Intelligent detergent dispensing control method and system for automated car washing equipment

Abstract

The present application relates to the field of automation control technology, and provides an intelligent detergent dispensing control method and system for automated car washing equipment. The method includes: using a high-precision camera to collect stain images on the vehicle surface, identifying stain features to generate a multidimensional feature set; clustering the feature set to obtain a stain region feature set, and calling the car washing solution parameter space; parsing the regional feature set based on the parameter space to determine the cleaning solution parameters for each region; associating the detergent dispensing component control logic to generate regional dispensing control parameters; real-time monitoring of ambient temperature and humidity, and optimizing detergent dispensing and feedback control in combination with control parameters, so as to solve the technical problems that existing automated car washing equipment lacks pertinence when dispensing detergent, cannot accurately control the detergent dispensing amount according to the actual stain situation of the vehicle and environmental changes, resulting in poor car washing effect and detergent waste, and achieves the technical effects of improving car washing quality, reducing detergent waste, and realizing intelligent and precise control.

Description

Technical Field

[0001] The present application relates to the field of automation control technology, and in particular to an intelligent detergent delivery control method and system for automated car washing equipment. Background Art

[0002] While currently available automated car wash equipment can perform basic cleaning processes, it generally uses fixed programs to control detergent dispensing, allowing only rough proportioning based on preset times or water volumes. This makes it impossible to accurately identify differences in stain type, distribution density, and adhesion levels across different areas of the vehicle body, leading to incomplete cleaning of stubborn stains or excessive detergent use in low-pollution areas. Furthermore, changes in ambient temperature and humidity directly affect the chemical activity and fluidity of detergents. Traditional equipment lacks the ability to respond to these dynamic parameters in real time, easily leading to problems such as detergent residue in low-temperature environments or rapid foam dissipation in high-temperature environments. Especially when dealing with mixed stains such as mud, oil, and gum, static dispensing strategies struggle to meet differentiated cleaning needs. This not only increases the combined consumption of water, electricity, and chemicals, but can also accelerate equipment corrosion or damage the paint due to the misuse of strong detergents. Against this backdrop, there is an urgent need for a detergent dispensing method and system that integrates intelligent sensing, dynamic zoning control, and environmental adaptation to improve car wash efficiency, reduce resource consumption, and ensure consistent cleaning quality. Summary of the Invention

[0003] This application provides an intelligent detergent dispensing control method and system for automated car washing equipment, aiming to solve the technical problems that existing automated car washing equipment lacks specificity when dispensing detergents and cannot accurately control the amount of detergent dispensed according to the actual stain conditions of the vehicle and environmental changes, resulting in poor car washing effects and detergent waste. The application achieves the goal of accurately dividing the stain areas according to the stain characteristics of the vehicle body, and formulating personalized cleaning plans based on the parameter space of the car washing plan. At the same time, the detergent dispensing is adjusted in real time according to the ambient temperature and humidity, thereby improving the car washing quality, reducing detergent waste, and achieving the technical effect of intelligent and precise control.

[0004] The first aspect disclosed in the present application provides an intelligent detergent dispensing control method for automated car washing equipment, the method comprising: acquiring a body surface stain image of a target vehicle through a high-precision camera, performing stain feature recognition on the body surface stain image, and obtaining a multidimensional feature set of body stains; performing clustering division on the body stain multidimensional feature set to obtain N body stain area feature sets, and simultaneously calling a car washing solution parameter space according to a target automated car washing equipment; performing cleaning solution analysis on the N body stain area feature sets based on the car washing solution parameter space to determine N stain area cleaning solution parameters; performing control logic association on the detergent dispensing component of the target automated car washing equipment based on the N stain area cleaning solution parameters to obtain N area detergent dispensing control parameters; and obtaining an ambient temperature and humidity data stream through real-time monitoring, and performing detergent dispensing control and feedback regulation optimization on the target vehicle through the target automated car washing equipment based on the N area detergent dispensing control parameters and the ambient temperature and humidity data stream.

[0005] Another aspect disclosed herein provides an intelligent detergent dispensing control system for automated car wash equipment, the system comprising: a stain feature recognition module that acquires a stain image on the surface of a target vehicle through a high-precision camera, performs stain feature recognition on the stain image, and obtains a multidimensional feature set of the stain; a clustering module that performs clustering on the multidimensional feature set of the stain to obtain N stain region feature sets, and simultaneously calls a car wash solution parameter space according to a target automated car wash equipment; a cleaning solution parsing module that performs cleaning solution parsing on the N stain region feature sets based on the car wash solution parameter space to determine N stain region cleaning solution parameters; a control logic association module that performs control logic association on the detergent dispensing components of the target automated car wash equipment based on the N stain region cleaning solution parameters to obtain N region detergent dispensing control parameters; and a dispensing control module that monitors and obtains an ambient temperature and humidity data stream in real time, and performs detergent dispensing control and feedback regulation optimization on the target vehicle through the target automated car wash equipment based on the N region detergent dispensing control parameters and the ambient temperature and humidity data stream.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The aforementioned intelligent detergent dispensing control method for automated car washes first uses a high-precision camera to capture images of the vehicle surface and, through image recognition technology, extracts multidimensional features such as stain color, shape, and texture. These features are then clustered and analyzed to identify multiple stain regions. Combined with the car wash's preset program parameters, a specific cleaning strategy is developed for each region, including the type, concentration, and dosage of detergent to be used. These cleaning strategies are then converted into executable control parameters to drive the car wash's detergent dispensing components to precisely dispense detergent by region. Simultaneously, real-time temperature and humidity data from the car wash environment is collected to dynamically adjust the detergent dispensing logic to adapt to the impact of environmental changes on cleaning performance, enabling feedback control and self-optimization of the cleaning process. The overall process forms a closed-loop control system from image recognition, feature analysis, program development, to environmental sensing and adjustment, improving car wash effectiveness and resource efficiency.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0010] Figure 1 The figure is a flow chart of a method for controlling the dispensing of intelligent detergents for automated car washing equipment in one embodiment.

[0011] Figure 2 This is an architecture diagram of an intelligent detergent dispensing control system for automated car washing equipment in one embodiment.

[0012] Explanation of the accompanying symbols: stain feature recognition module 11, clustering module 12, cleaning solution analysis module 13, control logic association module 14, and delivery control module 15. DETAILED DESCRIPTION

[0013] The embodiments of the present application provide an intelligent detergent dispensing control method and system for automated car washing equipment to solve the technical problems that existing automated car washing equipment lacks specificity when dispensing detergent and cannot accurately control the amount of detergent dispensed according to the actual stain conditions of the vehicle and environmental changes, resulting in poor car washing effect and detergent waste. The method achieves the goal of accurately dividing the stain area according to the stain characteristics of the vehicle body, formulating a personalized cleaning plan based on the parameter space of the car washing plan, and adjusting the detergent dispensing in real time according to the ambient temperature and humidity, thereby improving the car washing quality, reducing detergent waste, and achieving the technical effect of intelligent and precise control.

[0014] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0015] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0016] Example 1, as Figure 1 As shown, the present application provides an intelligent detergent dispensing control method for an automated car washing device, the method comprising:

[0017] The stain image of the target vehicle's body surface is acquired by a high-precision camera, and stain features are identified on the stain image to obtain a multi-dimensional feature set of the body stain.

[0018] In the embodiment of the present application, a high-precision camera is first used to capture images of the target vehicle's body, obtaining high-resolution stain images covering the entire vehicle surface. These images clearly record the distribution of stains on different parts of the vehicle body. Subsequently, the captured stain images are de-noised using an image filter, and through stain recognition and feature extraction, a multi-dimensional feature set of vehicle body stains is obtained, such as color features (such as the color differences between different stains such as oil, mud, or bird droppings), shape features (edge contours and area size of the stains), and texture features (texture consistency and uniformity, etc.). These features serve as basic data for subsequent clustering and cleaning strategy formulation, helping the system to comprehensively identify stains.

[0019] Furthermore, the present application provides the multi-dimensional feature set of vehicle body stains, including:

[0020] Noise characteristics of the vehicle body surface stain image are identified to obtain vehicle body image noise characteristic information, and an image filter is initialized based on the vehicle body image noise characteristic information; the vehicle body surface stain image is filtered and denoised using the image filter to obtain a denoised vehicle body surface stain image; a standard vehicle body surface image is obtained based on the specification and model information of the target vehicle; stain identification and feature extraction are performed on the denoised vehicle body surface stain image based on the standard vehicle body surface image to obtain a multi-dimensional feature set of vehicle body stains.

[0021] Preferably, a preliminary analysis is first performed on the captured vehicle body stain image to identify the noise type and distribution characteristics. This process analyzes the image's brightness histogram and pixel value distribution to determine whether there is obvious random noise (such as salt and pepper noise) or uniform noise (such as Gaussian noise). If there is no obvious random noise or uniform noise, local area texture analysis is also performed (for example, calculating the standard deviation of edge directions in multiple local windows. If the direction distribution in a certain area is dispersed and random, it may be blurry). The image edge areas and flat areas are compared. If the edges are blurred or there are abnormal texture mutations between regions, it is considered to be blurry noise. After the preliminary analysis is completed, the vehicle body image noise characteristic information, including noise type and noise intensity, is generated based on the identified noise type. Subsequently, the appropriate image filter type and parameter configuration are automatically selected based on the noise characteristics of the vehicle body image. For example, if Gaussian noise is identified, a Gaussian filter is initialized, and the standard deviation σ and convolution kernel size are set based on the noise intensity. If salt and pepper noise is identified, a median filter is applied, and the optimal sliding window size is determined. If fuzzy noise is identified, a bilateral filter or adaptive sharpening filter is applied to enhance edge details. Once the image filter is initialized, it is loaded as a dynamic parameter in the image processing module for subsequent image cleaning. The initialized image filter is then used to filter the original stain image, removing background interference and excess texture while retaining the main stain information. This results in a denoised vehicle body surface stain image with improved clarity and edge resolution, providing a clean data foundation for subsequent stain identification. Then, based on the current vehicle's model and specifications (such as vehicle type, color, and body size), a standard body surface image matching the vehicle is retrieved from the body surface database. This image represents the standard appearance of the vehicle in an ideal state, uncovered by stains, and serves as an important reference template for subsequent identification of stained areas. After obtaining the standard body surface image, it is compared with the denoised body surface stain image. By analyzing the body background area, areas that deviate from the standard appearance, i.e., locations where stains may exist, are identified. Information is then extracted from multiple dimensions, including color (shape features), shape (edge contours, area), and texture (contrast), to construct a complete multidimensional feature set for body stains. In summary, through the aforementioned denoising, standard comparison, and feature extraction processes, accurate stain identification is achieved, laying a stable, high-quality data foundation for subsequent clustering and cleaning solution matching.

[0022] Furthermore, the present application provides the method for obtaining a multidimensional feature set of vehicle body stains, including:

[0023] The standard vehicle body surface image is used as the background area, and the grayscale distribution of the background area is identified to obtain the grayscale threshold of the vehicle body background area; the denoised vehicle body surface stain image is subjected to stain comparison and identification based on the grayscale threshold of the vehicle body background area to obtain a set of vehicle body surface stain areas; edge detection and region segmentation are performed on the set of vehicle body surface stain areas in sequence, and a set of vehicle body surface stain target frames is marked to obtain; multidimensional feature extraction is performed on the set of vehicle body surface stain target frames respectively to obtain a multidimensional feature set of vehicle body stains, which includes color features, shape features and texture features of the stain area.

[0024] Optionally, first use a standard vehicle body image as the background area and convert the RGB value of each pixel in the background area of the standard vehicle body image to a grayscale value using the formula: Grayscale value = 0.2989 × R + 0.5870 × G + 0.1140 × B, where R is the value of the red channel, G is the value of the green channel, and B is the value of the blue channel. After obtaining the grayscale value of each pixel, a grayscale histogram is generated to represent the frequency of occurrence of each grayscale value (usually grayscale levels in the range of 0-255) in the image. Based on the concentrated area in the grayscale histogram, an upper and lower threshold are set. The range formed by these two thresholds will serve as the grayscale threshold for the vehicle body background area, used to distinguish pixels in the vehicle body surface stain image from the background area, thereby helping the system accurately identify the stained area. The denoised vehicle surface stain image is then converted to a corresponding grayscale value for each pixel using the same method described above. Based on the determined grayscale threshold for the vehicle body background area, the grayscale value of the denoised vehicle surface stain image is then compared with the converted grayscale value. Portions of the image that deviate from the standard background area are identified and recorded as stain regions. These regions are then organized into a set of vehicle surface stain regions. Edge detection is then performed on each stain region in the set using the Canny edge detection algorithm to accurately identify the contours and boundaries of the stain. After edge detection, each stain region is segmented and labeled to form a set of vehicle surface stain target frames. Each target frame in this set contains the location information of the stain region, facilitating subsequent feature extraction and analysis. Multidimensional feature extraction is then performed on each target frame. Specifically, based on the RGB value of each stain target frame on the vehicle body surface, the color information of the stain area is extracted through the conversion of the HSV color space, and the hue, saturation and brightness of the stain are identified to form the color features of the stain area; based on the number of pixels of each stain target frame on the vehicle body surface, the area of each stain target frame on the vehicle body surface is calculated, and based on the formula Calculate the edge smoothness of each body surface stain target frame, where Smoothness is the edge smoothness of the body surface stain target frame, Perimeter is the total length of the edge contour in the body surface stain target frame, and Area is the area of the body surface stain target frame. Based on the formula The contour complexity of each stain target box on the vehicle body surface is calculated, where Complexity represents the contour complexity of the stain target box on the vehicle body surface. The calculated area, edge smoothness, and contour complexity of the stain target box are summarized to obtain the shape characteristics of the stain region. The surface structure of the stain region is analyzed based on the gray-level co-occurrence matrix (GLCM), and contrast, homogeneity, and energy are calculated. Contrast reflects the degree of variation in pixel grayscale values in the image, homogeneity reflects the uniformity of the image texture, and energy reflects the consistency of the image texture. These features together constitute the texture characteristics of the stain region. Finally, the color, shape, and texture features of the stain region are added to a set to obtain a complete multidimensional feature set for vehicle body stains, providing data support for subsequent stain classification, region optimization, and cleaning solution design. In summary, through the step-by-step operations of grayscale distribution recognition, stain comparison, edge detection and region segmentation, the positioning and identification of stains are refined, and through multi-dimensional feature extraction, the visual characteristics of stains (color, shape, texture) are comprehensively analyzed. This information will help in subsequent clustering analysis and matching of cleaning strategies, thereby improving the intelligence level and cleaning effect of car washing.

[0025] Clustering is performed on the multidimensional feature set of the vehicle body stains to obtain N vehicle body stain region feature sets, and at the same time, a car wash solution parameter space is called according to a target automated car wash equipment.

[0026] In one embodiment, cluster analysis is performed on the extracted multidimensional feature set of vehicle body stains. Specifically, stain areas are classified based on features such as color, shape, and texture, with similar stain areas grouped together. Using a clustering algorithm, different stain areas on the vehicle body surface are divided into multiple stain area feature sets, each with similar characteristic features. In this way, all stain areas on the vehicle body surface can be divided into N area feature sets based on feature similarity. After the stain area division is completed, the target automated car wash equipment's unique identifier, such as its ID, is used to access its wash solution parameter space. This parameter space contains information such as the usage, concentration, and dosage of different detergents. Based on the characteristics of each stain area, the most appropriate cleaning solution is automatically selected to ensure optimal cleaning of each stain area. This approach not only enables accurate stain identification based on characteristics, but also enables the development of targeted cleaning strategies, improving car wash efficiency and cleaning results.

[0027] Furthermore, the present application provides the method of obtaining N vehicle body stain region feature sets, including:

[0028] A cluster number range is selected based on the distribution characteristic information of the multidimensional feature set of vehicle body stains; a cluster number K is sequentially selected within the cluster number range to perform clustering error calculation on the multidimensional feature set of vehicle body stains to obtain a sum of squared errors within clusters for multiple K values; an intra-cluster sum of squared errors curve is generated based on the multiple sum of squared errors within clusters for K values, and an elbow point is marked on the intra-cluster sum of squared errors curve to determine a target number of clusters K; cluster division is performed on the multidimensional feature set of vehicle body stains based on the target number of clusters K to obtain N vehicle body stain area feature sets.

[0029] Preferably, a range of cluster numbers is determined based on the distribution characteristics of the multidimensional feature set of vehicle body stains (such as the degree of feature dispersion) and historical experience. This range represents the expected interval of possible cluster numbers and avoids selecting too many or too few clusters. Subsequently, the number of clusters K is selected sequentially within this 2, and the stain feature set is clustered using Euclidean distance. The clustering error for each K value is calculated. A common error calculation method is the within-cluster sum of squares (WSS), which calculates the sum of the distances between sample points within each cluster and the cluster center to reflect the compactness of samples within each cluster. Next, a squared error curve is generated based on the calculated squared errors for multiple K values. The x-axis represents the number of clusters K, and the y-axis represents the squared error. By analyzing this curve, we look for the elbow point, where the sum of squared errors begins to slow. This point typically indicates that the number of clusters has reached a reasonable balance, and adding more clusters will not significantly improve the clustering effect. The elbow point marks the target number of clusters, K, which represents the optimal number of clusters for partitioning stain regions. For example, when K = 4, the decrease in the sum of squared errors curve decreases significantly, so K = 4 is the target number of clusters. Finally, based on the determined target number of clusters, K, the final clustering operation is performed. During this process, the multidimensional feature set of the body stains is divided into K preliminary stain feature regions based on this K value. Similar regions of these K preliminary stain feature regions are then merged to obtain N body stain region feature sets. Each feature set contains similar stain features. These stain region feature sets will serve as the basis for subsequent cleaning solution matching and control strategies. In summary, through this process, the system effectively divides the stain areas on the vehicle body surface into multiple categories by selecting an appropriate number of clusters K. Each category represents a type of stain with similar characteristics. In this way, corresponding cleaning plans can be formulated according to different stain types to achieve efficient and accurate cleaning effects.

[0030] Furthermore, the present application provides the method of performing clustering division on the multidimensional feature set of vehicle body stains based on the target number of clusters K to obtain N vehicle body stain region feature sets, including:

[0031] Iterative clustering is performed on the multidimensional feature set of vehicle body stains based on the target number K of clusters to obtain K preliminary stain feature areas; feature similarity analysis is performed on the K preliminary stain feature areas according to the vehicle body cleaning demand target, and a stain feature similarity threshold is set; distribution space information of the K preliminary stain feature areas is obtained, and spatially adjacent and feature-similar regions of the K preliminary stain feature areas are merged based on the stain feature similarity threshold and the distribution space information to obtain N vehicle body stain merged regions; feature average values of the N vehicle body stain merged regions are calculated in sequence based on the multidimensional feature set of vehicle body stains to obtain the N vehicle body stain region feature sets.

[0032] Optionally, based on the target number of clusters K, K pixels are randomly selected from the multi-dimensional features of the vehicle body stain (such as color, shape, and texture) as initial cluster centers. These cluster centers represent the initial state of each cluster and are continuously optimized in subsequent iterations. The selection of initial cluster centers may be random or based on some heuristic rule (such as selecting representative sample points from the stain feature set). After the cluster centers are initialized, each vehicle body stain area is assigned to the closest cluster center using Euclidean distance. The cluster center with the smallest distance is considered the cluster to which the stain area belongs. After all stain areas are assigned to clusters, the center of each cluster is recalculated. Each cluster center is the mean of the features of all stain areas within the cluster. The updated cluster center better represents the characteristics of the stain areas within the cluster. After the cluster centers are updated, the pixel clustering operation is repeated until the stopping condition is met: the cluster center no longer changes significantly or the change is less than a preset threshold. K preliminary stain feature areas are obtained, each of which represents a class of stains with similar characteristics. After obtaining K preliminary stain feature regions, feature similarity analysis is performed on these regions based on the vehicle body cleaning requirements (such as the cleaning intensity required for different stain types). The similarity between the cluster centers of each preliminary stain feature region is calculated to obtain the regional similarity between each two regions. A stain feature similarity threshold is also set based on business requirements. This threshold determines which stain features are sufficiently similar to be merged into the same group of regions. Subsequently, the spatial distribution information of each preliminary stain feature region is obtained, including the location and relative position of the stain region in the image. Based on this spatial distribution information, adjacent preliminary stain feature regions are determined. The regional similarities of these adjacent regions are obtained from the calculated multiple regional similarities as the adjacent region's stain feature similarity. These stain feature similarities are then compared with the set stain feature similarity threshold. Based on the comparison results, adjacent preliminary stain feature regions with stain feature similarities less than or equal to the stain feature similarity threshold are merged to form N vehicle body stain merged regions, each of which contains one or more similar stain regions. After merging the areas, the feature average value will be calculated for each merged stain area in turn. This process involves averaging the color, shape, texture and other features of all stain samples in each merged area. By calculating the mean of these features, a single value representing the characteristics of the area can be created for each stain merged area, thereby generating a more accurate feature set of N body stain areas, providing clear reference data for subsequent cleaning plans, delivery control and other steps.In summary, through the above steps, the system starts from the preliminary stain feature area, combines feature similarity and spatial distribution information, and finally obtains N body stain merged areas. These merged areas not only have high feature consistency, but also take into account the spatial distribution of stains, making the cleaning requirements of each area clearer and more precise. This process provides important data support for subsequent optimization of cleaning plans, determination of detergent dosage, and other links.

[0033] A cleaning solution is analyzed for the N vehicle body stain area feature sets based on the vehicle wash solution parameter space to determine N stain area cleaning solution parameters.

[0034] In one embodiment, the N obtained feature sets of vehicle body stain areas are analyzed and matched based on the car wash solution parameter space. Specifically, the car wash solution parameter space contains cleaning strategies for different stain types. These strategies include multiple factors such as the type, concentration, and dosage of detergent, aiming to provide the most suitable cleaning solutions for different types of stain areas. Based on the characteristics of each stain area and combined with the data in the car wash solution parameter space, the most appropriate cleaning solution for each merged area is analyzed. For example, for a merged area with a lot of oil stains, a stronger detergent can be selected and set at a higher concentration; while for a merged area with a lot of mud stains, a mild detergent may be selected and set at a lower concentration. Through this process, specific cleaning solution parameters are determined for each stain area, forming N stain area cleaning solution parameters. These parameters will serve as the basis for subsequent detergent dosage control to ensure that different types of stains are cleaned reasonably and effectively.

[0035] Furthermore, the present application provides the method for determining the cleaning solution parameters for N stained areas, including:

[0036] Based on the parameter space of the car wash plan, the N vehicle body stain area feature sets are matched and analyzed respectively to determine N stain area matching cleaning plans, wherein the N stain area matching cleaning plans include detergent type, detergent concentration, and detergent dosage; priority analysis is performed on the N vehicle body stain area feature sets according to the importance of the cleaning areas to obtain the vehicle body stain area cleaning priorities; based on the vehicle body stain area cleaning priorities, the N stain area matching cleaning plans are impact-corrected to determine the N stain area cleaning plan parameters.

[0037] Optionally, a matching analysis is performed on the N obtained feature sets of vehicle body stain regions based on a car wash solution parameter space. The car wash solution parameter space encompasses various cleaning solution options, including detergent type (e.g., detergent, degreaser, etc.), detergent concentration, and detergent dosage. By matching each vehicle body stain region feature set with the stain feature range corresponding to each cleaning solution in the car wash solution parameter space, N matching cleaning solutions for the stain regions are obtained. After determining the preliminary cleaning solution, a weighted calculation is performed based on the cleanliness requirement of each stain region (determined by the location of the stain, such as the windshield, window, door, etc.), the area of the stain, and the type of stain. Each stain region is then assigned a corresponding priority based on this importance. This determines the cleaning priority of each vehicle body stain region. Areas with higher cleaning priorities are cleaned earlier, ensuring that critical areas and difficult-to-clean stains are promptly and thoroughly addressed. Subsequently, based on the cleaning priorities of these stained areas on the vehicle body, the cleaning plans for the N initially determined stained areas are revised and optimized. Specifically, the cleaning plan parameters for each stained area are adjusted according to the priority of each area and the impact of stain spread, ensuring that each stained area receives the most appropriate cleaning plan and achieves the best cleaning effect. In summary, through the above steps, the system not only accurately matches the cleaning plan but also adjusts the cleaning plan based on the characteristics and priority of each stained area, ensuring the efficiency and effectiveness of the cleaning process. In this way, the cleaning plan can be optimized based on the importance of the area and actual needs, thereby improving the overall quality of car washing and resource utilization.

[0038] Furthermore, the present application provides the method of modifying the impact of the N stain area matching cleaning solutions based on the vehicle body stain area cleaning priority, and determining the parameters of the N stain area cleaning solutions, including:

[0039] The N vehicle body stain area feature sets are arranged for cleaning based on the vehicle body stain area cleaning priority to obtain N stain cleaning sequence area feature sets; the stain diffusion influence degrees between the N stain cleaning sequence area feature sets are evaluated in sequence to obtain N stain area diffusion influence parameters; and the diffusion influence of the N stain area matching cleaning schemes is optimized based on the N stain area diffusion influence parameters to determine the N stain area cleaning scheme parameters.

[0040] Optionally, based on the previously obtained cleaning priority of the body stain area, N body stain area feature sets are arranged for cleaning. In this process, the body stain area feature sets corresponding to the stain areas with higher priorities are placed in front and cleaned first, while the body stain area feature sets corresponding to the stain areas with lower priorities are placed in the back. After arrangement, N stain cleaning sequence area feature sets are obtained. These feature sets are sorted according to cleaning priority and cleaning requirements to facilitate subsequent processing. Subsequently, the stain diffusion effect between the N stain cleaning sequence area feature sets is evaluated. Stain diffusion here refers to the impact that a stain area may have on other stain areas during the cleaning process, especially the secondary contamination or stain transfer that may be caused by detergent or water flow during the cleaning process. In order to evaluate the impact of the stain diffusion, the inverse calculation of the distance between each two stain areas is performed to obtain the spatial diffusion factor, which is used to quantify the spatial diffusion impact; the preset diffusion ability corresponding to the pollution type is used as the stain type factor, which is used to quantify the diffusion ability of the stain type; the preset cleaning ability of the detergent type is multiplied by the set concentration to obtain the detergent diffusion factor, which is used to quantify the diffusion effect of the detergent; the priority corresponding to the stain cleaning sequence area feature set is used as the sequential diffusion factor, which is used to quantify the diffusion impact of the priority cleaning area on the subsequent areas; by weighted summing the spatial diffusion factor, stain type factor, detergent diffusion factor and sequential diffusion factor, N stain area diffusion impact parameters are obtained. Each stain area diffusion impact parameter represents the degree of impact that the corresponding area may have on other areas during the cleaning process. Afterwards, based on the obtained diffusion impact parameters of the N stain areas, the N stain area matching cleaning solutions are optimized. The purpose of this optimization is to reduce the diffusion effect that may occur during the stain cleaning process and ensure that the cleaning of each stain area does not adversely affect other areas. For example, if the stain diffusion impact of a certain area is large, the stain area matching cleaning solution for that area will be adjusted, such as increasing the concentration of the detergent, increasing the amount of detergent, or cleaning that area first and then cleaning other areas to ensure that the stain is completely removed and avoid diffusion. In this way, the diffusion impact of the cleaning solution parameters for each stain area is optimized, and the optimal cleaning solution is finally determined as the cleaning solution parameters for the N stain areas. In summary, through the above steps, the system not only considers the cleaning priority of each stain area, but also evaluates the mutual influence between the stain areas, and avoids unnecessary contamination or reduced effect by optimizing the cleaning solution. This process ensures that the entire car washing process is more efficient and accurate, and maximizes the cleaning effect and resource utilization.

[0041] Based on the N stain area cleaning solution parameters, control logic association is performed on the detergent delivery component of the target automated car washing equipment to obtain N area detergent delivery control parameters.

[0042] In one embodiment, based on the determined N stain area cleaning solution parameters, the detergent delivery component of the target automated car washing equipment is controlled logically associated, that is, the cleaning solution parameters of each stain area are transmitted to the control system of the target automated car washing equipment corresponding to the stain area, and converted into parameter instructions that can be recognized and called by the control system of the target automated car washing equipment, thereby obtaining N regional detergent delivery control parameters. These regional detergent delivery control parameters can ensure the precise delivery of detergent to each stain area, thereby improving the cleaning effect and minimizing resource waste.

[0043] Real-time monitoring and acquisition of environmental temperature and humidity data streams, and the target automated car wash equipment performing detergent delivery control and feedback regulation optimization on the target vehicle based on the N zone detergent delivery control parameters and the environmental temperature and humidity data streams.

[0044] In one embodiment, the temperature and humidity data stream of the environment is monitored and acquired in real time through the arranged temperature and humidity sensors to reflect the climatic conditions of the current car wash environment. Subsequently, based on these temperature and humidity data, the previously determined N regional detergent delivery control parameters are adjusted and corrected. For example, in a high humidity environment, the detergent may take longer to take effect, while in a high temperature environment, the detergent may evaporate faster. The system will dynamically adjust the detergent delivery amount, concentration and other parameters based on these environmental factors, and apply the corrected regional detergent delivery control parameters to the detergent delivery control. Through this process, the detergent delivery control can be optimized in real time to ensure the best cleaning effect in each area. At the same time, the cleaning plan can be feedback-controlled according to environmental changes, further improving car wash efficiency and reducing resource waste.

[0045] Furthermore, the present application provides the method for performing detergent delivery control and feedback regulation optimization on the target vehicle, including:

[0046] Based on the ambient temperature and humidity data stream, the cleaning effect impact analysis of the N area detergent delivery control parameters is performed to obtain N stain cleaning effect influencing factors; the N area detergent delivery control parameters are regulated and corrected using the N stain cleaning effect influencing factors to determine N detergent delivery correction control parameters; and based on the N detergent delivery correction control parameters, detergent delivery control and feedback regulation optimization are performed on the target vehicle.

[0047] Preferably, after obtaining the ambient temperature and humidity data stream, the ambient temperature and humidity data stream will be used to analyze the impact of the N regional detergent delivery control parameters on the cleaning effect. Specifically, the current temperature will be compared with the reference temperature corresponding to the N regional detergent delivery control parameters, and the temperature deviation will be calculated. This deviation will be calculated as a ratio with the reference temperature to obtain the temperature impact factor. Similarly, the same operation is performed on the current humidity to obtain the humidity impact factor, and then the temperature impact factor is added to the humidity impact factor to obtain N stain cleaning effect impact factors. Subsequently, the N stain cleaning effect impact factors are subtracted from 1 respectively, and then the control parameters are adjusted and corrected by multiplying the calculated N differences with the corresponding N regional detergent delivery control parameters to determine N detergent delivery correction control parameters. Afterwards, based on the corrected N detergent delivery correction control parameters, detergent delivery control is performed on the target vehicle to accurately control the detergent delivery amount, concentration, etc. of each stain area to ensure the best cleaning effect under different environmental conditions. During the actual application process, the cleaning effect is monitored in real time, and N detergent application correction control parameters are fine-tuned based on feedback information. For example, if the cleaning effect in a certain area does not meet expectations, the detergent application amount in that area will be increased or the detergent type will be adjusted until the optimal cleaning effect is achieved. Through this feedback control process, detergent application control can be continuously optimized to ensure the entire car wash process is efficient, energy-saving, and has the best cleaning effect.

[0048] Furthermore, the present application provides the method of performing detergent delivery control and feedback regulation optimization on the target vehicle based on the N detergent delivery correction control parameters, including:

[0049] The N detergent delivery correction control parameters are used to perform detergent delivery control monitoring on the target vehicle to obtain vehicle cleaning feedback parameters; the N detergent delivery correction control parameters are dynamically regulated and optimized based on the vehicle cleaning feedback parameters, and closed-loop cleaning control of the target vehicle is performed using the optimized N detergent delivery correction control parameters.

[0050] Optionally, detergent delivery control is performed on the target vehicle based on the N detergent delivery correction control parameters obtained. During the cleaning process, the detergent delivery status of each area is continuously monitored, and the detergent delivery amount, concentration, time, and regional cleaning effect are recorded. Through this monitoring, vehicle cleaning feedback parameters for each stained area can be collected, including detergent coverage, cleaning effect, and cleaning time. These feedback parameters provide data support for subsequent dynamic regulation and help determine the effectiveness of the current cleaning strategy. Subsequently, the N detergent delivery correction control parameters are dynamically regulated and optimized based on the obtained vehicle cleaning feedback parameters. For example, if the detergent coverage rate and cleaning effect of certain areas are low, the detergent delivery amount or the detergent concentration will be increased to ensure that the stains can be completely removed. For areas that have been fully cleaned, the detergent delivery amount can be reduced to avoid wasting resources. Afterwards, closed-loop control of cleaning will be performed based on the optimized N detergent delivery correction control parameters. That is, based on the current optimization results, the detergent delivery to each stained area will be re-controlled, and precise monitoring and adjustment will be carried out to ensure that the cleaning effect of each area is optimal, and the amount of detergent delivered and the effect are optimally balanced to avoid waste of resources. At the same time, based on the feedback data continuously obtained, the detergent delivery is continuously adjusted until the expected cleaning effect is finally achieved. During this process, the detergent delivery control parameters will be continuously optimized based on real-time feedback to ensure that each stained area of the vehicle is fully cleaned. In summary, through detergent delivery control monitoring, dynamic regulation optimization and closed-loop cleaning control, the detergent delivery to each stained area is ensured to be in the best state at all times. This process makes the cleaning effect more precise and efficient, while avoiding waste of resources and ensuring the automation and intelligence of the cleaning process, ultimately providing customers with high-quality car wash services.

[0051] In summary, the embodiments of the present application have at least the following technical effects:

[0052] The embodiment of the present application first acquires a body surface stain image of a target vehicle through high-precision camera capture, performs stain feature recognition on the body surface stain image, and obtains a multi-dimensional feature set of body stains; then, clustering is performed on the multi-dimensional feature set of body stains to obtain N body stain area feature sets, and at the same time, a car wash solution parameter space is called according to a target automated car wash equipment; thereafter, a cleaning solution is analyzed for the N body stain area feature sets based on the car wash solution parameter space to determine N stain area cleaning solution parameters; then, control logic association is performed on the detergent dispensing component of the target automated car wash equipment based on the N stain area cleaning solution parameters to obtain N area detergent dispensing control parameters; finally, the ambient temperature and humidity data stream is acquired through real-time monitoring, and detergent dispensing control and feedback regulation optimization are performed on the target vehicle through the target automated car wash equipment based on the N area detergent dispensing control parameters and the ambient temperature and humidity data stream. These technical effects jointly solve the technical problems that existing automated car washing equipment lacks specificity when adding detergents, and cannot accurately control the amount of detergent added according to the actual stain conditions of the vehicle and environmental changes, resulting in poor car washing effects and waste of detergents. It achieves the technical effect of accurately dividing the stain areas according to the characteristics of the stains on the vehicle body, and formulating personalized cleaning plans based on the parameter space of the car washing plan. At the same time, the detergent addition is adjusted in real time according to the ambient temperature and humidity, thereby improving the quality of car washing, reducing detergent waste, and realizing intelligent and precise control.

[0053] Example 2, based on the same inventive concept as the intelligent detergent delivery control method for automated car washing equipment in the previous embodiment, Figure 2 As shown, the present application provides an intelligent detergent delivery control system for automated car washing equipment, the system comprising: a stain feature recognition module 11: acquiring a stain image on the body surface of a target vehicle through a high-precision camera, performing stain feature recognition on the stain image on the body surface, and obtaining a multi-dimensional feature set of body stains; a clustering module 12: performing clustering on the multi-dimensional feature set of body stains to obtain N body stain area feature sets, and at the same time calling a car wash solution parameter space according to the target automated car washing equipment; a cleaning solution parsing module 13: performing clustering on the multi-dimensional feature set of body stains to obtain N body stain area feature sets, and at the same time calling a car wash solution parameter space according to the target automated car washing equipment; a cleaning solution parsing module 13: parsing the body stains based on the car wash solution parameter space. A cleaning solution is analyzed based on N feature sets of vehicle body stain areas to determine N stain area cleaning solution parameters; a control logic association module 14 performs control logic association on the detergent delivery component of the target automated vehicle washing equipment based on the N stain area cleaning solution parameters to obtain N area detergent delivery control parameters; a delivery control module 15 monitors and acquires the ambient temperature and humidity data stream in real time, and performs detergent delivery control and feedback regulation optimization on the target vehicle through the target automated vehicle washing equipment based on the N area detergent delivery control parameters and the ambient temperature and humidity data stream.

[0054] Furthermore, the stain feature recognition module 11 is further configured to perform the following method:

[0055] Noise characteristics of the vehicle body surface stain image are identified to obtain vehicle body image noise characteristic information, and an image filter is initialized based on the vehicle body image noise characteristic information; the vehicle body surface stain image is filtered and denoised using the image filter to obtain a denoised vehicle body surface stain image; a standard vehicle body surface image is obtained based on the specification and model information of the target vehicle; stain identification and feature extraction are performed on the denoised vehicle body surface stain image based on the standard vehicle body surface image to obtain a multi-dimensional feature set of vehicle body stains.

[0056] Furthermore, the stain feature recognition module 11 is further configured to perform the following method:

[0057] The standard vehicle body surface image is used as the background area, and the grayscale distribution of the background area is identified to obtain the grayscale threshold of the vehicle body background area; the denoised vehicle body surface stain image is subjected to stain comparison and identification based on the grayscale threshold of the vehicle body background area to obtain a set of vehicle body surface stain areas; edge detection and region segmentation are performed on the set of vehicle body surface stain areas in sequence, and a set of vehicle body surface stain target frames is marked to obtain; multidimensional feature extraction is performed on the set of vehicle body surface stain target frames respectively to obtain a multidimensional feature set of vehicle body stains, which includes color features, shape features and texture features of the stain area.

[0058] Furthermore, the clustering module 12 is further configured to perform the following method:

[0059] A cluster number range is selected based on the distribution characteristic information of the multidimensional feature set of vehicle body stains; a cluster number K is sequentially selected within the cluster number range to perform clustering error calculation on the multidimensional feature set of vehicle body stains to obtain a sum of squared errors within clusters for multiple K values; an intra-cluster sum of squared errors curve is generated based on the multiple sum of squared errors within clusters for K values, and an elbow point is marked on the intra-cluster sum of squared errors curve to determine a target number of clusters K; cluster division is performed on the multidimensional feature set of vehicle body stains based on the target number of clusters K to obtain N vehicle body stain area feature sets.

[0060] Furthermore, the clustering module 12 is further configured to perform the following method:

[0061] Iterative clustering is performed on the multidimensional feature set of vehicle body stains based on the target number K of clusters to obtain K preliminary stain feature areas; feature similarity analysis is performed on the K preliminary stain feature areas according to the vehicle body cleaning demand target, and a stain feature similarity threshold is set; distribution space information of the K preliminary stain feature areas is obtained, and spatially adjacent and feature-similar regions of the K preliminary stain feature areas are merged based on the stain feature similarity threshold and the distribution space information to obtain N vehicle body stain merged regions; feature average values of the N vehicle body stain merged regions are calculated in sequence based on the multidimensional feature set of vehicle body stains to obtain the N vehicle body stain region feature sets.

[0062] Furthermore, the cleaning solution analysis module 13 is also used to perform the following method:

[0063] Based on the parameter space of the car wash plan, the N vehicle body stain area feature sets are matched and analyzed respectively to determine N stain area matching cleaning plans, wherein the N stain area matching cleaning plans include detergent type, detergent concentration, and detergent dosage; priority analysis is performed on the N vehicle body stain area feature sets according to the importance of the cleaning areas to obtain the vehicle body stain area cleaning priorities; based on the vehicle body stain area cleaning priorities, the N stain area matching cleaning plans are impact-corrected to determine the N stain area cleaning plan parameters.

[0064] Furthermore, the cleaning solution analysis module 13 is also used to perform the following method:

[0065] The N vehicle body stain area feature sets are arranged for cleaning based on the vehicle body stain area cleaning priority to obtain N stain cleaning sequence area feature sets; the stain diffusion influence degrees between the N stain cleaning sequence area feature sets are evaluated in sequence to obtain N stain area diffusion influence parameters; and the diffusion influence of the N stain area matching cleaning schemes is optimized based on the N stain area diffusion influence parameters to determine the N stain area cleaning scheme parameters.

[0066] Furthermore, the delivery control module 15 is further configured to execute the following method:

[0067] Based on the ambient temperature and humidity data stream, the cleaning effect impact analysis of the N area detergent delivery control parameters is performed to obtain N stain cleaning effect influencing factors; the N area detergent delivery control parameters are regulated and corrected using the N stain cleaning effect influencing factors to determine N detergent delivery correction control parameters; and based on the N detergent delivery correction control parameters, detergent delivery control and feedback regulation optimization are performed on the target vehicle.

[0068] Furthermore, the delivery control module 15 is further configured to execute the following method:

[0069] The N detergent delivery correction control parameters are used to perform detergent delivery control monitoring on the target vehicle to obtain vehicle cleaning feedback parameters; the N detergent delivery correction control parameters are dynamically regulated and optimized based on the vehicle cleaning feedback parameters, and closed-loop cleaning control of the target vehicle is performed using the optimized N detergent delivery correction control parameters.

[0070] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0071] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

[0072] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. An intelligent detergent dispensing control method for automated car washing equipment, characterized in that: The method comprises: Acquire a stain image on the surface of a target vehicle using a high-precision camera, perform stain feature recognition on the stain image, and obtain a multi-dimensional feature set of the stains on the vehicle body; Perform clustering on the multidimensional feature set of the vehicle body stains to obtain N vehicle body stain region feature sets, and at the same time call a car wash solution parameter space according to a target automated car wash equipment; Performing a cleaning solution analysis on the N vehicle body stain area feature sets based on the vehicle wash solution parameter space to determine the N stain area cleaning solution parameters; Performing control logic association on the detergent dispensing components of the target automated car washing equipment based on the N stain area cleaning solution parameters to obtain N area detergent dispensing control parameters; Real-time monitoring and acquisition of an ambient temperature and humidity data stream, and performing detergent dispensing control and feedback regulation optimization on the target vehicle through the target automated car wash equipment based on the N zone detergent dispensing control parameters and the ambient temperature and humidity data stream; The step of obtaining N vehicle body stain region feature sets includes: selecting a range of cluster numbers based on the distribution characteristic information of the multidimensional feature set of vehicle body stains; Selecting a cluster number K in sequence within the cluster number range to perform clustering error calculation on the multidimensional feature set of the vehicle body stains, and obtaining a sum of squares of intra-cluster errors for multiple K values; generating an intra-cluster sum of squared errors curve according to the multiple K values, marking the elbow point of the intra-cluster sum of squared errors curve, and determining the target number of clusters K; Performing clustering on the multidimensional feature set of vehicle body stains based on the target number K of clusters to obtain N vehicle body stain region feature sets; The step of performing clustering on the vehicle body stain multidimensional feature set based on the target cluster number K to obtain N vehicle body stain region feature sets includes: Performing iterative clustering on the multidimensional feature set of the vehicle body stains based on the target number of clusters K to obtain K preliminary stain feature regions; Performing feature similarity analysis on the K preliminary stain feature regions according to the vehicle body cleaning requirement target, and setting a stain feature similarity threshold; Obtaining distribution spatial information of the K preliminary stain feature regions, and merging spatially adjacent and feature-similar regions of the K preliminary stain feature regions based on the stain feature similarity threshold and the distribution spatial information to obtain N vehicle body stain merged regions; Based on the multi-dimensional feature set of the vehicle body stains, sequentially calculating the feature averages of the N vehicle body stain merged regions to obtain the N vehicle body stain region feature sets; The step of determining N cleaning solution parameters for the stained areas includes: Based on the car wash solution parameter space, matching analysis is performed on the N vehicle body stain area feature sets to determine N stain area matching cleaning solutions, wherein the N stain area matching cleaning solutions include detergent type, detergent concentration, and detergent dosage; Performing a priority analysis on the N vehicle body stain area feature sets according to the importance of the cleaning areas to obtain a cleaning priority of the vehicle body stain areas; Based on the cleaning priority of the vehicle body stain area, the matching cleaning solutions of the N stain areas are modified to determine the cleaning solution parameters of the N stain areas; The multi-dimensional feature set of vehicle body stains is obtained, including: performing noise characteristic recognition on the vehicle body surface stain image to obtain vehicle body image noise characteristic information, and initializing an image filter based on the vehicle body image noise characteristic information; Using the image filter to perform filtering and denoising on the vehicle body surface stain image to obtain a denoised vehicle body surface stain image; Acquire a standard vehicle body surface image according to the specification and model information of the target vehicle; Performing stain recognition and feature extraction on the denoised vehicle body surface stain image based on the standard vehicle body surface image to obtain a multi-dimensional feature set of vehicle body stains; The step of obtaining a multidimensional feature set of vehicle body stains includes: Taking the standard vehicle body surface image as the background area, performing grayscale distribution recognition on the background area to obtain a grayscale threshold of the vehicle body background area; Performing stain comparison and identification on the denoised vehicle body surface stain image based on the grayscale threshold of the vehicle body background area to obtain a vehicle body surface stain area set; Performing edge detection and region segmentation on the vehicle body surface stain region set in sequence, and marking to obtain a vehicle body surface stain target frame set; Multidimensional feature extraction is performed on the vehicle body surface stain target frame set to obtain a vehicle body stain multidimensional feature set, wherein the vehicle body stain multidimensional feature set includes color features, shape features, and texture features of the stain area.

2. The intelligent detergent dispensing control method for an automated car washing device according to claim 1, wherein: The step of modifying the matching cleaning solutions for the N stained areas based on the cleaning priorities of the vehicle body stain areas and determining the cleaning solution parameters for the N stained areas includes: Arrange the N body stain area feature sets for cleaning based on the body stain area cleaning priority to obtain N stain cleaning sequence area feature sets; Sequentially evaluating the degree of stain diffusion influence between the N stain cleaning sequence region feature sets to obtain N stain region diffusion influence parameters; Diffusion influence optimization is performed on the N stained area matching cleaning solutions based on the N stained area diffusion influence parameters to determine the N stained area cleaning solution parameters.

3. The intelligent detergent dispensing control method for an automated car washing device according to claim 1, wherein: The performing detergent delivery control and feedback regulation optimization on the target vehicle includes: Performing a cleaning effect analysis on the N area detergent delivery control parameters based on the ambient temperature and humidity data stream to obtain N stain cleaning effect influencing factors; Using the N stain cleaning effect influencing factors to adjust and correct the detergent delivery control parameters of the N areas, and determine N detergent delivery correction control parameters; Detergent dispensing control and feedback regulation optimization are performed on the target vehicle based on the N detergent dispensing correction control parameters.

4. The intelligent detergent dispensing control method for an automated car washing device according to claim 3, characterized in that: The performing detergent dispensing control and feedback regulation optimization on the target vehicle based on the N detergent dispensing correction control parameters includes: Using the N detergent delivery correction control parameters to perform detergent delivery control monitoring on the target vehicle to obtain vehicle cleaning feedback parameters; The N detergent delivery correction control parameters are dynamically regulated and optimized based on the vehicle washing feedback parameters, and the target vehicle is subjected to a washing closed-loop control using the optimized N detergent delivery correction control parameters.

5. Intelligent detergent delivery control system for automated car washing equipment, characterized in that: The system is used to execute the intelligent detergent dispensing control method for automated car washing equipment according to any one of claims 1 to 4, and the system comprises: Stain feature recognition module: uses a high-precision camera to capture a stain image of the target vehicle's body surface, performs stain feature recognition on the stain image, and obtains a multi-dimensional feature set of the body stain; Clustering module: performing clustering on the multi-dimensional feature set of the vehicle body stains to obtain N vehicle body stain region feature sets, and at the same time calling the parameter space of the vehicle wash solution according to the target automated vehicle wash equipment; A cleaning solution analysis module: performs cleaning solution analysis on the N vehicle body stain area feature sets based on the vehicle wash solution parameter space to determine the cleaning solution parameters for the N stain areas; A control logic association module: performing control logic association on the detergent dispensing component of the target automated car washing equipment based on the N stain area cleaning solution parameters to obtain N area detergent dispensing control parameters; The delivery control module monitors and obtains the ambient temperature and humidity data stream in real time, and performs detergent delivery control and feedback regulation optimization on the target vehicle through the target automated car washing equipment based on the N zone detergent delivery control parameters and the ambient temperature and humidity data stream.

Images