribution uniformity coefficient is obtained by evaluating the infrared signal intensity image of the bowl body; The dirt coverage coefficient, dirt thickness coefficient and dirt distribution uniformity coefficient are normalized, and the dirt accumulation index is obtained by evaluating the normalized dirt coverage coefficient, dirt thickness coefficient and dirt distribution uniformity coefficient. The specific acquisition steps are as follows: , where AD represents the dirt accumulation index, DC represents the dirt coverage coefficient, TD represents the dirt thickness coefficient, and HD represents the dirt distribution uniformity coefficient. , , It is expressed as the weight coefficient of dirt coverage coefficient, dirt thickness coefficient and dirt distribution uniformity coefficient.

2. The bowl automatic cleaning system according to claim 1, characterized in that: The steps for obtaining the dirt coverage factor are: The infrared sensor is rotated to scan the entire bowl body, and the infrared signal strength at different positions is recorded to obtain an infrared signal strength image of the bowl body, and the total number of pixels of the image is obtained through the infrared signal strength image of the bowl body; Analyze the surface temperature or reflected light intensity distribution through the infrared signal intensity image of the bowl body, identify the dirt coverage area, and obtain the total number of dirt pixels; The coverage area ratio of the dirt is calculated by an image processing algorithm, and the coverage area ratio of the dirt is recorded as the dirt coverage coefficient.

3. The bowl automatic cleaning system according to claim 2, characterized in that: The steps of analyzing the surface temperature or reflected light intensity distribution through the infrared signal intensity image of the bowl body, identifying the dirt covered area, and obtaining the total number of dirt pixels are as follows: Convert the bowl body infrared signal intensity image into a grayscale image, apply image filtering algorithm to remove noise points in the image, and use histogram equalization or stretching dynamic range; Using the threshold segmentation method, a segmentation threshold is selected, and the area in the infrared signal intensity image of the bowl body with a signal intensity higher than the segmentation threshold is marked as dirt; Use the connectivity algorithm to mark adjacent white pixel blocks as dirt-covered areas and obtain the total number of dirt pixels.

4. The bowl automatic cleaning system according to claim 1, characterized in that: The steps of clustering the average dirt thickness of each sub-measurement area are as follows: Step 1: Take the average dirt thickness as the clustering feature, take the average dirt thickness of all sub-measurement areas as the data set, and each average dirt thickness in the data set as a data point; Step 2: Use the elbow method to determine the optimal number of clusters K for the data set; Step 3: Randomly select K data points in the data set as the initial cluster centers. For each data point, calculate its Euclidean distance to each initial cluster center. For each data point, traverse the K initial cluster centers and assign it to the cluster corresponding to the nearest initial cluster center. Step 4: After traversing all data points, the initial clusters are obtained. For each initial cluster, the mean of the data points in it is calculated to obtain a new cluster center. Step 5: Repeat steps 3 and 4 until the cluster center no longer changes, and obtain the final cluster and the final cluster center.

5. The bowl automatic cleaning system according to claim 4, characterized in that: The step of evaluating and obtaining the dirt thickness coefficient according to the clustering processing result is: The weight of each final cluster is calculated by calculating the ratio of the number of data points in each final cluster to the total number of data points in the data set; The weight of each final cluster is weighted and summed with the final cluster center to obtain the dirt thickness coefficient.

6. The bowl automatic cleaning system according to claim 1, characterized in that: The steps for obtaining the dirt distribution uniformity coefficient are: The infrared signal intensity image of the bowl body is matched with the sub-measurement area. For each sub-measurement area, the ratio of the total number of dirt pixels to the total number of pixels in the sub-measurement area is calculated, which is recorded as the dirt density. The average dirt density of the bowl body is calculated according to the dirt density of each sub-measurement area, and the standard deviation of the dirt density of the bowl body is calculated according to the average dirt density of the bowl body; The dirt distribution uniformity coefficient is calculated based on the standard deviation of the dirt density of the bowl body. The specific steps for obtaining it are: , where HD is the dirt distribution uniformity coefficient, Expressed as the standard deviation of the dirt density on the bowl.

7. The bowl automatic cleaning system according to claim 1, characterized in that: The steps for obtaining the actually required water flow are: A dirt accumulation threshold is set, and the adjustment factor is calculated by calculating the ratio of the dirt accumulation index to the dirt accumulation threshold; Set the initial water flow rate, multiply the initial water flow rate by the adjustment factor to obtain the actual required water flow rate. The specific steps are as follows: , where Expressed as the actual required water flow, Expressed as the adjustment factor, Expressed as the initial water flow rate.

8. The bowl automatic cleaning system according to claim 7, characterized in that: The steps for obtaining the actual required cleaning time are: Set the initial cleaning time, multiply the initial cleaning time by the adjustment factor to get the actual required cleaning time.

Images