Cleaning mode switching method and device of pool multifunctional cleaning robot

Abstract

The application relates to the technical field of swimming pool cleaning equipment control, and provides a cleaning mode switching method and device for a multifunctional swimming pool cleaning robot, which acquires water quality data corresponding to a swimming pool, stain distribution images of a pool wall and a pool bottom, pool structure size data and stain type data in real time; divides a cleaning area according to the pool structure size data, generates a stain area marking result in the cleaning area in combination with the stain distribution images and the stain type data, judges the pollution level of the whole swimming pool according to the water quality data, and retrieves a corresponding cleaning mode from a preset cleaning mode library, wherein the preset cleaning mode library comprises a global coverage mode, a key reinforcement mode, a corner fitting mode and a water quality maintenance mode; generates a corresponding cleaning path plan and an execution instruction according to the retrieved cleaning mode, and controls a driving module, a brushing module and a purification module to work cooperatively. The method realizes accurate analysis of the swimming pool environment and avoids blind cleaning of a traditional fixed mode.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pool cleaning equipment control, in particular to a cleaning mode switching method and device of a pool multifunctional cleaning robot. BACKGROUND

[0002] The cleaning efficiency and adaptability of a pool cleaning robot, which is a commonly used equipment for pool maintenance, directly affect the pool maintenance effect. The traditional pool cleaning robot usually presets a fixed cleaning mode (such as fixed path coverage, single frequency brushing, etc.), but in the actual pool environment, the water quality condition, the stain distribution (such as pool wall scale, pool bottom silt, corner algae, etc.) and the pool structure (such as the ladder gap, the arc-shaped pool wall) have significant differences, and the stain removal effect will dynamically change during the cleaning process. In the prior art, the cleaning robot lacks comprehensive sensing ability for real-time water quality data, stain type, regional pollution degree and pool structure, and cannot dynamically adjust the cleaning strategy according to the real-time environment. For example, the traditional scheme cannot distinguish between light and heavy stain areas and match different cleaning intensity. The cleaning of complex structure areas (such as the junction of the pool wall and the pool bottom) is often insufficient due to the fixed angle of the robot body, and cannot intelligently switch modes according to the real-time feedback effect data during the cleaning process, which may cause "over cleaning" or "insufficient cleaning" problems. In addition, the prior art does not combine water quality maintenance (such as purifier release and circulating filtration) with physical brushing to form a linkage strategy, and the cleaning function is single.

[0003] Therefore, there is an urgent need for a method that can real-time perceive the environment, intelligently divide the cleaning area and dynamically switch the cleaning mode, so as to improve the adaptability and cleaning efficiency of the pool cleaning robot. SUMMARY

[0004] The present application provides a cleaning mode switching method and device of a pool multifunctional cleaning robot, which aims to solve the problem that the traditional scheme cannot distinguish between light and heavy stain areas and match different cleaning intensity, and the cleaning of complex structure areas (such as the junction of the pool wall and the pool bottom) is often insufficient due to the fixed angle of the robot body, and cannot intelligently switch modes according to the real-time feedback effect data during the cleaning process, which may cause "over cleaning" or "insufficient cleaning" problems.

[0005] In a first aspect, the present application provides a cleaning mode switching method of a pool multifunctional cleaning robot, applied to the cleaning robot, comprising:

[0006] Through the water quality sensor, the camera, the ultrasonic ranging module and the stain recognition module, the water quality data corresponding to the pool, the stain distribution image of the pool wall and the pool bottom, the pool structure size data and the stain type data are collected in real time;

[0007] According to the pool structure size data, the cleaning area is divided, the stain distribution image and the stain type data are combined, the stain area mark result is generated in the cleaning area, the pollution level of the whole pool is judged according to the water quality data, the corresponding cleaning mode is called from the preset cleaning mode library, and the corresponding cleaning mode is called from the preset cleaning mode library. The cleaning mode library includes a global coverage mode, a key reinforcement mode, a corner fitting mode and a water quality maintenance mode; wherein the global coverage mode is used to cover the cleaning at a uniform speed in a spiral path; the key reinforcement mode is used to clean in a reciprocating high-frequency brushing mode when there is a heavy stain area; the corner fitting mode is used to process the junction of the pool wall and the pool bottom and the ladder gap, adjust the corresponding body angle and enable the flexible brush head to fit the cleaning; the water quality maintenance mode is used to release the water quality purifying agent and perform the circulating filtration when the water quality data is abnormal.

[0008] According to the called cleaning mode, the corresponding cleaning path planning and execution instruction are generated, and the driving module, the brushing module and the purifying module are controlled to work cooperatively.

[0009] In the cleaning process, the real-time state data of the cleaning area is acquired in real time, the cleaning area division and the cleaning mode parameters are dynamically adjusted according to the real-time state data, and if it is detected that the execution effect of the current cleaning mode does not reach the preset cleaning standard, a matching cleaning mode is re-called from the cleaning mode library.

[0010] In some embodiments, the water quality data, the stain distribution image of the pool wall and the pool bottom, the pool structure size data and the stain type data of the pool are collected in real time by the water quality sensor, the camera, the ultrasonic ranging module and the stain identification module, including: controlling the water quality sensor to continuously collect the turbidity, pH value, residual chlorine concentration and pollutant particle content data of the pool water; controlling the camera to collect images of the pool wall and the pool bottom at a preset frame rate, generating continuous frame images containing stain position and shape; controlling the ultrasonic ranging module to emit ultrasonic signals to the pool wall, the pool bottom and the structure such as the ladder, calculating the distance data of each structure according to the echo time and constructing the three-dimensional contour of the pool; controlling the stain identification module to identify the stain type as any one of the mud, algae, scale and grease based on the image color feature, texture feature and gray value difference, and mark the coordinate position of each stain type in the image.

[0011] In some embodiments, before the cleaning area is divided according to the pool structure size data, the method further comprises: removing burst abnormal values by performing noise reduction processing on the water quality data through a median filtering algorithm; enhancing the contrast of the stain distribution image by using a histogram equalization algorithm, so as to improve the distinguishability of the stain and the pool wall or pool bottom background; performing coordinate calibration on the pool structure size data obtained by the ultrasonic ranging module, establishing a local coordinate system with the initial position of the cleaning robot as the coordinate origin, and correcting the measurement error through multi-frame data fusion; and forming a standardized vector according to the preprocessed water quality data, the stain distribution image, the pool structure size data and the stain type data.

[0012] In some embodiments, the cleaning area is divided according to the pool structure size data, comprising: dividing the pool into a pool bottom plane area, a vertical pool wall area, a pool wall and pool bottom junction arc area, a ladder area and a handrail gap area based on the calibrated pool three-dimensional contour data; assigning a unique area identifier to each area, and setting an upper limit of the moving speed of the cleaning robot in the area and an allowed range of the body inclination angle of the cleaning robot according to the geometric characteristics of the area; for an irregular pool, decomposing the complex structure into several calculable standard geometric units through a piecewise fitting algorithm, and dividing the cleaning sub-area respectively; the irregular pool includes an arc-shaped pool wall and a special-shaped step.

[0013] In some embodiments, the stain area marking result is generated in the cleaning area by combining the stain distribution image and the stain type data, comprising: extracting the stain contour from the preprocessed stain distribution image through an image segmentation algorithm, and calculating the area and the average pixel gray value of each stain area; calculating the pollution index of each stain area according to the pollution degree weight of the stain type preset, combining the stain area and the average gray value; comparing the pollution index with the preset heavy stain area, moderate stain area and light stain threshold interval, marking the heavy stain area, moderate stain area and light stain area in the corresponding cleaning area, and adding a stain type label to each marked area; wherein the pollution index corresponding to the heavy stain area is greater than a first threshold value, the pollution index corresponding to the moderate stain area is less than or equal to the first threshold value and greater than a second threshold value, the pollution index corresponding to the light stain area is less than or equal to the second threshold value, and the first threshold value is greater than the second threshold value.

[0014] In some embodiments, the preset cleaning standard includes that the residual stain area ratio of a light stain area is not more than 5%, the residual stain area ratio of a medium stain area is not more than 10%, the residual stain area ratio of a heavy stain area is not more than 20%, and the decrease amplitude of a key indicator in the water quality data is not less than 30%, the key indicator including turbidity and pollutant particle content; and if it is detected that the execution effect of the current cleaning mode does not reach the preset cleaning standard, a matched cleaning mode is re-called from the cleaning mode library, including: after the cleaning mode is executed or after each sub-area cleaning is completed, the real-time state data is compared with the preset cleaning standard, if the residual area ratio of any one type of stain area or the improvement amplitude of the water quality indicator does not reach the standard, the mode switching logic is triggered; wherein the mode switching logic includes re-calculating the cleaning priority and calling the matched cleaning mode according to the current real-time collected water quality data, residual stain distribution image and pool structure data, and if the execution of the global coverage mode does not reach the standard, the key reinforcement mode is called to process the residual area.

[0015] In some embodiments, the pollution level of the entire pool is determined according to the water quality data, and a corresponding cleaning mode is called from the preset cleaning mode library, including: a water quality pollution level judgment rule library is established, and multi-level threshold intervals of turbidity, pH value, residual chlorine concentration and pollutant particle content are defined in the rule library; a fuzzy logic algorithm is used to fuzz the pollution degree of each water quality parameter to generate a fuzzy membership value; the fuzzy membership degrees of each parameter are weighted and summed by a preset weight coefficient to obtain the overall pollution level of the pool; when the overall pollution level reaches a preset starting threshold, the water quality maintenance mode is preferentially called, and the release amount of the purifying agent and the circulation filtration time are adjusted according to the pollution level.

[0016] In some embodiments, the cleaning path planning and execution instructions corresponding to the called cleaning mode are generated, and the driving module, the brushing module and the purifying module are controlled to work cooperatively, including: if the global coverage mode is called, a spiral coverage path with the current position of the cleaning robot as the starting point is generated according to the coordinate range of the pool bottom plane area, the path interval is not more than the effective cleaning width of the brushing module, and the driving module is controlled to move at a uniform speed; if the key reinforcement mode is called, a reciprocating cleaning sub-path is generated by extending 10 cm outward based on the boundary coordinates of the marked heavy stain area, the rotating speed of the brush head of the brushing module is increased to a high frequency gear, and the contact pressure of the brush head and the stain surface is increased; if the corner fitting mode is called, the inclination angle of the cleaning robot body is calculated according to the curvature radius of the junction arc area of the pool wall and the pool bottom, so that the brush head axis is perpendicular to the tangent of the arc, and the flexible brush head is switched, and the driving module is controlled to move along the junction line at a low speed; if the water quality maintenance mode is called, the purifying agent of the corresponding type is released from the purifying agent storage cabin according to the pollutant type in the water quality data, the built-in filtration pump is started, the circulation filtration is performed at a flow rate of 1.5 times the pool water circulation flow rate, and the camera is used to monitor the uniformity of the purifying agent diffusion in real time.

[0017] In some embodiments, the dynamic adjustment of the cleaning area division and the cleaning mode parameters according to the real-time state data comprises: collecting images of the cleaned area in real time through the camera, performing difference calculation on the images with the stain distribution images before cleaning, and identifying the positions of the residual stains that are not removed; if the proportion of the area of the residual stains to the area of the original marked area exceeds 15%, the residual area corresponding to the residual stain positions is re-marked as a new moderate stain area, and a corresponding sub-area is added in the existing cleaning area division; the moving speed of the cleaning robot and the brush head pressure in the complex structure area are dynamically adjusted according to the real-time returned driving module current value and the brush head motor torque value, wherein when the current value exceeds 120% of the rated current, the moving speed is automatically reduced by 50% and the brush head pressure is reduced by 30%.

[0018] In a second aspect, the application provides a cleaning mode switching device of a multifunctional pool cleaning robot, applied to the cleaning robot, comprising:

[0019] a data acquisition unit configured to collect water quality data, stain distribution images of the pool walls and the pool bottom, pool structure size data, and stain type data in real time through the water quality sensor, the camera, the ultrasonic ranging module, and the stain identification module carried by the cleaning robot;

[0020] a mode acquisition unit configured to divide the cleaning area according to the pool structure size data, generate stain area marking results in the cleaning area in combination with the stain distribution images and the stain type data, determine the pollution level of the entire pool according to the water quality data, and retrieve a corresponding cleaning mode from a preset cleaning mode library, wherein the preset cleaning mode library includes a global coverage mode, a key reinforcement mode, a corner fitting mode, and a water quality maintenance mode; the global coverage mode is used to cover and clean at a uniform speed in a spiral path; the key reinforcement mode is used to clean in a reciprocating high-frequency brushing manner when there is a heavy stain area; the corner fitting mode is used to adjust the corresponding robot body angle and enable the flexible brush head to fit and clean when processing the junction of the pool wall and the pool bottom and the staircase gap; and the water quality maintenance mode is used to release water purifying agents and perform cyclic filtration when the water quality data is abnormal;

[0021] an instruction execution unit configured to generate corresponding cleaning path planning and execution instructions according to the retrieved cleaning mode, and control the driving module, the brushing module, and the purification module to work cooperatively;

[0022] a mode switching unit configured to acquire real-time state data of the cleaning area in real time during the cleaning process, dynamically adjust the cleaning area division and the cleaning mode parameters according to the real-time state data, and retrieve a matched cleaning mode from the cleaning mode library again if it is detected that the execution effect of the current cleaning mode does not reach the preset cleaning standard.

[0023] In the prior art, the cleaning mode switching of the pool cleaning robot depends on preset programs or simple sensor feedback (such as single distance detection or stain identification), lacks multi-dimensional data fusion processing of water quality data, stain distribution image, pool structure size and stain type, and does not construct an intelligent algorithm model based on fuzzy logic and decision tree algorithm to realize cleaning priority calculation and mode dynamic matching. Through the technical solutions of the first step to the sixth step, the present application first proposes to use multi-sensor to collect multi-dimensional data in real time, dynamically divide the cleaning area through the intelligent algorithm model, mark the stain grade and match the differentiated cleaning mode, and dynamically adjust the strategy based on the real-time feedback data in the cleaning process, thereby solving the core problem of fixed mode and poor adaptability in the traditional scheme. The prior art does not disclose a dynamic switching mechanism combining multi-source data fusion and intelligent algorithm, and does not propose a control method of linking the modes such as global coverage, key reinforcement, corner fitting and water quality maintenance with real-time environmental data.

[0024] The cleaning mode switching method and device of the pool multifunctional cleaning robot provided by the embodiment of the present application, the method collects data in real time through a water quality sensor, a camera, an ultrasonic ranging module and a stain identification module, combines an intelligent model constructed based on fuzzy logic and a decision tree algorithm, realizes accurate analysis of the pool environment, and avoids blind cleaning of the traditional fixed mode; the global coverage, key reinforcement, corner fitting and other modes are called in a targeted manner according to the stain grade (severe, moderate and slight) and the pool structure to divide the area, the cleaning efficiency is improved, and resource waste is avoided; the cleaning parameters are dynamically adjusted according to the real-time feedback data in the cleaning process, and the mode is automatically triggered when the effect is not up to standard, thereby ensuring the reliability of the cleaning effect; the physical brushing (different brush heads and paths) and water quality maintenance (purifying agent release and circulating filtration) are combined to form a multifunctional collaborative cleaning system, thereby covering the full-scene demand of pool maintenance.

[0025] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0027] Figure 1 is a step schematic flow chart of a cleaning mode switching method of a pool multifunctional cleaning robot provided by an embodiment of the present application;

[0028] Figure 2Fig. 1 is a schematic diagram of a principle of a cleaning mode switching method of a multifunctional cleaning robot for a swimming pool according to an embodiment of the present application.

[0029] It should be understood that the general description above and the following detailed description are only exemplary and explanatory, and are not intended to limit the present application. DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of the present application.

[0031] The flowcharts shown in the drawings are only exemplary and are not necessarily required to include all the contents and operations / steps, and are not necessarily required to be executed in the described order. For example, some operations / steps can be further decomposed, combined or partially combined, and thus the actual execution order can be changed according to actual situations.

[0032] It should be understood that, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, the terms “first”, “second”, etc. are used to distinguish the same items or similar items with basically the same functions and effects. Those of ordinary skill in the art can understand that the terms “first”, “second”, etc. do not limit the quantity and execution order, and the terms “first”, “second”, etc. also do not necessarily mean that they are different.

[0033] It should be understood that the terms used in the present application specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the present application specification and the appended claims, unless otherwise clearly indicated by the context, the singular forms “a”, “an” and “the” are intended to include the plural forms.

[0034] It should also be understood that the term “and / or” used in the present application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0035] Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. The following embodiments and features in the embodiments can be combined with each other without conflict.

[0036] The pool cleaning robot is a common equipment for pool maintenance, and its cleaning efficiency and adaptability directly affect the pool maintenance effect. The traditional pool cleaning robot usually presets a fixed cleaning mode (such as fixed path coverage, single frequency brushing, etc.), but in the actual pool environment, the water quality condition, the stain distribution (such as pool wall scale, pool bottom silt, corner algae, etc.) and the pool structure (such as the gap of the escalator, the arc-shaped pool wall) have significant differences, and the stain removal effect will dynamically change during the cleaning process. In the prior art, the cleaning robot lacks comprehensive sensing capability for real-time water quality data, stain type, regional pollution degree and pool structure, and cannot dynamically adjust the cleaning strategy according to the real-time environment. For example, the traditional scheme cannot distinguish between light and heavy stain areas and match differentiated cleaning intensity, and the cleaning of complex structure areas (such as the junction of the pool wall and the pool bottom) is often insufficient due to the fixed angle of the robot body, and cannot intelligently switch modes according to the real-time feedback effect data during the cleaning process, which is prone to the problems of "over cleaning" or "insufficient cleaning". In addition, the prior art does not combine water quality maintenance (such as purifier release and circulating filtration) with physical brushing to form a linkage strategy, and the cleaning function is single.

[0037] Therefore, there is an urgent need for a method that can real-time perceive the environment, intelligently divide the cleaning area and dynamically switch the cleaning mode, so as to improve the adaptability and cleaning efficiency of the pool cleaning robot.

[0038] Please refer to Figure 1 , Figure 1 is a schematic flow chart of the cleaning mode switching method of the pool multifunctional cleaning robot provided by an embodiment of the present application. The cleaning mode switching method of the pool multifunctional cleaning robot can be realized by the cleaning robot, and the specific type of the cleaning robot provided by the present application embodiment is not limited.

[0039] Specifically, as shown in Figures 1 to 2 The cleaning mode switching method of the pool multifunctional cleaning robot provided by the present application includes steps S101 to S104, which are described in detail as follows:

[0040] Step S101. Through the water quality sensor, camera, ultrasonic ranging module and stain recognition module carried, real-time acquisition of water quality data corresponding to the pool, pool wall and pool bottom stain distribution image, pool structure size data and stain type data.

[0041] Specifically, by integrating multiple sensors, real-time multi-dimensional data of the pool environment is obtained, providing a basis for subsequent strategy formulation. The collected data includes: water quality data: water pollution level, pH value, turbidity, residual chlorine content, etc.; stain distribution and type: location, area, severity (mild / severe) and type (scale, silt, algae, etc.) of pool wall / floor stains; pool structure size: pool wall curvature, ladder position, pool bottom slope, pool wall and pool bottom junction area (inside and outside corners) geometric parameters; dynamic feedback data: real-time updated stain removal effect, water quality changes, etc. during cleaning.

[0042] Water quality sensors are deployed at the front or side of the robot by using multi-parameter water quality sensors (such as pH electrode, turbidity sensor, conductivity sensor) to monitor water quality parameters in real time.

[0043] The camera is equipped with a waterproof high-definition camera (supports infrared or underwater fill light), installed at the front or top of the body, and captures images of the pool wall, pool bottom and corners with a resolution of ≥1080P and a frame rate of ≥30fps, supporting wide-angle lenses to cover a larger area.

[0044] The ultrasonic ranging module is deployed around the body with 3-6 ultrasonic sensors to emit fan-shaped sound waves to scan pool walls, ladders, corners and other structures, obtain distance data (accuracy ±5mm), and construct a three-dimensional contour model of the pool.

[0045] The stain recognition module processes camera images in real time based on image recognition algorithms (such as convolutional neural network CNN), identifies stain types (training set includes scale, silt, algae and other features), and evaluates stain coverage area and concentration through pixel analysis. The data from each sensor is synchronized by timestamp, and a synchronous clock (such as IEEE 1588) is used to ensure spatiotemporal consistency; image data is preprocessed by denoising (median filtering), grayscale conversion, etc., and ranging data is filtered by Kalman filter to remove noise, generating structured data (such as point cloud map, two-dimensional grid map).

[0046] Step S102. Divide the cleaning area according to the pool structure size data, generate a stain area marking result in the cleaning area in combination with the stain distribution image and stain type data, judge the pollution level of the whole pool according to the water quality data, and retrieve the corresponding cleaning mode from a preset cleaning mode library, which includes a global coverage mode, a key reinforcement mode, a corner fitting mode and a water quality maintenance mode; wherein the global coverage mode is used to cover the cleaning at a uniform speed in a spiral path; the key reinforcement mode is used to clean in a reciprocating high-frequency brushing mode when there is a heavy stain area; the corner fitting mode is used to adjust the corresponding body angle and enable the flexible brush head to fit when processing the junction of the pool wall and the pool bottom and the escalator gap; and the water quality maintenance mode is used to release water quality purifying agent and perform circulating filtration when the water quality data is abnormal.

[0047] Specifically, the functional areas are divided based on the structure data, the cleaning strategy is matched in combination with the stain distribution and water quality data, and the optimal mode is retrieved from the preset mode library.

[0048] The area division divides the pool into a pool bottom plane, a vertical pool wall, a junction of a male and female corner, an escalator gap, an arc-shaped wall surface and the like; the stain marking marks heavy / light stain areas (such as red marking heavy algae area and yellow marking light silt area) on the area map; the pollution level includes comprehensive water quality turbidity, stain coverage area and type, and defines the pollution level (such as level I light, level II moderate and level III heavy); and the mode matching selects a single or combined mode (such as global coverage + key reinforcement) from the mode library according to the area characteristics and the pollution level.

[0049] The area division algorithm identifies the pool wall and pool bottom junction line through edge detection (Canny operator) based on ultrasonic point cloud data and camera image, and calculates the area geometric parameters (such as escalator gap width and arc-shaped wall surface curvature radius) in combination with ranging data;

[0050] The grid method (Grid Map) is adopted to divide the pool into 50cm x 50cm basic units, mark the type (pool bottom, pool wall, corner, escalator) and structural characteristics (such as curvature > 90° marked as arc-shaped area) of each unit.

[0051] The stain area marking and pollution level judgment output the stain type and concentration value of each pixel by performing semantic segmentation (such as U-Net network) on the camera image, and set the threshold (such as pixel concentration > 70% marked as heavy stain area);

[0052] The pollution level calculation formula includes: pollution level = f (water quality turbidity, heavy stain area proportion, algae / water scale and other difficult-to-clean stain proportion); wherein f is a weighted function (such as water quality accounting for 30%, stain area accounting for 50% and type accounting for 20%), and levels I-III are divided.

[0053] Step S103. According to the retrieved cleaning mode, the corresponding cleaning path planning and execution instructions are generated to control the driving module, brushing module and purification module to work cooperatively.

[0054] Specifically, according to the target mode, the precise path is generated to coordinate the driving, brushing and purification modules to execute the task, ensuring efficient collaboration.

[0055] The path planning combines the region division results and stain marks to generate a collision-free optimal path; through parameter configuration of the driving module (motor speed, steering), brushing module (frequency, pressure), and purification module (release amount, timing), and avoiding action conflicts between modules (such as adjusting the path to avoid the released area when purifying).

[0056] The path planning algorithm includes: global coverage mode: based on SLAM (simultaneous localization and mapping) technology to build a pool map, using an improved Boustrophedon blocking algorithm to divide the area into sub-blocks and generate a spiral coverage path, with an adjacent path overlap rate of 10% to ensure no omission; key reinforcement mode: generate a back-and-forth straight path for heavily stained areas, with a spacing equal to the brush head width (such as 20 cm), and a coverage frequency ≥3 times; corner fitting mode: calculate the body tilt angle (such as the angle θ between the pool wall and the pool bottom, the body tilt θ-10°) through the kinematic model, the path is an arc motion along the boundary line, and the speed is reduced to 0.2 m / s to ensure fitting.

[0057] The hardware control strategy includes: driving module: four-wheel differential drive, real-time adjustment of left and right wheel speed according to path curvature (such as left wheel speed < right wheel in arc area), equipped with IMU inertial measurement unit for real-time attitude calibration; brushing module: servo motor drives the brush head, dynamically adjusts the torque through current feedback in key reinforcement mode (torque ≥0.5 N*m), flexible brush head with built-in pressure sensor, pressure stable at 5-8 N when fitting; purification module: liquid tank capacity 5L, electromagnetic valve controls release amount (such as 5mL flocculant released per square meter), after release, start the circulating pump to work for 10 minutes, and at the same time drive the robot to move along the pool wall at a speed of 0.3 m / s to promote diffusion.

[0058] Step S104. In the cleaning process, real-time state data of the cleaning area is obtained in real time, and the cleaning area division and cleaning mode parameters are dynamically adjusted according to the real-time state data, if the current cleaning mode execution effect does not reach the preset cleaning standard, a matching cleaning mode is retrieved from the cleaning mode library.

[0059] Specifically, the cleaning effect is monitored through real-time data, and the region division and mode parameters are dynamically optimized to form a closed-loop control.

[0060] Real-time state data: post-cleaning stain residue rate, water quality improvement value, brush head fit (pressure feedback), motor energy consumption (overload detection); adjustment mechanism: re-divide non-compliant areas, switch modes or modify parameters (such as increasing brushing frequency); mode switching conditions: trigger re-call logic when residue rate > 20% or water quality is not up to standard. Effect evaluation indicators: stain removal rate: calculated by comparing before and after images (removal rate = (initial pixel concentration - current pixel concentration) / initial pixel concentration), preset standard ≥ 80%; water quality compliance rate: turbidity < 20 NTU and pH value 6.5-8.5, if not up to standard, extend the working time of the purification module; fit feedback: when the pressure sensor data < 3N, it is determined that the fit is insufficient, triggering the second adjustment of the body angle (± 5°).

[0061] Every 5 minutes, re-scan the cleaned area through the camera, if a heavy residual stain (area > 0.5m 2 ) is detected, mark it as a new key area and insert it into the current path; judge the brush head load according to the motor current data (reduce the moving speed when overloaded, increase the brushing frequency when underloaded), dynamically adjust the speed and pressure using PID algorithm; when the removal rate is detected for two consecutive times < 70%, switch from "key reinforcement mode" to "key reinforcement + water quality maintenance combined mode" (synchronous release of decontaminant to assist brushing).

[0062] Abnormal processing includes: if the ultrasonic sensor detects an obstacle (such as a sudden entry of debris into the pool), immediately pause cleaning and start an obstacle avoidance path (return to the breakpoint after bypassing the obstacle); when the power is < 20%, automatically switch to "return mode" and return to the charging base along the shortest path.

[0063] In some embodiments, the real-time collection of water quality data, pool wall and pool bottom stain distribution images, pool structure size data, and stain type data through the mounted water quality sensor, camera, ultrasonic ranging module, and stain identification module includes: controlling the water quality sensor to continuously collect turbidity, pH value, residual chlorine concentration, and pollutant particle content data of the pool water; controlling the camera to collect images of the pool wall and pool bottom at a preset frame rate, generating continuous frame images containing stain location and shape; controlling the ultrasonic ranging module to emit ultrasonic signals to the pool wall, bottom, and ladder structures, calculating distance data for each structure based on echo time and constructing a three-dimensional profile of the pool; controlling the stain identification module to identify the stain type as any of silt, algae, scale, and grease based on image color features, texture features, and gray value differences, and mark the coordinate positions of each stain type in the image.

[0064] By specifying the specific collection objects, data types, and implementation methods of multiple sensors, the comprehensiveness and accuracy of environmental data are ensured.

[0065] The water quality sensor focuses on four core indicators: turbidity, pH value, residual chlorine concentration, and pollutant particle content. The camera collects images at a fixed frame rate, recording the spatial position and morphological characteristics of stains. The ultrasonic ranging constructs a three-dimensional profile of the pool by echo time, covering structures such as walls, floors, and escalators. Stain identification is based on color, texture, and gray scale differences, classifying stains into four typical types and locating them.

[0066] The water quality sensor control uses an integrated water quality sensor, collecting data every 2 seconds, continuously monitoring water turbidity (unit NTU), pH value (accuracy ±0.01), residual chlorine concentration (mg / L), and pollutant particle content (measured by laser scattering method >5μm particle count).

[0067] The camera frame rate is set to 25fps, resolution 1920x1080, equipped with a waterproof shell (IP68 level), and the lens is coated with an anti-fouling layer. When shooting, the robot's current position is taken as the center, and a fisheye correction algorithm is used to generate a planar expansion diagram, marking the stain coordinates (x, y) and morphology (block, sheet, flocculent).

[0068] By deploying 6 groups of ultrasonic sensors distributed in front, back, left, right, and two sides at an angle, 40kHz sound waves are emitted every 100ms, and the distance is calculated according to the echo time (formula: distance = speed of sound x time / 2). The point cloud data of the pool wall, floor, and escalator are constructed by triangulation method, generating a three-dimensional contour model (accuracy ±1cm).

[0069] The stain recognition algorithm includes: color features: extracting hue (H) and saturation (S) features in HSV color space (e.g. algae are green, H∈[40°, 80°]); texture features: calculating contrast and entropy values through gray level co-occurrence matrix (GLCM) (e.g. scale texture is rough, entropy value >0.8); gray value difference: threshold segmentation method to distinguish stains from background (e.g. sand stains have gray value <80, pool bottom background has gray value >150); the classifier uses support vector machine (SVM) to train the model, inputs the feature vector, and outputs the stain type (sand, algae, scale, oil), and marks the coordinates in the image (pixel-level positioning).

[0070] In some embodiments, before dividing the cleaning area according to the pool structure size data, it also includes: denoising the water quality data by median filtering algorithm to remove sudden outliers; using histogram equalization algorithm to enhance the contrast of the stain distribution image, improving the discrimination between stains and pool wall or pool bottom background; coordinate calibration of the pool structure size data obtained by the ultrasonic ranging module, establishing a local coordinate system with the initial position of the cleaning robot as the coordinate origin, and correcting the measurement error through multi-frame data fusion; forming a standardized vector according to the pretreated water quality data, stain distribution image, pool structure size data, and stain type data.

[0071] The data quality is improved to support subsequent processing by denoising, enhancing, calibrating and standardizing the original sensor data. The water quality data is denoised by median filtering to remove sudden noise; the image contrast is enhanced by histogram equalization to improve the contrast between stains and background; the coordinate calibration and data fusion establish a local coordinate system with the initial position of the robot as the origin, and multi-frame data fusion corrects the ranging error; the standardized vector converts heterogeneous data into a uniform format input vector.

[0072] The water quality data is denoised by using a 5-point median filter window to remove outliers (such as jump data caused by sudden electromagnetic interference) exceeding 3σ for turbidity, pH value and other sequence data. The image contrast is enhanced by converting the RGB image to a grayscale image and applying the histogram equalization algorithm to expand the pixel grayscale value distribution to the full range of [0, 255], making the stain edge clearer (such as the grayscale difference between the light algae area and the pool wall is increased from 20 to 50). The coordinate calibration and data fusion establish a local coordinate system: the x-axis points to the long side of the pool, the y-axis points to the short side, and the z-axis is vertical upward (the initial position of the robot is (0, 0, 0)); the ranging data fusion uses a sliding window (window size 10 frames) to perform Kalman filtering on the ultrasonic data to correct the measurement error caused by water surface fluctuations (error reduced from ±3 cm to ±0.5 cm).

[0073] The standardized vector is constructed by converting water quality data (4 dimensions), image features (stain area, type one-hot encoding), structural data (region coordinates, curvature), etc. into a unified 128-dimensional feature vector, normalized to the [0, 1] interval (formula: (x-μ) / σ, μ is the mean, σ is the standard deviation).

[0074] In some embodiments, the cleaning area is divided according to the pool structure size data, including: based on the calibrated pool three-dimensional contour data, the pool is divided into a pool bottom plane area, a vertical pool wall area, a pool wall and pool bottom junction arc area, a ladder area and a handrail gap area; each area is assigned a unique area identifier, and the upper limit of the movement speed of the cleaning robot in the area and the allowed range of the body inclination angle are set according to the geometric characteristics of the area; for irregular pools, the complex structure is decomposed into several calculable standard geometric units by a piecewise fitting algorithm, and the cleaning sub-area is divided respectively; the irregular pool includes an arc-shaped pool wall and a special-shaped step.

[0075] Based on the three-dimensional contour data, the pool is divided into functional sub-areas, the area characteristic parameters are set, and the irregular structure is processed.

[0076] Standard region division: divided into 5 types of regions, including pool bottom, pool wall, junction arc, staircase, and handrail gap; the upper limit of moving speed and the range of body inclination angle are defined for each region; the complex structure is decomposed into standard geometric units by piecewise fitting for irregular pool processing.

[0077] Standard region division and identification includes: pool bottom plane region: horizontal region with z coordinate <0.5 m and curvature <5°, assigned with identifier R01, upper limit of moving speed 0.5 m / s, and allowed range of inclination angle [-5°, 5°]; vertical pool wall region: region with z coordinate 0.5-1.5 m and normal vector perpendicular to horizontal plane, identifier R02, upper limit of speed 0.3 m / s, and allowed range of inclination angle [0°, 20°] (convenient for fitting); junction arc region: arc transition zone with pool wall and pool bottom included angle <135°, radius R≤30 cm, identifier R03, upper limit of speed 0.2 m / s, and allowed range of inclination angle [15°, 30°]; staircase region: detected step-like structure (height difference ≥15 cm), identifier R04, upper limit of speed 0.15 m / s, and high-speed movement is prohibited to prevent collision; handrail gap region: narrow region with width <10 cm, identifier R05, and flexible brush head needs to be enabled.

[0078] Irregular structure processing includes: for arc-shaped pool wall (curvature radius R=50-100 cm), piecewise Bezier curve fitting is adopted to decompose it into 5-10 arc segments (each segment has a central angle ≤30°); for special-shaped steps (non-right-angle steps), straight line fitting is adopted to fit the step edges, height and width parameters of each step are defined, and independent sub-regions are generated (e.g., step facade is marked as R02 sub-class).

[0079] In some embodiments, the combination of the stain distribution image and the stain type data generates a stain region marking result in the cleaning area, including: extracting the stain contour from the pre-processed stain distribution image by an image segmentation algorithm, calculating the area and pixel gray value mean of each stain region; according to the pollution degree weight preset by the stain type, combining the stain area and the gray value mean, calculating the pollution index of each stain region; comparing the pollution index with the preset heavy stain region, moderate stain region and light stain threshold interval, marking the heavy stain region, moderate stain region and light stain region in the corresponding cleaning area, and adding a stain type label to each marked region; wherein the pollution index of the heavy stain region is greater than the first threshold value, the pollution index of the moderate stain region is less than or equal to the first threshold value and greater than the second threshold value, and the pollution index of the light stain region is less than or equal to the second threshold value, and the first threshold value is greater than the second threshold value.

[0080] By image segmentation and weighted calculation, the pollution degree of the stain region is quantified, and different level regions are marked and labeled with type labels.

[0081] Stain profile extraction obtains stain boundary based on image segmentation; pollution index calculation combines stain type weight, area, and mean gray value; threshold comparison and labeling divides heavy, moderate, and light areas and adds type labels.

[0082] Stain profile extraction and feature calculation use a U-Net semantic segmentation model (pretrained on a pool stain dataset) to output a stain profile mask, calculate the area (unit: pixels 2 , converted to the actual area m 2 ), and the mean gray value (reflecting stain concentration, 0-255, the smaller the value, the higher the concentration).

[0083] The pollution index calculation formula includes: Pollution index = wt*T + wa*A / Amax + wg*(1-G / 255); where:

[0084] wt is the type weight (scale = 0.4, algae = 0.3, sand = 0.2, grease = 0.4); wa and wg are the area and gray weight (both 0.3); the first threshold = 0.7 (heavy), the second threshold = 0.4 (moderate), <0.4 is light; mark with different colors on the area map: red (heavy + scale), orange (heavy + algae), yellow (moderate), green (light), each marked area stores coordinates, type, pollution index, etc.

[0085] In some embodiments, the preset cleaning standard includes that the residual stain area of the light stain area accounts for no more than 5%, the moderate stain area accounts for no more than 10%, the heavy stain area accounts for no more than 20%, and the key indicators in the water quality data decrease by no less than 30%, the key indicators including turbidity and pollutant particle content; if the current cleaning mode execution effect does not meet the preset cleaning standard, the matching cleaning mode is re-called from the cleaning mode library, including: after the cleaning mode is executed or after each sub-area cleaning is completed, comparing the real-time state data with the preset cleaning standard, if the residual area ratio of any type of stain area or the improvement amplitude of the water quality indicators does not meet the standard, triggering the mode switching logic; wherein the mode switching logic includes recalculating the cleaning priority and calling the matching cleaning mode according to the current real-time collected water quality data, residual stain distribution image, and pool structure data, and if the global coverage mode does not meet the standard, calling the key reinforcement mode to process the residual area.

[0086] By defining the residual standards of different stain levels and water quality improvement targets, setting mode switching conditions, and ensuring that the cleaning effect meets the standard.

[0087] Residual standards include: mild ≤ 5%, moderate ≤ 10%, severe ≤ 20% residual area; water quality indicators include: turbidity, pollutant particle content decreased by ≥ 30%; switching logic recalculates priority when not met, retrieves matching mode (such as global to focus on strengthening).

[0088] By taking a new photo of each sub-area after cleaning, the residual area ratio is calculated by image difference method (formula: residual rate = residual pixel number / initial stain pixel number x 100%); the improvement rate of water quality indicators = (pre-cleaning value - post-cleaning value) / pre-cleaning value x 100%, requiring turbidity and particle content to improve by ≥ 30% (such as turbidity from 80 NTU to below 56 NTU).

[0089] Mode switching trigger conditions include: single area residual rate: severe > 20%, moderate > 10%, mild > 5%; global water quality improvement < 30%; prioritize the area with the highest residual rate, if the original mode is global coverage (not met), retrieve the focus strengthening mode, and generate a dense brushing path for the residual area (from 3 times to 5 times).

[0090] In some embodiments, the water quality data is used to determine the overall pollution level of the pool, and a corresponding cleaning mode is retrieved from a pre-set cleaning mode library, including: establishing a water quality pollution level judgment rule library, defining multi-level threshold intervals for turbidity, pH value, residual chlorine concentration and pollutant particle content in the rule library; using fuzzy logic algorithm to fuzz the pollution degree of each water quality parameter, generating fuzzy membership values; weighting and summing the fuzzy membership of each parameter by a pre-set weight coefficient to obtain the overall pollution level of the pool; when the overall pollution level reaches a pre-set starting threshold, the water quality maintenance mode is prioritized, and the release amount of purifying agent and the circulation filtration time are adjusted according to the pollution level.

[0091] By fuzzy logic algorithm, the overall pollution level is calculated by synthesizing multiple water quality parameters, and the water quality maintenance mode and parameter adjustment are driven. The rule library is established by defining multi-level threshold intervals for each parameter; the fuzzy processing is achieved by converting the parameters into "low, medium, high" membership values; the weighted sum is achieved by obtaining the pollution level to adjust the purifying agent release strategy.

[0092] The water quality pollution level rule library is shown in the following table:

[0093]

[0094] Fuzzy logic calculation by calculating the membership of each parameter (e.g. turbidity = 60 NTU, membership "high pollution" = 0.8, "medium pollution" = 0.2); weighted formula includes: pollution level = 0.4 x turbidity membership + 0.3 x particle membership + 0.2 x pH membership + 0.1 x residual chlorine membership, result ∈ [0, 1], ≥ 0.6 start water quality maintenance mode.

[0095] Purification strategy adjustment includes: mild pollution (0.4-0.6): release 50 mL flocculant, cycle filtration for 15 minutes; severe pollution (> 0.6): release 100 mL special algae removal agent, cycle filtration for 30 minutes, while reducing the brushing speed to prolong the action time of the purification agent.

[0096] In some embodiments, the corresponding cleaning path planning and execution instructions are generated according to the retrieved cleaning mode, and the driving module, the brushing module and the purification module are controlled to work cooperatively, including: if the global coverage mode is retrieved, a spiral coverage path with the current position of the cleaning robot as the starting point is generated according to the coordinate range of the pool bottom plane area, the path spacing is not more than the effective cleaning width of the brushing module, and the driving module is controlled to move at a uniform speed; if the key reinforcement mode is retrieved, a reciprocating cleaning sub-path is generated by extending 10 centimeters outward based on the boundary coordinates of the marked heavy stain area, the brush head rotation speed of the brushing module is increased to the high frequency gear, and the contact pressure of the brush head with the stain surface is increased; if the corner fitting mode is retrieved, the inclination angle of the cleaning robot body is calculated according to the curvature radius of the intersection arc area of the pool wall and the pool bottom, so that the brush head axis is perpendicular to the tangent of the arc, and the flexible brush head is switched to, the driving module is controlled to move along the intersection line at a low speed; if the water quality maintenance mode is retrieved, the corresponding type of purification agent is released from the purification agent storage cabin according to the type of pollutants in the water quality data, and the built-in filtration pump is started to perform cycle filtration at a flow rate of 1.5 times the pool water circulation flow rate, and the camera is used to monitor the uniformity of the purification agent diffusion in real time.

[0097] For different cleaning modes, generate exclusive path planning and hardware control instructions to realize multi-module cooperation. Global coverage includes: spiral path, uniform speed movement; key reinforcement includes: extended boundary reciprocating path, high frequency and high pressure brushing; corner fitting includes: inclined body fitting arc, flexible brush head low speed movement; water quality maintenance includes: release corresponding purification agent, control filtration pump flow.

[0098] Global coverage mode includes: path planning: generate a spiral path with a current position as the starting point, with a pitch = brush head width - 10 cm (e.g. brush head width 30 cm, pitch 20 cm), ensuring 10% overlap rate; driving control: four-wheel differential drive, speed 0.4 m / s, IMU real-time calibration of heading angle (automatic correction when deviation > 2°).

[0099] The focus strengthening mode includes: path expansion: the coordinates of the heavy stain area (x1, y1, x2, y2) are expanded by 10 cm (x1-10 cm, y1-10 cm, x2+10 cm, y2+10 cm), generating a round-trip straight line path (interval = brush head width); brushing control: the brush head rotation speed is increased from 50 rpm to 120 rpm, and the brush head pressure is adjusted to 8-10 N through pressure sensor feedback.

[0100] The corner fitting mode includes: angle calculation: according to the junction circular arc curvature radius R, the body inclination angle θ = arctan (brush head radius / R) (for example, R = 20 cm, brush head radius 5 cm, θ ≈ 14°), to ensure that the brush head axis is perpendicular to the tangent of the circular arc; hardware switching: enable the silicone flexible brush head (hardness Shore A 40°), reduce the driving speed to 0.15 m / s, and make a circular arc interpolation motion along the junction line.

[0101] The water quality maintenance mode includes: purifying agent release: according to the type of pollutants (such as releasing copper sulfate for algae and releasing citric acid for scale), the release amount is controlled by electromagnetic valve (release amount per square meter = pollution level x 20 mL); filtration control: start the circulating pump with a flow rate of 150 L / h (pool water circulating flow rate is 1.5 times), and the camera monitors the purifying agent diffusion in real time (stop circulating when color uniformity > 90%).

[0102] In some embodiments, the dynamic adjustment of the cleaning area division and the cleaning mode parameters according to the real-time state data includes: real-time image acquisition of the cleaned area by the camera, difference calculation with the stain distribution image before cleaning, identification of the residual stain position that has not been removed; if the residual stain area accounts for more than 15% of the original marked area, the residual stain position is re-marked as a new moderate stain area, and a corresponding sub-area is added in the existing cleaning area division; according to the real-time returned driving module current value and brush head motor torque value, the moving speed of the cleaning robot in the complex structure area and the brush head pressure are dynamically adjusted, wherein when the current value exceeds the rated current by 120%, the moving speed is automatically reduced by 50% and the brush head pressure is reduced by 30%.

[0103] Residual stain identification includes: difference calculation to locate the uncleaned area; area re-marking includes: residual area over 15% is marked as a new moderate area; parameter self-adaptation includes: dynamically adjusting the speed and pressure according to the current and torque to avoid overload.

[0104] Residual stain detection includes: gray scale difference between the cleaned image and the pre-processed original image (formula: ΔG = |Gcleaned - Gcleaned|), and the area with ΔG < 30 is determined as residual stain, and the area ratio is calculated.

[0105] Region redivision logic includes: if residual proportion > 15%, mark as a new region in the map (e.g. the original heavy region is marked as a moderate region R06 after residual), insert into the current cleaning queue, priority higher than the uncleaned light region; when regenerating the path, the shortest path to the new region is planned through the A* algorithm to avoid repeated coverage of the already compliant region.

[0106] Drive module current monitoring includes: rated current 1.5A, more than 120% (1.8A), determine that the brush head is stuck (e.g. stuck in the escalator gap), speed from 0.3m / s to 0.15m / s, brush head pressure from 10N to 7N; Brush head motor torque feedback includes: torque sensor real-time monitoring, under load (torque <0.3N*m) to increase the speed to 150rpm, to fully utilize the cleaning capacity.

[0107] In some embodiments, by proposing a multi-modal Transformer-based environmental perception framework, visual, ultrasonic, and water quality data are fused for joint modeling, and the lack of stain sample labeling is solved through self-supervised learning, achieving robust stain detection and classification.

[0108] Multi-modal data encoding includes: visual branch: using an improved YOLOv8 model, embedding attention mechanism (CBAM) to focus on the stain area, outputting stain position mask and type probability (silt / algae, etc.); Ultrasonic branch: three-dimensional point cloud data is encoded into structural feature vector (including curvature, roughness, etc. geometric properties) through PointNet++; Water quality branch: turbidity, residual chlorine and other parameters are mapped into water quality feature vector through fully connected layer; The fusion layer learns the correlation between sensors (such as the co-occurrence probability of high turbidity area and silt stain) through the cross-modal attention mechanism of Transformer.

[0109] Self-supervised pre-training strategy includes: mask image modeling: randomly occlude 30% of the image area, train the model to predict the stain type and texture of the missing part (use contrast loss function); Ultrasonic data enhancement: add Gaussian noise to the three-dimensional point cloud, and learn the invariance representation of the structural features through the twin network; Pseudo-label generation: automatically label unlabelled data using threshold method (e.g. regions with gray value <50 and ultrasonic roughness >0.8 are marked as "heavy silt stain"), and construct a weakly supervised training set.

[0110] Real-time inference optimization deploys the model to an edge computing module (such as NVIDIA Jetson AGX Orin), and controls the inference delay within 50ms through model quantization technology; The output after fusion includes stain coordinates (accuracy ±5cm), type confidence (>0.7 trigger alarm) and structural risk level (e.g. collision risk index of escalator gap).

[0111] In some embodiments, by constructing a graph neural network (GNN) model, the pool structure is abstracted as a graph node with attributes, the relevance between regions is learned through graph convolution, intelligent regional division based on pollution propagation rules is realized, and the trend of stain diffusion is predicted by using a spatiotemporal prediction model.

[0112] The pool structure graph modeling includes: node definition: each standard region (such as pool bottom partition, pool wall plate) is taken as a graph node, and the attributes include geometric parameters (curvature, area), historical pollution data (algae outbreak frequency in the past 7 days); edge definition: the connection relationship between nodes (such as the water flow resistance coefficient of the edge of the intersection of the pool bottom and the pool wall), and the weight reflects the pollution migration probability (such as when the water flow velocity is greater than 0.2 m / s, the edge weight is +0.3).

[0113] The pollution prediction and regional dynamic division includes: a spatiotemporal graph convolution network (ST-GCN): inputting the water quality data (time dimension) and the regional pollution index (spatial dimension) in the past 24 hours, predicting the pollution index change trend of each region in the next 2 hours (such as the escalator region due to water flow retention, the predicted algae growth rate is +15%); intelligent division strategy: if it is predicted that the pollution index of a pool wall region will exceed the threshold, it is automatically upgraded from the “moderate region” to the “key monitoring region”, and the pre-cleaning path is planned in advance.

[0114] The cleaning priority sorting algorithm is based on the shortest path priority of the graph (Dijkstra algorithm improvement): combining the predicted pollution diffusion speed, the “high propagation risk node” (such as the intersection circular arc node connecting multiple regions, and the pollution diffusion influence degree is calculated by the PageRank algorithm) is preferentially processed; after completing the cleaning of a sub-region, the pollution state of the graph node is updated, triggering the GNN to recalculate the regional relevance (such as after the cleaning of a certain region, the pollution migration probability of the adjacent region is reduced).

[0115] In some embodiments, by constructing a digital twin model of pool cleaning, the physical environment and the robot state are mapped in real time, the cleaning strategy is dynamically updated by combining an online learning algorithm, and an intelligent closed loop of “prediction-execution-feedback” is realized.

[0116] The digital twin construction includes: geometric twin: generating a high-precision pool three-dimensional model (accuracy ±0.5 cm) based on ultrasonic point cloud data, and integrating a water flow simulation module (CFD simplified model, calculating the water flow velocity field in different regions); behavior twin: establishing a robot dynamics model (considering water pressure resistance, brush head friction), inputting driving instructions to predict the moving trajectory (position error <2 cm); pollution twin: simulating the diffusion process of the purifying agent (such as the concentration distribution prediction of copper sulfate in pool water, error <8%) through the reaction-diffusion equation.

[0117] The online learning optimization mechanism includes: model updating: after completing each cleaning task, compare the actual cleaning effect (residual rate, water quality improvement data) with the digital twin prediction result, and update the pollution diffusion model parameters using the online gradient descent algorithm; policy iteration: if the actual residual rate is more than 10% higher than the predicted value, trigger policy correction: increase the scrubbing pressure of this type of stain by 2N, increase the brush speed by 10 rpm, and verify the adjusted effect in the digital twin; anomaly detection: identify device failure (such as brush head jam) through the difference between the twin and the physical robot (such as drive motor current difference > 15%), and automatically switch to the backup cleaning module.

[0118] Multi-agent collaborative expansion shares the cleaning data of each pool through federated learning technology when deploying multiple robots (only encrypted model parameters are uploaded to protect user privacy); the central server periodically aggregates global knowledge and updates the general cleaning strategy (such as finding that the frequency of algae outbreak is high in a certain area during the rainy season, and automatically increasing the default value of the release amount of algae removal agent).

[0119] The embodiments of the present application also provide a cleaning mode switching device of a pool multifunctional cleaning robot. The cleaning mode switching device of the pool multifunctional cleaning robot is used to execute the steps of the cleaning mode switching method of the pool multifunctional cleaning robot shown in each of the above embodiments. The cleaning mode switching device of the pool multifunctional cleaning robot can be a single server or a server cluster, or the cleaning mode switching device of the pool multifunctional cleaning robot can be a terminal, which can be a handheld terminal, a notebook computer, a wearable device, or a robot, etc.

[0120] The cleaning mode switching device of the pool multifunctional cleaning robot includes:

[0121] The data acquisition unit is configured to acquire water quality data, pool wall and pool bottom stain distribution images, pool structure size data, and stain type data corresponding to the pool in real time through the water quality sensor, the camera, the ultrasonic ranging module, and the stain recognition module.

[0122] The mode acquisition unit is configured to divide a cleaning area according to the pool structure size data, generate a stain area marking result in the cleaning area in combination with a stain distribution image and stain type data, determine a pollution level of the pool as a whole according to water quality data, and retrieve a corresponding cleaning mode from a preset cleaning mode library, wherein the preset cleaning mode library includes a global coverage mode, a key reinforcement mode, a corner fitting mode, and a water quality maintenance mode; the global coverage mode is configured to uniformly cover the cleaning area at a constant speed in a spiral path; the key reinforcement mode is configured to clean the area with heavy stains in a reciprocating high-frequency brushing manner; the corner fitting mode is configured to adjust a corresponding body angle and enable a flexible brush head to fit and clean when processing the junction of the pool wall and the pool bottom and the staircase gap; and the water quality maintenance mode is configured to release a water quality purifying agent and perform cyclic filtration when the water quality data is abnormal.

[0123] The instruction execution unit is configured to generate corresponding cleaning path planning and execution instructions according to the retrieved cleaning mode, and control the driving module, the brushing module, and the purifying module to work cooperatively.

[0124] The mode switching unit is configured to acquire real-time state data of the cleaning area in real time during the cleaning process, dynamically adjust the cleaning area division and the cleaning mode parameters according to the real-time state data, and retrieve a matched cleaning mode from the cleaning mode library again if it is detected that the execution effect of the current cleaning mode does not reach a preset cleaning standard.

[0125] It should be noted that, for the convenience and brevity of description, the specific working processes of the cleaning mode switching device and each module of the pool multifunctional cleaning robot described above can refer to the corresponding processes in the cleaning mode switching method embodiments of the pool multifunctional cleaning robot described in the above embodiments, which will not be described herein again.

[0126] The cleaning mode switching method of the pool multifunctional cleaning robot described above can be implemented in the form of a computer program, which can run on the device provided in the present application.

[0127] The present application also provides a cleaning robot. The cleaning robot includes a processor, a memory, and a network interface connected through a device bus, wherein the memory can include a storage medium and an internal memory.

[0128] The storage medium can store an operating device and a computer program. The computer program includes program instructions, which, when executed, can cause the processor to execute any one of the cleaning mode switching methods of the pool multifunctional cleaning robot.

[0129] The processor is configured to provide computing and control capabilities to support the operation of the entire cleaning robot.

[0130] The internal memory provides an environment for the running of a computer program in a non-volatile storage medium, which, when executed by the processor, can cause the processor to perform any one of the cleaning mode switching methods of the multifunctional pool cleaning robot.

[0131] The network interface is used for network communication, such as sending assigned tasks. Those skilled in the art can understand that the structures shown in the above embodiments are only part of the structures related to the scheme of the present application, and do not constitute a limitation on the terminal to which the scheme of the present application is applied. Specifically, the cleaning robot can include more or fewer components than mentioned in the embodiments, or combine certain components, or have a different component arrangement.

[0132] It should be understood that the processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0133] In one embodiment, the processor is configured to run a computer program stored in the memory to perform the following steps:

[0134] The water quality sensor, camera, ultrasonic ranging module, and stain recognition module are used to collect real-time water quality data, pool wall and pool bottom stain distribution images, pool structure size data, and stain type data of the pool;

[0135] The cleaning area is divided according to the pool structure size data, and stain area label results are generated in the cleaning area in combination with the stain distribution images and stain type data. The pollution level of the entire pool is determined according to the water quality data, and the corresponding cleaning mode is retrieved from a preset cleaning mode library. The preset cleaning mode library includes a global coverage mode, a key reinforcement mode, a corner fitting mode, and a water quality maintenance mode. The global coverage mode is used to uniformly cover the cleaning at a constant speed in a spiral path. The key reinforcement mode is used to clean in a reciprocating high-frequency brushing manner when there is heavy stain in the area. The corner fitting mode is used to adjust the corresponding body angle and enable the flexible brush head to fit the cleaning when processing the junction of the pool wall and the pool bottom and the ladder gap. The water quality maintenance mode is used to release water purifying agent and perform circulating filtration when the water quality data is abnormal.

[0136] According to the retrieved cleaning mode, a corresponding cleaning path planning and execution instruction is generated to control the driving module, the brushing module and the purification module to work cooperatively;

[0137] In the cleaning process, real-time state data of the cleaning area is acquired in real time, the cleaning area division and the cleaning mode parameters are dynamically adjusted according to the real-time state data, and if it is detected that the execution effect of the current cleaning mode does not reach the preset cleaning standard, a matched cleaning mode is retrieved from the cleaning mode library.

[0138] In some embodiments, the water quality data, the pool wall and pool bottom stain distribution image, the pool structure size data and the stain type data corresponding to the swimming pool are collected in real time by the mounted water quality sensor, camera, ultrasonic ranging module and stain identification module, including: controlling the water quality sensor to continuously collect the turbidity, pH value, residual chlorine concentration and pollutant particle content data of the swimming pool water body; controlling the camera to collect images of the pool wall and pool bottom at a preset frame rate, generating continuous frame images containing stain position and shape; controlling the ultrasonic ranging module to emit ultrasonic signals to the pool wall, bottom and ladder structures, calculating the distance data of each structure according to the echo time and constructing the three-dimensional profile of the pool; controlling the stain identification module to identify the stain type as any one of silt, algae, scale and grease based on image color features, texture features and gray value differences, and mark the coordinate position of each stain type in the image.

[0139] In some embodiments, before the cleaning area is divided according to the pool structure size data, it further includes: performing noise reduction processing on the water quality data by a median filter algorithm to remove sudden outliers; performing contrast enhancement on the stain distribution image by a histogram equalization algorithm to improve the distinguishability of the stain and the pool wall or pool bottom background; performing coordinate calibration on the pool structure size data obtained by the ultrasonic ranging module to establish a local coordinate system with the initial position of the cleaning robot as the coordinate origin, and correct the measurement error through multi-frame data fusion; forming a standardized vector according to the pretreated water quality data, stain distribution image, pool structure size data and stain type data.

[0140] In some embodiments, the cleaning area is divided according to the pool structure size data, including: based on the calibrated pool three-dimensional profile data, the pool is divided into a pool bottom plane area, a vertical pool wall area, a pool wall and pool bottom junction arc area, a ladder area and a handrail gap area; each area is assigned a unique area identifier, and the upper limit of the moving speed of the cleaning robot in the area and the allowed range of the body inclination angle are set according to the geometric characteristics of the area; for irregular swimming pools, the complex structure is decomposed into several calculable standard geometric units by a piecewise fitting algorithm, and the cleaning sub-area is divided respectively; the irregular swimming pool includes an arc-shaped pool wall and a special-shaped step.

[0141] In some embodiments, the combination of the stain distribution image and the stain type data generates a stain area marking result in the cleaning area, including: extracting the stain contour from the pre-processed stain distribution image by an image segmentation algorithm, calculating the area and pixel gray value mean of each stain area; according to the pollution degree weight preset by the stain type, combining the stain area and the gray value mean, calculating the pollution index of each stain area; comparing the pollution index with the preset threshold interval of heavy stain area, moderate stain area and light stain area, marking the heavy stain area, moderate stain area and light stain area in the corresponding cleaning area, and attaching a stain type label to each marked area; wherein the pollution index corresponding to the heavy stain area is greater than the first threshold value, the pollution index corresponding to the moderate stain area is less than or equal to the first threshold value and greater than the second threshold value, and the pollution index corresponding to the light stain area is less than or equal to the second threshold value, and the first threshold value is greater than the second threshold value.

[0142] In some embodiments, the preset cleaning standard includes that the residual stain area ratio of the light stain area does not exceed 5%, the moderate stain area does not exceed 10%, the heavy stain area does not exceed 20%, and the key indicators in the water quality data decrease by no less than 30%, the key indicators including turbidity and pollutant particle content; if the detection result of the current cleaning mode execution effect does not reach the preset cleaning standard, the matching cleaning mode is re-called from the cleaning mode library, including: after the completion of the cleaning mode execution or after the completion of the cleaning of each sub-area, comparing the real-time state data with the preset cleaning standard, if the residual area ratio of any type of stain area or the improvement amplitude of the water quality indicators does not meet the standard, triggering the mode switching logic; wherein the mode switching logic includes re-calculating the cleaning priority and calling the matching cleaning mode according to the real-time collected water quality data, residual stain distribution image and pool structure data, and if the execution of the global coverage mode does not meet the standard, calling the key reinforcement mode to process the residual area.

[0143] In some embodiments, the pollution level of the pool as a whole is determined according to the water quality data, and the corresponding cleaning mode is called from the preset cleaning mode library, including: establishing a water quality pollution level judgment rule library, and defining multi-level threshold intervals of turbidity, pH value, residual chlorine concentration and pollutant particle content in the rule library; using a fuzzy logic algorithm to fuzz the pollution degree of each water quality parameter to generate a fuzzy membership value; weighting and summing the fuzzy membership of each parameter by a preset weight coefficient to obtain the overall pollution level of the pool; when the overall pollution level reaches a preset starting threshold, the water quality maintenance mode is preferentially called, and the release amount of the purifying agent and the circulation filtration time are adjusted according to the pollution level.

[0144] In some embodiments, the method further comprises: if the global coverage mode is called, generating a spiral coverage path with the current position of the cleaning robot as the starting point according to the coordinate range of the pool bottom plane area, the path interval being not more than the effective cleaning width of the brushing module, and controlling the driving module to move at a constant speed; if the intensive reinforcement mode is called, generating a reciprocating cleaning sub-path by extending 10 cm outward on the basis of the boundary coordinates of the marked heavy stain area, controlling the brush head rotation speed of the brushing module to be raised to a high-frequency gear, and increasing the contact pressure of the brush head and the stain surface; if the corner fitting mode is called, calculating the inclination angle of the body of the cleaning robot according to the curvature radius of the junction arc area of the pool wall and the pool bottom, so that the brush head axis is perpendicular to the tangent of the arc, and switching to a flexible brush head, and controlling the driving module to move along the junction line at a low speed; and if the water quality maintenance mode is called, releasing the corresponding type of purifying agent from the purifying agent storage cabin according to the type of pollutants in the water quality data, starting the built-in filter pump to perform cyclic filtration at a flow rate of 1.5 times the pool water circulation flow rate, and monitoring the uniformity of the purifying agent diffusion in real time through the camera.

[0145] In some embodiments, the method further comprises: identifying the position of the residual stain that has not been removed by calculating the difference between the image of the cleaned area collected by the camera in real time and the stain distribution image before cleaning; if the proportion of the area of the residual stain to the area of the original marked area is more than 15%, re-marking the residual area corresponding to the residual stain as a new moderate stain area, and adding a corresponding sub-area in the existing cleaning area division; and dynamically adjusting the moving speed of the cleaning robot and the brush head pressure in the complex structure area according to the real-time returned driving module current value and brush head motor torque value, wherein when the current value exceeds 120% of the rated current, the moving speed is automatically reduced by 50% and the brush head pressure is reduced by 30%.

[0146] In some embodiments, the application further provides a computer readable storage medium storing a computer program, the computer program comprising program instructions, and the processor executes the program instructions to implement the steps of the cleaning mode switching method of the swimming pool multifunctional cleaning robot provided in the above embodiments.

[0147] The computer readable storage medium can be an internal storage unit of the cleaning robot, such as a hard disk or a memory of the cleaning robot. The computer readable storage medium can also be an external storage device of the cleaning robot, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc.

[0148] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed by the present application, and these modifications or replacements should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for switching cleaning modes of a multi-functional swimming pool cleaning robot, characterized in that, Applications in cleaning robots, including: The system uses a water quality sensor, camera, ultrasonic ranging module, and stain recognition module to collect real-time data on the pool's water quality, stain distribution on the pool walls and bottom, pool structure dimensions, and stain types. The cleaning area is divided based on the pool's structural dimensions. Combined with stain distribution images and stain type data, stain area markings are generated within each cleaning area. The overall pollution level of the pool is determined based on water quality data, and a corresponding cleaning mode is retrieved from a pre-set cleaning mode library. This library includes a global coverage mode, a focused cleaning mode, a corner-fitting mode, and a water quality maintenance mode. The global coverage mode uses a spiral path for uniform cleaning. The focused cleaning mode uses a repetitive, high-frequency brushing method to clean heavily soiled areas. The corner-fitting mode adjusts the machine angle and uses a flexible brush head for cleaning the junction of the pool wall and bottom, and the gaps in the ladder. The water quality maintenance mode releases a water purifier and performs circulating filtration when water quality data is abnormal. Based on the retrieved cleaning mode, the corresponding cleaning path plan and execution instructions are generated to control the drive module, scrubbing module and purification module to work together. During the cleaning process, real-time status data of the cleaning area is acquired, and the cleaning area division and cleaning mode parameters are dynamically adjusted based on the real-time status data. If the current cleaning mode is found to be not performing up to the preset cleaning standard, a matching cleaning mode is retrieved from the cleaning mode library.

2. The method according to claim 1, characterized in that, The system utilizes a water quality sensor, camera, ultrasonic ranging module, and stain recognition module to collect real-time data on the pool's water quality, stain distribution images on the pool walls and bottom, pool structural dimensions, and stain type, including: The water quality sensor continuously collects data on turbidity, pH value, residual chlorine concentration, and pollutant particle content in the pool water. The camera is controlled to capture images of the pool wall and bottom at a preset frame rate, generating continuous frame images that include the location and shape of the stains; The ultrasonic ranging module is controlled to emit ultrasonic signals to the pool wall, bottom and ladder, and the distance data of each structure is calculated based on the echo time to construct the three-dimensional outline of the pool. The stain recognition module identifies stain types as mud, algae, scale, and grease based on image color features, texture features, and grayscale differences, and marks the coordinate position of each stain type in the image.

3. The method according to claim 1, characterized in that, Before dividing the cleaning area according to the pool structure size data, the method also includes: The water quality data is denoised by using a median filtering algorithm to remove sudden outliers. Histogram equalization algorithm is used to enhance the contrast of the stain distribution image, thereby improving the distinction between the stain and the background of the pool wall or bottom. The pool structure dimension data acquired by the ultrasonic ranging module is calibrated by coordinates. A local coordinate system is established with the initial position of the cleaning robot as the coordinate origin, and the measurement error is corrected by fusing multiple frames of data. A standardized vector is generated based on the pretreated water quality data, stain distribution images, pool structure size data, and stain type data.

4. The method according to claim 1, characterized in that, The process of dividing the cleaning area according to the pool's structural dimensions includes: Based on the calibrated 3D contour data of the pool, the pool is divided into the bottom plane area, the vertical pool wall area, the arc area where the pool wall and the bottom meet, the ladder area, and the handrail gap area. Each area is assigned a unique area identifier, and the maximum speed limit for the cleaning robot and the allowable range of body tilt angle in that area are set according to the geometric characteristics of the area. For irregular swimming pools, the complex structure is decomposed into several computable standard geometric units using a piecewise fitting algorithm, and each unit is divided into a clean sub-region; the irregular swimming pool includes curved pool walls and irregularly shaped steps.

5. The method according to claim 1, characterized in that, The process of combining stain distribution images and stain type data to generate stain area marking results within the cleaning area includes: The stain contours are extracted from the preprocessed stain distribution image using an image segmentation algorithm, and the area and average pixel gray value of each stain region are calculated. Based on the preset pollution degree weight of the stain type, and combined with the stain area and the mean gray value, the pollution index of each stain area is calculated. The contamination index is compared with preset threshold ranges for heavily stained areas, moderately stained areas, and lightly stained areas. The corresponding cleaning areas are marked as heavily stained areas, moderately stained areas, and lightly stained areas, and a stain type label is attached to each marked area. The contamination index corresponding to a heavily stained area is greater than a first threshold, the contamination index corresponding to a moderately stained area is less than or equal to the first threshold and greater than a second threshold, and the contamination index corresponding to a lightly stained area is less than or equal to the second threshold. The first threshold is greater than the second threshold.

6. The method according to claim 5, characterized in that, The preset cleaning standards include that the residual stain area in lightly soiled areas does not exceed 5%, in moderately soiled areas it does not exceed 10%, and in heavily soiled areas it does not exceed 20%, and the key indicators in the water quality data decrease by no less than 30%. Key indicators include turbidity and pollutant particle content. If the current cleaning mode is found to be not meeting the preset cleaning standards, a matching cleaning mode is retrieved from the cleaning mode library, including: After the cleaning mode is completed or after each sub-area is cleaned, the real-time status data is compared with the preset cleaning standards. If the residual area ratio of any type of stain or the improvement of water quality indicators does not meet the standard, the mode switching logic is triggered. The mode switching logic includes recalculating the cleaning priority and retrieving the matching cleaning mode based on the currently collected water quality data, residual stain distribution images, and pool structure data. If the global coverage mode fails to meet the requirements, the key enhancement mode is retrieved to treat the residual areas.

7. The method according to claim 1, characterized in that, The step of determining the overall pollution level of the swimming pool based on water quality data and retrieving the corresponding cleaning mode from a preset cleaning mode library includes: Establish a rule base for judging water pollution levels, defining multi-level threshold ranges for turbidity, pH value, residual chlorine concentration, and pollutant particulate content in the rule base; The pollution degree of each water quality parameter is fuzzified using a fuzzy logic algorithm to generate fuzzy membership values; The overall pollution level of the swimming pool is obtained by weighting and summing the fuzzy membership degrees of each parameter using preset weighting coefficients. When the overall pollution level reaches the preset activation threshold, the water quality maintenance mode is activated first, and the amount of purifying agent released and the circulation filtration time are adjusted according to the pollution level.

8. The method according to claim 1, characterized in that, The process of generating corresponding cleaning path planning and execution instructions based on the retrieved cleaning mode, and controlling the collaborative work of the drive module, scrubbing module, and purification module includes: If the global coverage mode is invoked, a spiral coverage path is generated starting from the current position of the cleaning robot based on the coordinate range of the bottom plane area. The path spacing does not exceed the effective cleaning width of the brushing module, and the drive module is controlled to move at a constant speed. If the focus enhancement mode is activated, for the marked heavily soiled areas, a reciprocating cleaning sub-path is generated by extending 10 centimeters outward from the area boundary coordinates, the brush head speed of the scrubbing module is increased to a high frequency level, and the contact pressure between the brush head and the soiled surface is increased. If the corner fitting mode is selected, the tilt angle of the cleaning robot body is calculated based on the radius of curvature of the arc area where the pool wall and the pool bottom meet, so that the brush head axis is perpendicular to the tangent of the arc, and the flexible brush head is switched to control the drive module to move along the junction line at a low speed. If the water quality maintenance mode is activated, the corresponding type of purifier will be released from the purifier storage compartment according to the type of pollutants in the water quality data, and the built-in filter pump will be started to circulate and filter the water at a flow rate 1.5 times that of the pool water circulation flow rate. The uniformity of the purifier diffusion will be monitored in real time by a camera.

9. The method according to claim 1, characterized in that, The method of dynamically adjusting the cleaning area division and cleaning mode parameters based on real-time status data includes: The system uses a camera to capture images of the cleaned area in real time, and calculates the difference between these images and the images of the stain distribution before cleaning to identify the location of any remaining stains. If the area of ​​residual stains exceeds 15% of the area of ​​the original marked area, the residual area corresponding to the location of the residual stains will be remarked as a new medium stain area, and a corresponding sub-area will be added to the existing cleaning area division. Based on the real-time feedback of the drive module current value and the brush head motor torque value, the cleaning robot's moving speed and brush head pressure are dynamically adjusted in complex structural areas. When the current value exceeds 120% of the rated current, the moving speed is automatically reduced by 50% and the brush head pressure is reduced by 30%.

10. A cleaning mode switching device for a multi-functional swimming pool cleaning robot, characterized in that, Applications in cleaning robots, including: The data acquisition unit is used to collect real-time water quality data, images of stain distribution on the pool walls and bottom, pool structural dimensions, and stain type data of the swimming pool through the built-in water quality sensor, camera, ultrasonic ranging module, and stain recognition module. The pattern acquisition unit is used to divide the cleaning area according to the pool's structural dimensions, combine the stain distribution image and stain type data, generate stain area marking results within the cleaning area, and determine the overall pollution level of the pool based on water quality data. It then retrieves the corresponding cleaning mode from a preset cleaning mode library, which includes a global coverage mode, a focused cleaning mode, a corner-fitting mode, and a water quality maintenance mode. The global coverage mode is used for uniform coverage cleaning along a spiral path; the focused cleaning mode is used for cleaning heavily soiled areas with repetitive high-frequency brushing; the corner-fitting mode is used to adjust the machine angle and activate a flexible brush head for cleaning the junction of the pool wall and bottom and the gaps in the ladder; and the water quality maintenance mode is used to release a water purifier and perform circulating filtration when water quality data is abnormal. The instruction execution unit is used to generate corresponding cleaning path planning and execution instructions based on the retrieved cleaning mode, and control the drive module, brushing module and purification module to work together. The mode switching unit is used to acquire real-time status data of the cleaning area during the cleaning process, dynamically adjust the cleaning area division and cleaning mode parameters based on the real-time status data, and if it is detected that the current cleaning mode does not meet the preset cleaning standard, it retrieves a matching cleaning mode from the cleaning mode library.

Images