1074 results about "Stain" patented technology

The invention provides a steel plate surface defect detection method and system based on multi-source data fusion, and relates to the technical field of steel production automatic detection.The method comprises the steps that water stain pretreatment is conducted on the surface of a steel plate, the residual humidity is reduced to be below a preset low humidity threshold value, and a dry surface is obtained; based on the dry surface, collecting multi-source data through a 3D laser line scanning camera and a 2D industrial line scanning camera which are synchronously triggered, obtaining line scanning laser point cloud data, a line scanning reflectivity gray level image, a line scanning depth gray level image and an area array reflectivity color image, and establishing a space corresponding relation among the multi-source data; and forming a multi-source data set based on the spatial correspondence among the multi-source data. According to the method, a high-precision and high-robustness steel plate surface defect detection system covering the whole detection process is constructed by eliminating water stain interference, unifying a multi-source data reference, optimizing data quality, accurately identifying defects and realizing automatic feedback and data closed loop.

The invention relates to the technical field of oil stain detection, and discloses an oil-filled equipment oil stain detection method based on fluorescence reflection. The method comprises the following steps: carrying out cleaning pretreatment on a to-be-detected surface; an ultraviolet light source is utilized to excite the oil stain to generate fluorescence; collecting a fluorescence image through an imaging device with a filter; performing noise reduction and edge processing on the image to extract an oil stain area; and finally judging the existence and type of oil stain and estimating the thickness according to image features. According to the invention, the fluorescence characteristic of the oil stain is utilized, no fluorescent agent needs to be added, and pollution-free, high-precision and high-efficiency non-contact detection is realized.

The invention discloses a surface treatment process of a hydraulic rod and a coating monitoring system, relates to the technical field of electroplating, and aims to solve the problems that various complementary sensing technologies cannot be integrated, information such as thickness, uniformity and microstructure cannot be synchronously acquired in a lossless, in-situ and real-time manner, and closed-loop control cannot be formed based on the information in the background technology. According to the scheme, the method comprises the steps that PR electrolytic degreasing is conducted, a workpiece serves as an anode, an oil film is torn through the oxygen evolution effect, an extremely-thin oxidation film possibly existing on the surface of the workpiece is dissolved, base metal is completely activated, and an optimal combination basis is provided for a follow-up coating; and washing with hot water, namely removing residual alkaline degreasing fluid and emulsified oil stains by using hot water with the temperature higher than 60 DEG C in a stirring and spraying manner. According to the method, multi-dimensional information such as the thickness, the uniformity and the microstructure can be synchronously obtained in a lossless, in-situ and real-time mode in the surface treatment process, closed-loop control is formed based on the information, and it is ensured that plating growth is always located on the optimal track.

The invention provides an engineering machinery man-machine binding card punching management system based on fingerprint biological recognition, and belongs to the field of fingerprint recognition, and the method comprises the steps: obtaining a fingerprint image of a to-be-recognized constructor and an initial fingerprint matching degree; dividing the fingerprint image of the construction personnel to be identified into a plurality of areas; obtaining a normal fingerprint area and a suspected stain area according to the shape of each area; according to the number of normal fingerprint areas around each suspected dirty area and the distribution of pixel points in each suspected dirty area, obtaining a dirty area; and completing identification according to the normal fingerprint area, the stain area and the initial fingerprint matching degree of the to-be-identified constructor. The invention aims to solve the problem that the construction personnel cannot identify the fingerprint when performing fingerprint card punching identification on the construction site due to the fact that the fingers of the constructor may be stained with oil stains, soil and the like in the construction process. And the problem that fingerprint card punching comparison is wrong may occur.

The invention discloses a bridge disease detection method based on a diffusion model and a bitter fish optimization algorithm, and relates to the technical field of bridge detection. The method comprises the following steps: fixing a visual angle and a distance at an easy-to-peel or crack position of a bridge, and collecting and aligning visible light and near-infrared images; carrying out multi-scale downsampling on the image, and carrying out wavelet denoising, brightness correction and texture smoothing; inputting the preprocessing result into an improved diffusion model, weighting the edge during forward diffusion, and reversely generating and applying texture and contour smoothing; the multi-source feature channel and the reconstructed image are combined and input into a deep segmentation network, shadow and stain are eliminated by using a local difference function, and global search is performed on a segmentation threshold, a noise coefficient and the like based on a disease detection rate, a false detection rate and the like by using a bitter fish algorithm; training and correcting the high-noise area again according to the optimal parameters; and uniformly marking disease areas. According to the method, the recognition recall rate of tiny spalling and irregular cracks in an extreme environment can be greatly improved, and the intelligent level and the practical effect of bridge disease detection are improved.

This invention belongs to the field of coating technology, specifically relating to a moisture-proof and stain-resistant acrylic resin coating and its preparation process. The moisture-proof and stain-resistant acrylic resin coating comprises 100 parts by weight of a main agent and 20-25 parts by weight of a curing agent. The main agent comprises the following raw materials in weight percentages: dispersant 1.5-3%, butyl acetate 10-15%, xylene 5-10%, filler 10-20%, titanium dioxide 10-20%, carbon black 1-5%, cellulose acetate butyrate 1-2%, anti-settling agent 1-1.5%, leveling agent 0.5-1%, defoamer 0.1-0.5%, with the balance being acrylic resin. The moisture-proof and stain-resistant acrylic resin coating of this invention exhibits excellent comprehensive performance, high filling and sealing properties, strong adhesion to alloys, and good stain resistance, water resistance, and gloss retention.

1. The name of the design product: cleaning brush. 2. The use of the design product: for cleaning stains on the surface of articles. 3. The design features of the design product: in shape. 4. The picture or photo that best shows the design features: perspective view.

The invention discloses a wear-resistant coating and application thereof on a leather surface, and belongs to the technical field of leather finishing. The coating comprises a functionalized polyurethane-acrylate composite emulsion, a photoinitiator, an auxiliary agent and deionized water. Wherein the composite emulsion is prepared from hyperbranched polyester polyol, a dynamic bond chain extender and the like through prepolymerization, fluorine-containing grafting and in-situ sol-gel reaction, a hyperbranched skeleton provides mechanical support, double dynamic bonds endow a self-repairing function, in-situ nano-compounding enhances wear resistance, a diurea hydrogen bond enhances binding force, and a fluorine-containing side chain endows a coating with hydrophobic and stain-resistant performance; and preparing the coating by matching with a gradient curing process. The coating prepared by the invention has high wear resistance, efficient self-repairing property, firm adhesive force, excellent stain resistance and leather adaptation flexibility, and meets the actual requirements of middle and high-end leather finishing.

The invention relates to the technical field of ship outboard video monitoring, in particular to a marine intelligent self-cleaning camera system and a control method thereof. Through cooperation of the rotary telescoping mechanism, the lens self-cleaning module, the control unit and the image detection algorithm module, intelligent storage of the camera and automatic cleaning of the lens can be realized, and the reliability and environment adaptability of the marine outboard camera can be greatly improved; the lens self-cleaning module integrates a cleaning liquid spraying function and a high-pressure water washing function, and intelligently adjusts a cleaning strategy in combination with the stain level recognized by the image detection algorithm module and parameters such as salt mist concentration collected by the environment sensing module, so that precise cleaning in different pollution scenes is realized, the cleaning effect is improved, and cleaning consumables are saved; the image detection algorithm module is based on a deep learning model and an image gray analysis algorithm, and is combined with a reference image regular updating mechanism, so that interference factors such as ambient light change can be effectively eliminated, and the accuracy of stain detection is improved.

The invention relates to the technical field of robots, in particular to a robot operation method and system combined with a scene graph. According to the method, a monitoring camera can be utilized to perform semantic segmentation on a shot image (scene graph) of a target ground to identify a stain area and a stain type, the cleaning complexity is distinguished, and the stain cleaning sequence and the cleaning parameters are determined from low to high based on the complexity, so that low-complexity stains can be processed firstly, and the cleaning efficiency is improved. The method has the advantages that high-complexity stains are processed, the sequence is reasonable, secondary pollution is avoided, different cleaning parameters are determined according to different complexities, one-step operation is avoided, cleaning is more reasonable, in addition, a scene graph acquired by the robot is acquired by monitoring, scanning by the robot is not needed, the efficiency is high, and omission is avoided.

The invention provides a cleaning head path planning method for a glass curtain wall cleaning robot, and belongs to the technical field of glass curtain wall cleaning robots. Curtain wall images are collected through a multispectral visual sensor, and stain distribution is identified and energy consumption is predicted by using a probability graph structured prediction model; cleaning sub-regions are divided according to the stain coordinates, a grid map is established, a double-layer game optimization model with minimization of chassis movement energy consumption as an upper layer target and minimization of cleaning head operation time as a lower layer target is constructed, and two layers of paths are alternately optimized by adopting a Nash equilibrium algorithm until convergence; and through a resource constraint penalty term iteration adjustment path scheme, it is ensured that resource consumption does not exceed carrying capacity, and finally a robot chassis moving path and a cleaning head operation path are output, so that the technical problem that global optimization is difficult due to mutual coupling of the robot chassis moving path and the cleaning head operation path is solved.

The invention discloses a window cleaning robot cleaning liquid supply and recovery control system and method based on intelligent perception, and belongs to the technical field of intelligent cleaning equipment. The problems that in the prior art, the supply and recovery process of cleaning liquid is extensive, self-adaption to the stain degree cannot be achieved, energy consumption is high, and potential safety hazards exist are solved. According to the technical principle, the visual detection module recognizes the grade of stains on the surface of glass, the recovery sensing module monitors the state of waste liquid and feeds back mop state signals through the negative pressure adjusting module, and the central controller adjusts the spraying amount of cleaning liquid according to the grade of the stains, judges the sewage load according to the state of the waste liquid and controls the recovery pump to operate in a continuous, intermittent or closed mode. And adjusting the rotating speed of the fan according to the mop state signal to maintain the optimal adsorption force. Intelligent cooperation of cleaning liquid supply and recovery and negative pressure adjustment is achieved, precise cleaning, energy conservation and consumption reduction are achieved, safety and reliability are improved, and control parameters are continuously optimized through the self-learning function.

The invention discloses a high-robustness multi-scale defect detection method for a metal matrix surface, and relates to the technical field of machine vision and surface defect detection. In order to solve the problems of large scale difference of metal matrix surface defects, strong background noise and easy missing detection of tiny targets in a complex service environment, an EMA-YOLO deep network proposed by the invention is characterized in that an efficient multi-scale attention (EMA) mechanism is introduced into a YOLOv8 backbone network, and the influence of background interferences such as surface water stains and oil stains on defect identification is inhibited through a cross-space learning strategy; a P2 layer-based high-resolution tiny target detection head is constructed, and shallow geometric details are reserved to accurately capture early pitting corrosion and microcracks; a Shape-IoU loss function is introduced, and through shape perception and adaptive weight adjustment, the positioning precision of cracks and irregular spalling defects with extreme length-width ratios is optimized. The EMA-YOLO deep network provided by the invention can effectively improve the accuracy, stability and robustness of multi-scale defect detection under a complex texture background.

The invention provides a cleaning equipment control method, cleaning equipment, a storage medium and a program product, and relates to the technical field of intelligent cleaning equipment.The method comprises the steps that in the process that the cleaning equipment executes a cleaning task, according to a target steam requirement corresponding to an identified cleaning attribute of a to-be-cleaned object, the to-be-cleaned object is cleaned according to the target steam requirement; and steam is sprayed to the to-be-cleaned object to clean the to-be-cleaned object, and the cleaning attributes comprise at least one of the object type and the stain type, so that the cleaning effect of the cleaning equipment and the intelligent level of steam control are improved.

The invention discloses an intelligent cleaning unmanned aerial vehicle for high-rise building curtain wall maintenance and a cleaning method of the intelligent cleaning unmanned aerial vehicle. The cleaning method comprises the steps that data such as wind speed, temperature and humidity are detected in real time through a sensor system, and a flight control unit dynamically adjusts the flight path and attitude according to the information. The image recognition technology is used for recognizing the stain type and distribution of the building curtain wall, generating a cleaning path and adjusting the working mode of the cleaning module. And the spraying and cleaning modes are automatically adjusted according to the types of stains. The intelligent calculation module monitors the cleaning effect in real time, and feedback information is used for adjusting cleaning parameters. Meanwhile, the flight control unit plans a flight path to ensure that obstacles outside the building are avoided; according to the intelligent cleaning unmanned aerial vehicle for high-rise building curtain wall maintenance and the cleaning method thereof, the defects in the prior art are overcome, the intelligent cleaning unmanned aerial vehicle has the advantages of being high in wind resistance, intelligent in cleaning, high in endurance and high in efficiency, and automatic cleaning of the high-rise building curtain wall is achieved.

The invention provides an intelligent photovoltaic glass surface cleaning system and method based on a multi-axis mechanical arm and a magnetic attraction track, and relates to the technical field of photovoltaic power station operation and maintenance. The magnetic attraction track unit, the moving platform unit, the multi-axis mechanical arm, the multifunctional end effector and the sensing and navigation unit are in control connection with the central control unit. The sensing and navigation unit comprises a visual sensor which is mounted at the tail end of the multi-axis mechanical arm or on the mobile platform unit and is used for identifying the boundary, the stain degree and the stain type of the photovoltaic glass; the distance sensor is used for detecting the distance between the tail end of the mechanical arm and the glass surface; and the positioning module is used for determining the accurate position of the mobile platform unit on the magnetic attraction track unit. According to the photovoltaic power station cleaning device, efficient, safe and high-adaptability cleaning capable of covering complex surfaces and reducing water resource dependence can be carried out on the photovoltaic modules, and therefore full-automatic and intelligent photovoltaic power station cleaning operation and maintenance are achieved.

The invention relates to the technical field of coatings, in particular to a solvent-free anti-doodling cover agent as well as a preparation method and application thereof. The solvent-free anti-doodling finishing agent is prepared from the following raw materials in percentage by mass: 80 to 95 weight percent of solvent-free methyl phenyl silicone resin, 1 to 5 weight percent of a curing agent, 3 to 8 weight percent of an adhesion enhancer, 0.5 to 3 weight percent of an anti-doodling auxiliary agent and 0 to 6 weight percent of an optional delustering agent. The core is that the adhesion enhancer is an enhanced silane coupling agent and is prepared by carrying out molecular-level chemical bonding on a titanium compound, the silane coupling agent and a self-made antifouling agent. The finishing agent disclosed by the invention has the advantages of high adhesive force, excellent stain resistance, adjustable glossiness and the like, and is suitable for base material protection of various scenes such as building outer walls, household crystal plating and artistic coatings.

The invention discloses a water quality COD analysis device, and relates to the technical field of COD water quality detectors, the water quality COD analysis device comprises a COD water quality detector body, a calibration mechanism is arranged on the outer side of the COD water quality detector body, a wiping mechanism is arranged on the outer side of the COD water quality detector body, the calibration mechanism can detect a plurality of detection samples after sample water calibration equipment is utilized, and the wiping mechanism is arranged on the outer side of the COD water quality detector body. The wiping mechanism can wipe the surface of a test tube of a detection sample, the calibration mechanism comprises a first stepping motor, the outer surface of the first stepping motor is fixedly connected to the inner wall of the COD water quality detector body, the output end of the first stepping motor is fixedly connected with a turntable, and the outer surface of the turntable is fixedly connected with a plurality of same rectangular frames; the inner wall of each rectangular frame is rotationally connected with a rubber barrel, stains and water stains on the surface of the test tube of the detection sample can be cleaned by utilizing the wiping rings, and the problem that the detection efficiency is reduced due to the fact that the test tube of the sample to be detected needs to be manually wiped before detection is solved.

The invention relates to the technical field of image recognition, in particular to a petrochemical pipeline leakage recognition method based on an unmanned aerial vehicle inspection image, which comprises the following steps: generating a pixel-level surface normal vector field according to an unmanned aerial vehicle inspection image sequence, and calculating an angle variation between adjacent vectors in the pixel-level surface normal vector field, and generating a surface normal vector gradient map in combination with luminosity change information of the multiple frames of images. According to the method, the analysis range is focused in the determined geometric deformation candidate area, the unique gloss and color change characteristics of liquid leakage are captured, and finally, the wet abnormal coordinate set and the geometric deformation area are subjected to space alignment and overlapping judgment, so that the high credibility of an identification result is ensured, and the identification accuracy is improved. False report and missing report caused by interference of environmental factors such as illumination change and surface stains of a single feature source are avoided.

Techniques for using combination stain types for machine learning models for digital pathology are described herein. In an example, a system accesses a first image of a sample comprising an immunohistochemistry (IHC) stain for a biomarker. The system accesses a second image of the sample comprising a hematoxylin and eosin (H&E) stain for nuclei. The system can segment tissue regions in the one or more first images and the second image, partitions the tissue regions in the one or more first images and the second image, and extracts features from the set of tiles using a feature extractor. The system can generate, by a machine-learning model, an output classification indicating a first phenotype based on the features extracted from the set of tiles. The machine-learning model can include one or more classifiers and an aggregation model that provides an aggregated output for the set of tiles.

The invention discloses a simulation driving control method and system for cleaning equipment, and belongs to the technical field of equipment control. The method comprises the steps that sensor arrays are arranged at the water inlet end, the middle bending position and the water outlet end of the cleaning equipment respectively; a three-dimensional detection network is constructed to obtain spatial distribution data of the hollow target equipment to be cleaned in real time and transmit the spatial distribution data to the PLC; the PLC controller generates a stain load three-dimensional simulation map through fusion algorithm processing, calls a neural network model matching feature database to identify main stain types, and then performs linkage execution control; in the cleaning process, the cleanliness degree is judged according to the turbidity and pollutant content detected by a sensor at the water outlet end, and cleaning liquid is controlled to be recycled to a circulating water tank or discharged into a waste liquid tank; intelligent control over the cleaning process is achieved, the cleaning efficiency and cleanliness are improved, and cleaning fluid consumption is reduced.

The invention relates to the technical field of fabric fabrics, in particular to preparation of a stain-resistant and waterproof polyester composite fabric. The invention discloses a stain-resistant waterproof polyester composite fabric and a preparation method thereof, the composite fabric is composed of three layers from outside to inside, the first layer is a polyester filament yarn surface layer subjected to fluorinated graphene and plant source C18 alkylsilane amphiphobic finishing; the second layer is a copolyamide hot melt adhesive net film with a melting point of 105 DEG C; and the third layer is a degradable multifunctional thermoplastic polyurethane elastomer film loaded with silver zeolite antibacterial microcapsules and conductive carbon nanotubes. An amphiphobic finishing liquid is uniformly deposited on the surface of polyester by adopting a supercritical CO2 one-step method, and nanoparticles and fibers are covalently bonded through a chitosan-citric acid cross-linked network, so that the waterproof grade is still greater than or equal to 90 after 30 times of water washing, the oil repellent grade is greater than or equal to 5, and the water contact angle and the oil contact angle are reduced by lt; the temperature is 5.5 DEG C, and the moisture permeability retention rate is gt; the antibacterial rate is 97%, and the antibacterial rate is gt; the compost degradation rate within 180 days is gt; 90%.

The invention discloses a condom cleaning and drying system based on machine vision and a control method, and relates to the technical field of automatic control of condom production and processing equipment. Based on a preprocessed image, color features, texture features and morphological features are extracted through a multi-feature fusion stain recognition algorithm; inputting into a pre-trained stain level judgment model, and analyzing based on a stain coverage area calculation result to obtain a stain level; step 3, the main control module executes a targeted cleaning and drying control strategy according to the judged stain level in combination with the real-time operation parameters collected by the feedback regulation module; the condom image is collected and analyzed in real time through machine vision, the stain level is accurately judged in combination with a multi-feature fusion algorithm, targeted adjustment of a cleaning and drying strategy is achieved, and the condom cleaning cleanliness is effectively improved; and by dynamically optimizing control parameters, excessive cleaning and drying are avoided, and energy consumption is remarkably reduced.

The invention relates to the technical field of photovoltaic power generation, and discloses an automatic device for photovoltaic panel surface cleaning, the automatic device comprises a mobile platform, a mounting rack, a mobile mechanism and a cleaning mechanism, and the mobile mechanism drives the cleaning mechanism to reciprocate along the mounting rack. The cleaning mechanism comprises a cleaning unit, a flushing unit, a water absorption unit and a switching assembly. In the moving process of the cleaning mechanism, the switching assembly drives the cleaning unit and the flushing unit to alternately face the surface of the photovoltaic panel through the first switching part and the second switching part, and multi-step automatic cleaning is achieved. The cleaning agent can effectively decompose and remove stubborn stains, prevent water stain residues and improve the cleaning efficiency and the light transmittance, so that the power generation efficiency of the photovoltaic panel is improved.

The invention discloses a tableware cleaning method, device and equipment and a storage medium. The method comprises the steps that when it is determined that washing is needed, the target stain degree of to-be-cleaned tableware is obtained, the target oil smoke concentration of the environment related to the to-be-cleaned tableware is obtained, and the target stain degree is determined according to the cooking mode of food materials related to the to-be-cleaned tableware; according to the target stain degree and the target oil smoke concentration, recommended washing parameters are determined, the recommended washing parameters comprise recommended washing water temperature and a recommended rotating speed of a spraying arm, the recommended washing water temperature is in direct proportion to the target stain degree, and the recommended rotating speed of the spraying arm is in direct proportion to the target oil smoke concentration; and cleaning the to-be-cleaned tableware according to the recommended washing parameters and the user instruction. The recommended washing parameters determined by the tableware washing method conform to the actual washing scene, and the situation that washing is not in place is avoided, so that the washing effect of tableware is improved.

The invention belongs to the technical field of intelligent cleaning, and discloses an intelligent cleaning system for a passenger cabin. Comprising a stereoscopic vision positioning module used for acquiring a stereoscopic vision image in a passenger cabin; extracting three-dimensional information of the stain area; the image enhancement sub-module based on the generative adversarial network is used for preprocessing the stereoscopic vision image; the laser scanning and positioning module is used for shooting the whole environment of the passenger cabin and constructing a first point cloud map; the data fusion positioning module is used for receiving the three-dimensional information of the blotted area, performing data registration with the first point cloud map and outputting accurate three-dimensional coordinates of the blotted area; and the cleaning execution module is connected with the data fusion positioning module and is used for receiving the accurate three-dimensional coordinates of the dirty area and controlling a cleaning execution mechanism to clean point by point according to the three-dimensional coordinates so as to adapt to a complex environment, and the efficiency and the quality of passenger cabin cleaning are greatly improved.

The invention discloses a multi-cleaning and anti-adsorption cleaning assembly line for the bottom of a vacuum cup and a cleaning method of the multi-cleaning and anti-adsorption cleaning assembly line. In order to solve the technical problem that cleaning fluid cannot permeate into a contact surface due to negative pressure adsorption caused by a closed space formed by flanging micro-opening design in the stacking process of the cup bottoms of the vacuum cups, the device comprises a primary separation station, a stripping and refining station and an intermittent quantitative collection station which are sequentially arranged on a rack; and intelligent separation and anti-adsorption cleaning of the cup bottom are realized. A single cup bottom passes through the preliminary separation station, and the stacked cup bottoms are intercepted; the stripping and refining station is provided with a self-adaptive elastic stripping mechanism; the intermittent quantitative collection station comprises a receiving guide frame and a quantitative tidying structure, single-cup bottom flow control is achieved through channel inlet width limitation, a guide inclined plate in a sliding channel forms a double-positioning placement space, and it is ensured that the two cup bottoms are positioned in a layered mode, and the proper distance is kept. The fluid conveying assembly integrates the functions of movement driving, pre-flushing, surface activation and stain loosening, and pretreatment is conducted in the cup bottom conveying process.

The invention discloses a pathological image virtual dyeing method and system based on a diffusion model, and belongs to the technical field of cross of pathological image processing, deep learning and computer vision. Through an end-to-end process of data preprocessing, model construction, model training and virtual dyeing reasoning, AF to Hamp is realized; performing non-paired virtual dyeing on the E; the method comprises the following steps: acquiring a non-paired AF pathological image and a Hamp through data preprocessing; e, acquiring a pathological image; generating a trunk through single-step diffusion, and constructing an STAIN model through a multi-modal semantic enhancement module, a local significance perception module and a composite loss function; the STAIN model is trained; and inputting a to-be-processed AF pathological image into the trained STAIN model for virtual dyeing reasoning. According to the method, the multi-step iteration bottleneck of a diffusion model is broken through, and single-step rapid reasoning is realized; cell nucleus and gland pathological structures are accurately reserved; it is guaranteed that the dyeing style conforms to Hamp; e, clinical standard; a lightweight adaptation strategy is adopted; background noise interference is suppressed; the method adapts to non-pairwise data scenes, and the practicability and generalization are improved.

The invention discloses a cleaning machine and a cleaning control method thereof.The cleaning machine comprises a water tank, a water outlet valve and at least one cleaning device, the water tank is used for containing objects to be cleaned, the water outlet valve is located above the water tank, and the cleaning device is installed below the water tank in an attached mode; the cleaning control method of the cleaning machine comprises the steps that when it is determined that a to-be-cleaned article is placed in a water tank, the type of the to-be-cleaned article and the stain thickness of the to-be-cleaned article are obtained; when it is determined that the stain thickness is larger than the first preset thickness, the water outlet valve is controlled to be opened, and the cleaning device is controlled to operate according to the type and the stain thickness, so that various pollutants including stubborn pesticide residues, microorganisms and embedded dirt can be efficiently removed; fruit and vegetable epidermis damage, tissue damage or nutritional ingredient loss caused by improper cleaning force is avoided to the maximum extent, and the dual purposes of efficient and deep cleaning and maximum protection of fruit and vegetable form integrity, taste and nutritional value can be achieved.

The embodiment of the application provides a cleaning device and a control method thereof, and relates to the technical field of cleaning devices. The cleaning device comprises a machine body and a floor brush assembly; the floor brush assembly comprises: a mounting seat; a cleaning piece rotatably arranged on the front side of the mounting seat; and a front scraping strip arranged on the front side of the cleaning piece, the front scraping strip being capable of ascending and descending relative to the mounting seat. The front scraping strip comprises a first scraping part extending along the axial direction of the cleaning piece and a second scraping part extending laterally to the cleaning piece, and in a natural state, the bottom of the second scraping part is lower than the bottom of the first scraping part. The front scraping strip is configured to contact the second scraping part to the cleaning piece before the first scraping part contacts the cleaning surface when descending, so as to scrape the water on the side of the cleaning piece to the cleaning piece through the second scraping part when the floor brush assembly turns. Through the specific structure of the front scraping strip, the water stains on the cleaning surface can be scraped to the cleaning piece when the floor brush assembly is pulled backward and turns backward, so that the water stains are prevented from remaining on the cleaning surface, and the cleaning effect and the user experience are improved.