Intelligent control method and system for high-frequency vibration food material purification equipment

Abstract

The application relates to the technical field of device control, and discloses an intelligent control method and system for a high-frequency vibration food material purification device. The method comprises the following steps: optically scanning a food material pollution area to generate a pollution distribution map; quantitatively calculating pollution area parameters to obtain a vibration purification parameter table; driving a vibration element according to the vibration purification parameter table to form a directional cleaning waveform; collecting turbidity data to analyze the detachment rate of pollutants; adjusting vibration and flushing parameters to establish a linkage mechanism; scanning an outlet to evaluate cleanliness, optimizing linkage parameters according to differences, and realizing closed-loop control. Based on real-time state information of food material pollution, the application realizes accurate configuration of vibration parameters, collaborative control of multiple purification technologies, and closed-loop feedback optimization of purification effect, so that the efficiency, effect and energy utilization rate of food material purification are improved.

Description

Technical Field

[0001] The present application relates to the field of equipment control technology, and in particular to an intelligent control method and system for high-frequency vibration food purification equipment. Background Art

[0002] Food purification is an important part of food processing and home cooking. Traditional food purification methods mainly rely on manual hand washing or simple mechanical rinsing, which are often limited in effectiveness in removing pesticide residues, microbial contamination and other harmful substances. With the development of technology, methods such as ultrasonic cleaning, ozone water cleaning and ultraviolet sterilization have been introduced into the field of food purification. Among them, high-frequency vibration technology has gradually become an important means of food purification due to its non-contact and low-damage characteristics. Existing high-frequency vibration purification equipment usually uses fixed frequency and intensity parameters, and the purification time is manually preset, or the purification process is completed through simple timing control. Some advanced equipment has introduced a preset program selection function based on the type of food, which can automatically adjust the vibration parameters for different food ingredients, thereby improving the targeted purification.

[0003] However, existing high-frequency vibration food purification equipment has many shortcomings: First, it lacks the ability to accurately identify the contamination status of food surfaces, making it impossible to differentiate the contamination levels in different areas; second, the vibration parameter settings lack a scientific basis and are mostly empirical, making it difficult to achieve the optimal purification effect; third, the purification process lacks real-time monitoring and feedback adjustment mechanisms, making it impossible to dynamically adjust the working parameters according to the actual purification situation; fourth, a single vibration purification method has limited effect on removing stubborn contamination, and the combined application of multiple purification technologies lacks an effective coordinated control strategy; finally, the equipment is unable to quantitatively evaluate and continuously optimize the purification effect, resulting in energy waste and loss of food quality. These problems have seriously restricted the application effect and promotion value of high-frequency vibration purification technology in the field of food safety. Summary of the Invention

[0004] The present application provides an intelligent control method and system for high-frequency vibration food purification equipment, which is used to achieve precise configuration of vibration parameters, coordinated control of multiple purification technologies, and closed-loop feedback optimization of purification effects based on real-time status information of food contamination, thereby improving the efficiency, effect and energy utilization of food purification.

[0005] In a first aspect, the present application provides an intelligent control method for high-frequency vibration food purification equipment, which includes: scanning the contamination level of the food surface by a scanning device arranged at the entrance of the purification equipment, digitally processing the acquired food surface image, and obtaining a food contamination area distribution map; based on the food contamination area distribution map, quantitatively calculating the area and density of each contaminated area to obtain a vibration purification intensity parameter table; based on the vibration purification intensity parameter table, driving and controlling the vibration element in the purification chamber by a pulse signal generator to form a targeted vibration cleaning waveform; using a water quality turbidity detector installed on the wall of the purification chamber to collect the turbidity value of the water body in real time during the vibration process, performing time series analysis on the continuously collected turbidity data, and obtaining a pollutant detachment rate curve; based on the pollutant detachment rate curve, proportionally adjusting the vibration frequency and water flow flushing intensity to establish a vibration-flushing linkage mechanism; re-scanning the treated food surface by an imaging contrast system at the outlet, comparing and analyzing the acquired image with the food contamination area distribution map, and automatically optimizing the operating parameters of the vibration-flushing linkage mechanism according to the cleanliness difference to form a closed-loop control system for the purification process.

[0006] In a second aspect, the present application provides an intelligent control system for a high-frequency vibration food purification device, the intelligent control system for a high-frequency vibration food purification device comprising:

[0007] A scanning module is used to scan the surface of the food for contamination using a scanning device installed at the entrance of the purification equipment, digitize the acquired food surface image, and obtain a food contamination area distribution map;

[0008] a calculation module, configured to quantitatively calculate the area and density of each contaminated area based on the food contamination area distribution map, and obtain a vibration purification intensity parameter table;

[0009] A control module, configured to drive and control the vibration element in the purification chamber through a pulse signal generator based on the vibration purification intensity parameter table to form a targeted vibration cleaning waveform;

[0010] The acquisition module is used to use the water turbidity detector installed on the wall of the purification chamber to collect the turbidity value of the water in real time during the vibration process, perform time series analysis on the continuously collected turbidity data, and obtain the pollutant separation rate curve;

[0011] An adjustment module is used to proportionally adjust the vibration frequency and water flushing intensity according to the pollutant separation rate curve to establish a vibration-flushing linkage mechanism;

[0012] The scanning module is used to re-scan the surface of the processed food through the imaging contrast system at the outlet, compare and analyze the acquired image with the distribution map of the contaminated area of ​​the food, and automatically optimize the operating parameters of the vibration-flushing linkage mechanism according to the difference in cleanliness to form a closed-loop control system for the purification process.

[0013] In a third aspect, a computer device is provided, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the computer device executes the above-mentioned high-frequency vibration food purification equipment intelligent control method.

[0014] In a fourth aspect, a computer-readable storage medium is provided, wherein instructions are stored in the computer-readable storage medium, which, when executed on a computer, enables the computer to execute the above-mentioned intelligent control method for high-frequency vibration food purification equipment.

[0015] In the technical solution provided by the present application, a scanning device is set at the entrance of the purification equipment to achieve accurate scanning and digital processing of the surface contamination of food materials, generate a distribution map of food contamination areas, and provide an accurate data basis for subsequent targeted purification; by quantitatively calculating the area and density of each contaminated area, a vibration purification intensity parameter table is obtained, and the refined configuration of purification parameters is achieved, avoiding the blindness and experience dependence of traditional equipment parameter settings; based on the vibration purification intensity parameter table, the vibration element in the purification chamber is driven and controlled by a pulse signal generator to form a targeted vibration cleaning waveform, which significantly improves the utilization efficiency of purification energy and reduces unnecessary damage to food materials; the water turbidity detector installed on the wall of the purification chamber is used to monitor the vibration process The turbidity value of the water in the water is collected in real time, and the pollutant detachment rate curve is obtained through time series analysis. A real-time monitoring mechanism for the purification process is established, which solves the technical defect that traditional equipment cannot perceive the purification progress; according to the pollutant detachment rate curve, the vibration frequency and water flushing intensity are proportionally adjusted, and a vibration-flushing linkage mechanism is established, which realizes the synergistic effect of multiple purification technologies and greatly improves the ability to remove stubborn pollution; the surface of the processed food is scanned again by the imaging contrast system at the outlet, and compared with the food contamination area distribution map for analysis, and the operating parameters of the vibration-flushing linkage mechanism are automatically optimized according to the difference in cleanliness, forming a closed-loop control system for the purification process, which solves the technical problem that traditional equipment cannot perform effect evaluation and continuous optimization. In particular, when applying a lightweight convolutional neural network algorithm to process food surface images, the algorithm fully considers the characteristics of complex food surface texture and uneven illumination, extracts the features of the contaminated area through multi-layer convolution and pooling operations, and significantly improves the accuracy of pollution identification; when processing pollutant detachment rate data, the Kalman filter algorithm used effectively suppresses noise interference in water turbidity measurement through a prediction-correction mechanism, enhancing data reliability; in vibration-flushing linkage control, the fuzzy logic decision tree algorithm used converts multidimensional information such as food type, pollution characteristics and purification stage into precise control instructions, realizing intelligent decision-making under complex conditions; in purification effect evaluation, the gray correlation analysis method used adapts to the characteristics of small samples and incomplete information, and accurately quantifies the correlation between purification parameters and cleaning effects. The application of these algorithms and models in specific functional links greatly improves the intelligence level and adaptability of the system, enabling the present invention to automatically adjust the optimal purification strategy for food of different types and different pollution levels, significantly improving purification quality and efficiency and reducing energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 This is a schematic diagram of an embodiment of an intelligent control method for high-frequency vibration food purification equipment in an embodiment of the present application;

[0018] Figure 2 This is a schematic diagram of an embodiment of an intelligent control system for high-frequency vibration food purification equipment in an embodiment of the present application;

[0019] Figure 3 It is a schematic block diagram of the structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The embodiments of the present application provide an intelligent control method and system for high-frequency vibration food purification equipment. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0021] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 In one embodiment of the present application, an intelligent control method for high-frequency vibration food purification equipment includes:

[0022] Step S101: Scanning the surface of food for contamination using a scanning device located at the entrance of the purification equipment, digitizing the acquired surface image of the food, and obtaining a distribution map of contaminated areas of the food;

[0023] Step S102: Quantitatively calculate the area and density of each contaminated area based on the food contamination area distribution map to obtain a vibration purification intensity parameter table;

[0024] Step S103: Based on the vibration purification intensity parameter table, the vibration element in the purification chamber is driven and controlled by a pulse signal generator to form a targeted vibration cleaning waveform;

[0025] Step S104: using a water turbidity detector installed on the wall of the purification chamber to collect the turbidity value of the water in real time during the vibration process, performing time series analysis on the continuously collected turbidity data to obtain a pollutant separation rate curve;

[0026] Step S105: proportionally adjust the vibration frequency and water flushing intensity based on the pollutant separation rate curve to establish a vibration-flushing linkage mechanism;

[0027] Step S106: Scan the surface of the processed food again through the imaging contrast system at the outlet, compare and analyze the acquired image with the distribution map of the contaminated area of ​​the food, and automatically optimize the operating parameters of the vibration-flushing linkage mechanism according to the difference in cleanliness to form a closed-loop control system for the purification process.

[0028] It is understandable that the execution subject of this application can be a high-frequency vibration food purification equipment intelligent control system, or a terminal or a server, which is not limited here. The embodiment of this application is described by taking the server as the execution subject as an example.

[0029] Specifically, a scanning device, comprising a multispectral illumination unit and a high-resolution imaging device, is installed at the entrance of the purification equipment. When food enters the equipment, the multispectral illumination unit illuminates the food surface in all directions, collecting reflection data under different lighting conditions to form a raw light intensity dataset. This dataset is processed using threshold segmentation techniques to isolate suspected contaminated areas where surface brightness values ​​exceed background values. Simultaneously, the high-resolution imaging device captures the color and texture features of the food surface to establish a baseline feature library. By comparing these features with the data from the suspected contaminated areas, the actual contaminated areas are identified, ultimately generating a distribution map of the food contaminated areas. After obtaining the food contaminated area distribution map, the system grids it, dividing the food surface into micro-regions of equal area and constructing a grid coordinate system for the contaminated areas. Based on this, the number of contaminated pixels within each micro-region is counted, and the contamination density value for each region is calculated. These values ​​are normalized and converted into a standardized pollution intensity index on a scale of 0-100. Based on the differences in pollution intensity between adjacent micro-regions, the system merges areas of similar pollution intensity into the same contaminated block and calculates the total area and pollution load value for each block. For different pollution load values, the system queries matching parameters from the preset vibration frequency library and vibration intensity library, combines them to form a vibration parameter combination for each polluted block, and associates the location information of the polluted block with the vibration parameters to generate a vibration purification intensity parameter table.

[0030] According to the vibration purification intensity parameter table, the vibration elements are controlled in different zones. First, the data in the parameter table is spatially mapped to generate a partition control mapping table for the purification chamber vibration elements. Multiple vibration elements are divided into several independent control groups to form vibration area control units. Each control unit is assigned a corresponding vibration frequency and intensity coefficient, which is converted into a sub-region vibration control instruction sequence. These instruction sequences are input into the pulse waveform generation module, converted into a digital pulse sequence, and formed into a vibration element drive signal after power amplification. These signals are transmitted to the corresponding vibration area control unit through a sub-channel transmission system to form a vibration field with independent control of multiple zones. The system also adjusts the phase synchronization of the vibration field to eliminate the interference of vibration waves in adjacent zones, establishes a collaborative vibration wave array, and dynamically adjusts the propagation direction of the vibration waves in each zone according to the changes in the position of the food in the purification chamber to form a targeted vibration cleaning waveform.

[0031] During the purification process, water turbidity detectors mounted on the walls of the purification chamber collect turbidity values ​​in real time. These detectors, distributed at multiple points, sample water turbidity at regular intervals, acquiring raw data points. These data are then digitally filtered to create a smoothed turbidity data sequence. The system then divides this data into multiple consecutive time windows along the time axis and calculates the average turbidity value for each time window, generating a set of time-period turbidity values. By calculating the turbidity difference between adjacent time windows, the turbidity change data for each time period is obtained. This is then divided by the corresponding time window length to calculate the turbidity change rate per unit time, forming the initial release rate data point. The system correlates these data points with the current vibration parameters, constructing a table that correlates turbidity change with vibration parameters. The system then fits the turbidity change rate as a function of purification time to generate a time-varying turbidity model. Combining these data with the volume of the purified water and the surface area of ​​the food, the system then converts the pollutant release rate curve.

[0032] Based on the pollutant removal rate curve, the system dynamically adjusts the vibration-flushing linkage mechanism. First, the curve slope is calculated to identify the inflection point, dividing the purification process into an initial acceleration phase, a stable removal phase, and a slowdown phase. A pollutant removal signature database is then established for each phase. Real-time data points are matched against the signature database to determine the current phase type. Based on this, the frequency adjustment coefficient is extracted and the optimal vibration frequency value is calculated. Simultaneously, the pollutant removal rate trend is considered to determine the timing for initiating water flushing and the baseline intensity parameters. The dynamic adjustment coefficient for water flushing intensity is calculated by comparing the current pollutant removal rate to the historical peak. The vibration frequency and water flow intensity coefficient are combined into parameter pairs to generate a vibration-flushing parameter matching table. A signal triggering relationship is established between the vibration control unit and the water flow control unit, establishing a vibration-flushing linkage mechanism. An imaging contrast system at the outlet rescans the treated food surface to obtain a cleanliness status image. Through illumination correction and geometric transformation, the image is aligned with the initial contamination area distribution map to create a standardized post-processed image. The two images are overlaid pixel-by-pixel to calculate the contaminant removal rate for each area and generate a cleanliness distribution matrix. The system statistically analyzes this matrix, identifying areas of uneven and insufficient cleaning, and then tracks the corresponding vibration and flushing parameters to establish a database linking cleaning results and process parameters. For areas where cleanliness falls below a threshold, the system generates corrections for vibration frequency and water flow intensity, updates the vibration-flushing parameter matching table, and transmits these corrections to the control center via a parameter feedback channel. This adjusts the processing parameters for the next batch of food, forming a closed-loop control system for the purification process.

[0033] For example, when a batch of leafy vegetables enters the purification system, a scanning device collects reflectance spectral data, identifying the distribution of organic contaminants on the surface. The system then divides the surface into 100 micro-regions and calculates the contamination density of region 37 to be 78, corresponding to a vibration frequency of 32kHz and a vibration intensity coefficient of 0.85. During the purification process, data from the turbidity detector corresponding to region 37 showed a rapid increase in turbidity within the first 30 seconds before leveling off. The system, determining that it had entered the stable disengagement phase, adjusted the vibration frequency to 36kHz and simultaneously initiated water flushing at a medium intensity of 65%. After 120 seconds of processing, the exit imaging system showed that region 37 had a cleanliness level of 94%, while the adjacent region 36 had a cleanliness level of only 87%. Based on this information, the system optimized the vibration-flushing parameters for region 36 and increased the water flow intensity in that region to 75% for the next batch, achieving continued improvement in cleaning results.

[0034] In the embodiment of the present application, by setting a scanning device at the entrance of the purification equipment, accurate scanning and digital processing of the surface contamination of food materials are achieved, and a distribution map of food contamination areas is generated, providing an accurate data basis for subsequent targeted purification; by quantitatively calculating the area and density of each contaminated area, a vibration purification intensity parameter table is obtained, and a refined configuration of purification parameters is achieved, avoiding the blindness and experience dependence of traditional equipment parameter settings; based on the vibration purification intensity parameter table, the vibration element in the purification chamber is driven and controlled by a pulse signal generator to form a targeted vibration cleaning waveform, which significantly improves the utilization efficiency of purification energy and reduces unnecessary damage to food materials; a water turbidity detector installed on the wall of the purification chamber is used to detect the water turbidity during the vibration process. The turbidity value of the water body is collected in real time, and the pollutant detachment rate curve is obtained through time series analysis. A real-time monitoring mechanism for the purification process is established, which solves the technical defect that traditional equipment cannot perceive the purification progress; according to the pollutant detachment rate curve, the vibration frequency and water flushing intensity are proportionally adjusted, and a vibration-flushing linkage mechanism is established, which realizes the synergy of multiple purification technologies and greatly improves the ability to remove stubborn pollution; the surface of the processed food is scanned again by the imaging contrast system at the outlet, and compared with the food contamination area distribution map for analysis, and the operating parameters of the vibration-flushing linkage mechanism are automatically optimized according to the difference in cleanliness, forming a closed-loop control system for the purification process, which solves the technical problem that traditional equipment cannot perform effect evaluation and continuous optimization. In particular, when applying a lightweight convolutional neural network algorithm to process food surface images, the algorithm fully considers the characteristics of complex food surface texture and uneven illumination, extracts the features of the contaminated area through multi-layer convolution and pooling operations, and significantly improves the accuracy of pollution identification; when processing pollutant detachment rate data, the Kalman filter algorithm used effectively suppresses noise interference in water turbidity measurement through a prediction-correction mechanism, enhancing data reliability; in vibration-flushing linkage control, the fuzzy logic decision tree algorithm used converts multidimensional information such as food type, pollution characteristics and purification stage into precise control instructions, realizing intelligent decision-making under complex conditions; in purification effect evaluation, the gray correlation analysis method used adapts to the characteristics of small samples and incomplete information, and accurately quantifies the correlation between purification parameters and cleaning effects. The application of these algorithms and models in specific functional links greatly improves the intelligence level and adaptability of the system, enabling the present invention to automatically adjust the optimal purification strategy for food of different types and different pollution levels, significantly improving purification quality and efficiency and reducing energy consumption.

[0035] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0036] (1) Using a multispectral lighting unit to illuminate the surface of food in all directions, collecting surface reflection data of food under different lighting conditions, and forming an original light intensity data set;

[0037] (2) Based on the original light intensity data set, the surface brightness value is thresholded and segmented to filter out the suspected contaminated area data points that are higher than the background value;

[0038] (3) Using a high-resolution imaging device to shoot the food surface from multiple angles, obtain surface color and texture information, and establish a food surface benchmark feature library;

[0039] (4) Compare the data points of the suspected contaminated area with the food surface benchmark feature library, extract the areas with large deviations from the benchmark features, and obtain the candidate point set of the contaminated area;

[0040] (5) Density clustering is performed on the candidate point set of the polluted area, and points whose adjacent distance is less than a preset threshold are classified as the same polluted area, and the boundary coordinates of the polluted area are generated;

[0041] (6) Based on the boundary coordinates of the contaminated area and combined with the color depth value within the contaminated area, a distribution map of the food contaminated area is generated through coordinate mapping.

[0042] Specifically, a multispectral lighting unit illuminates the food surface in all directions. Here, a multispectral lighting unit refers to an illumination device equipped with light sources of different wavelengths, including visible, near-infrared, and ultraviolet. As the food passes through the conveyor belt at the entrance, these light sources of different wavelengths illuminate the food surface in a predetermined sequence. Each wavelength has specific reflective properties for different types of contaminants. A photoelectric sensor array receives the reflected light signals and records the reflective intensity values ​​of the food surface under each spectrum. These values ​​are organized into a three-dimensional data structure based on the coordinates of the food surface, forming a raw light intensity dataset. This dataset contains the reflective intensity values ​​of each microscopic area on the food surface at various wavelengths, providing a multi-dimensional information foundation for subsequent contamination identification. The raw light intensity dataset is then subjected to threshold segmentation, a basic technique for segmenting an image into foreground and background. First, the average reflective intensity value of the uncontaminated area of ​​the food surface is calculated as the background value. A difference threshold is then set based on the spectral characteristics of different contaminant types. Each point in the raw light intensity dataset is compared with the background value. If the reflective intensity deviation at a specific wavelength exceeds a preset threshold, the point is marked as a suspected contaminant. The preset threshold is a discriminant value derived from extensive experimental data. For example, for organic residues, the reflectance deviation threshold in the near-infrared band is set to ±15% of the background value; for pesticide residues, the reflectance deviation threshold in the ultraviolet band is set to ±20% of the background value. This step outputs a set of data points in the suspected contaminated area, including the coordinates of each suspected contamination point and the corresponding reflectance intensity deviation value.

[0043] A high-resolution imaging device captures food surfaces from multiple angles. A high-resolution imaging device refers to an industrial camera with a resolution of at least 12 megapixels, equipped with an adjustable mounting mechanism, capable of capturing food surface images from different perspectives. This device captures food surfaces from at least three different angles (typically 0°, 45°, and 90°) to obtain high-precision color images. After color correction, these images are used to extract color information (RGB values) and texture features (such as roughness and glossiness) from the food surface. For each food item, a standard color range and texture feature descriptor for its uncontaminated surface are established and stored in a food surface baseline feature library. This feature library is a structured dataset containing standard appearance feature parameters for different types of food items, serving as a reference for determining contamination. Data points in suspected contaminated areas are compared with the food surface baseline feature library. For each suspected contaminated data point, high-resolution image data is taken from the corresponding location, and the color and texture feature values ​​at that point are extracted and numerically compared with the standard features for that type of food in the baseline feature library. The Euclidean or Mahalanobis distance of the feature values ​​is calculated to quantify the degree of feature deviation. A feature deviation threshold is set. When the feature deviation of a point exceeds the threshold, it is confirmed as a candidate point for the contaminated area. The feature deviation threshold is a judgment standard set according to the type of food. For example, for food with smooth surfaces (such as apples), the color deviation threshold is lower and is set within 15% of the total deviation of the RGB three channels; while for food with irregular surfaces (such as cauliflower), the deviation threshold is higher and is set within 25%. Through this step, the true set of candidate points for the contaminated area is screened out, reducing false positive judgments caused by factors such as lighting changes and surface unevenness.

[0044] Density clustering is performed on the set of candidate points for the contaminated area. Density clustering is a clustering algorithm based on the density distribution of data points, which is suitable for identifying clusters of arbitrary shapes. In this method, an influence radius is first set for each candidate point in the contaminated area. The radius value is set according to the type of food and the expected size of the contaminant, and is usually between 0.5mm and 2mm. The number of neighboring points of each point within its influence radius is calculated to determine the density value of the point. Points with high density values ​​are selected as cluster centers, and through the connection relationship between points, points with adjacent distances less than a preset threshold are classified as the same contaminated area. The preset threshold here refers to the Euclidean distance threshold between two points, which is usually set to 1.5 times the influence radius. Finally, several independent contaminated area groups are obtained, and the set of outer boundary points of each area is calculated to form the boundary coordinates of the contaminated area.

[0045] Based on the boundary coordinates of the contaminated area and combined with the color depth values ​​within the contaminated area, a food contamination area distribution map is generated through coordinate mapping. The food surface is mapped into a two-dimensional plane coordinate system, and a surface grid is established with an appropriate resolution (usually 0.1mm / pixel). For each contaminated area, the area outline is determined according to its boundary coordinates, and the grid points inside the area are filled. Different pollution degree values ​​are assigned according to the color depth value of each point (converted from RGB value) to form a regional coloring map with pollution degree information. The final generated food contamination area distribution map is a two-dimensional image containing dual information of location and intensity, which intuitively shows the spatial distribution and severity of pollutants.

[0046] For example, when a batch of leafy vegetables passes through the purification equipment's inlet, a multispectral illumination unit sequentially illuminates the leafy surface with visible light, 365nm ultraviolet light, and 850nm near-infrared light. Photoelectric sensors record reflectance data at each wavelength. Under UV light, areas with pesticide residues exhibit a distinct fluorescence reaction, with reflectance intensities 30% higher than background. These spots are marked as suspected contamination points. A high-resolution camera captures the leafy surface from three angles to establish a standard green value range and surface texture characteristics for healthy leafy vegetables. Comparing the suspected contaminated spots with the standard features revealed that some areas not only exhibited abnormal reactions under UV light, but also had RGB values ​​that deviated from the standard range for normal leafy vegetables by up to 22%. These spots were identified as candidate contaminated areas. Using a density clustering algorithm, with an influence radius of 1.2mm and a cluster distance threshold of 1.8mm, adjacent candidate contaminated spots were grouped. Ultimately, three independent contaminated areas were identified: located at the leaf edge, near the veins, and in the center of the leaf, with their respective boundary coordinates determined. Based on the degree of RGB deviation within the contaminated area, a pollution distribution map is drawn. Darker areas indicate more severe pollution and require stronger vibration cleaning intensity. This precise pollution distribution information directly guides the configuration of subsequent vibration cleaning intensity parameters, ensuring the targeted and efficient purification process.

[0047] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0048] (1) Gridding the food contamination area distribution map, dividing the food surface into several micro-area units of equal area to form a contamination area grid coordinate system;

[0049] (2) According to the grid coordinate system of the polluted area, the number of polluted pixels in each micro-area unit is counted to obtain the pollution density value of each micro-area, and the pollution density value of each micro-area is normalized to convert the pollution density into a standardized pollution intensity index of 0-100;

[0050] (3) Based on the standardized pollution intensity index, adjacent micro-regions are clustered and grouped, and micro-regions with pollution intensity differences less than the threshold are merged into the same polluted block. The total area of ​​each polluted block is calculated by pixel accumulation, and the pollution load value of each polluted block is generated by combining the standardized pollution intensity index;

[0051] (4) According to the pollution load value, the optimal vibration frequency range is searched from the vibration frequency library, and the matching vibration intensity coefficient is searched from the vibration intensity library;

[0052] (5) Pairing the optimal vibration frequency range with the vibration intensity coefficient to form a vibration parameter combination for each contaminated area;

[0053] (6) The coordinate position information of each polluted block is associated with the corresponding vibration parameter combination to generate a vibration purification intensity parameter table.

[0054] Specifically, gridding is performed to divide the food surface into equal parts according to a preset grid size, creating a regular two-dimensional grid structure. Gridding refers to the process of discretizing a continuous two-dimensional space into a finite number of grid cells. The food surface is divided into square micro-regions with equal side lengths, and the area of ​​each cell is usually 1mm. 2 Up to 4mm 2 The specific size is determined by the type of food and the characteristics of the contaminants. For example, for smooth-surfaced fruits, smaller grid cells can be used; for uneven-surfaced root vegetables, larger grid cells can be used. The grid coordinate system of the contaminated area formed after grid division is a two-dimensional rectangular coordinate system, and each micro-area unit has a unique coordinate identifier.

[0055] Based on the established grid coordinate system of the polluted area, a quantitative analysis of the pollution situation in each micro-area unit is carried out. The specific operation is to superimpose the food pollution area distribution map on the grid coordinate system, count the number of pixels marked as polluted in each micro-area unit, and calculate the original pollution density value. The original pollution density value directly reflects the degree of pollution in the micro-area, but due to the large differences in the surface area and total amount of pollution of different food ingredients, normalization processing is required to make the data comparable. The normalization process uses a linear mapping method to map the original pollution density value to a standard range of 0-100. The calculation process is to first determine the maximum pollution density value and the minimum pollution density value in all micro-areas, and then proportionally map the original pollution density value of each micro-area to obtain a standardized pollution intensity index. This standardization process ensures the comparability of pollution levels between different food ingredients and different batches.

[0056] Based on the standardized pollution intensity index, adjacent micro-regions are clustered and grouped. Clustering aims to merge micro-regions with similar pollution characteristics into larger pollution blocks, reducing computational complexity and facilitating subsequent parameter configuration. The clustering process uses a region growing method, starting with the micro-region with the highest pollution intensity and gradually examining its surrounding adjacent micro-regions. If the difference between the pollution intensity index of an adjacent micro-region and the current region is less than a preset threshold (usually set to 10-15), it is merged into the current pollution block. The preset threshold is selected based on the continuity of the pollutant distribution. A smaller threshold will result in more fragmented pollution blocks, while a larger threshold will form fewer but larger blocks. For each merged pollution block, its total area is calculated (the number of micro-region units multiplied by the area of ​​a single micro-region) and the standardized pollution intensity index of all micro-regions within the block is accumulated to obtain the pollution load value. The pollution load value takes into account both the block area and the degree of pollution.

[0057] According to the pollution load value of the polluted block, the corresponding vibration parameters need to be determined. In this solution, a vibration frequency library and a vibration intensity library are established. These two libraries respectively store the optimal vibration frequency range and vibration intensity coefficient corresponding to different types of pollutants. The vibration frequency library is established based on a large amount of experimental data, and records the vibration frequency ranges in which different pollutants are most easily detached under different adhesion conditions. For example, for oil and grease pollutants, the optimal vibration frequency range is 25-30kHz; for pesticide residues, the optimal vibration frequency range is 32-38kHz; for microbial adhesion, the optimal vibration frequency range is 40-45kHz. Similarly, the vibration intensity library records the vibration intensity coefficients corresponding to different pollution load values. The vibration intensity coefficient is a value between 0-1, which is used to adjust the output power of the vibration element. According to the pollution load value of each polluted block, the optimal vibration frequency range and vibration intensity coefficient are obtained from these two parameter libraries by table lookup or interpolation calculation.

[0058] The optimal vibration frequency range obtained from the query is combined and paired with the vibration intensity coefficient to form a vibration parameter combination for each contaminated block. The vibration parameter combination includes multiple parameters such as the upper limit of the vibration frequency, the lower limit of the vibration frequency, the vibration intensity coefficient, the vibration duration, etc. These parameters together determine the vibration cleaning effect for a specific contaminated block. The parameter matching process takes into account the mutual influence between different parameters. For example, when the frequency is higher, a lower intensity is usually required to avoid damage to the food. Finally, the coordinate position information of each contaminated block (including the coordinates of the block center point and the boundary coordinates) is associated with the corresponding vibration parameter combination to generate a vibration purification intensity parameter table. The parameter table is a structured data set containing multiple data items, each of which corresponds to a contaminated block, recording the block location, area, pollution load and the corresponding vibration parameter combination.

[0059] For example, when an apple passes through the entrance of the purification equipment, the contamination area distribution map on its surface is obtained through optical scanning. The apple surface is divided into a 10×10 grid, with a total of 100 micro-area units, and each unit area is 2mm 2 . Statistics show that 78 pixels in the micro-area unit at coordinates (3,4) are marked as polluted, while the maximum pollution density in the entire grid is 120 pixels and the minimum is 0 pixels. Through normalization, the standardized pollution intensity index of the micro-area is calculated as (78-0) / (120-0)×100=65. Then, the adjacent micro-areas are clustered, and it is found that the pollution intensity indices of the four micro-areas at coordinates (3,4), (3,5), (4,4) and (4,5) are 65, 62, 59 and 63 respectively. The maximum difference between them is 6, which is less than the preset clustering threshold of 12. Therefore, these four micro-areas are merged into one polluted block. The total area of ​​the block is 4×2=8mm 2 The average pollution intensity index is (65+62+59+63) / 4=62.25, from which the pollution load value is calculated to be 8×

[0060] 62.25 = 498. A query of the vibration parameter database reveals that the optimal vibration frequency range for this contamination load value is 33-37 kHz, with a vibration intensity coefficient of 0.75. The coordinates of the block's center point (3.5, 4.5) are associated with the vibration parameter combination and recorded in the vibration purification intensity parameter table. This parameter table ultimately guides the vibration element in applying precisely controlled vibrations to different areas of the apple's surface, achieving efficient contaminant removal while minimizing damage to the food itself.

[0061] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0062] (1) spatially mapping the vibration parameters of each contaminated block in the vibration purification intensity parameter table to generate a partition control mapping table for the vibration elements in the purification chamber. Based on the partition control mapping table, the multiple vibration elements in the purification chamber are divided into several independent control groups to form vibration area control units;

[0063] (2) assigning corresponding vibration frequency values ​​and vibration intensity coefficients to the vibration region control units to generate a region-specific vibration control instruction sequence;

[0064] (3) Inputting the regional vibration control instruction sequence into the pulse waveform generation module and converting it into a digital pulse sequence with voltage-time relationship;

[0065] (4) performing power amplification processing on the digital pulse sequence, adjusting the voltage amplitude and current intensity of the output signal, and generating a vibration element driving signal;

[0066] (5) transmitting the vibration element driving signal to the corresponding vibration area control unit through a channel transmission system to form a vibration field with multiple independent areas under control, performing phase synchronization adjustment on the vibration field with multiple independent areas under control, eliminating the interference of vibration waves in adjacent areas, and establishing a vibration wave array that works in a coordinated manner;

[0067] (6) Based on the collaborative vibration wave array, the propagation direction of the vibration waves in each area is dynamically adjusted according to the position changes of the food in the purification chamber to form a targeted vibration cleaning waveform.

[0068] Specifically, the vibration parameters of each contaminated area in the vibration purification intensity parameter table are spatially mapped. This process converts the contaminated area information on a two-dimensional plane into control information for the vibration elements in three-dimensional space. Spatial mapping utilizes a coordinate transformation algorithm to map the location coordinates of the contaminated area on the food surface to the physical spatial coordinates within the purification chamber. Multiple vibration elements are pre-installed within the purification chamber, each with a unique spatial coordinate identifier. By calculating the spatial distance between the center point of the contaminated area and each vibration element, the vibration elements that affect each contaminated area are determined, generating a zone control mapping table for the vibration elements within the purification chamber. The zone control mapping table is a data matrix that records the contaminated area information controlled by each vibration element, as well as the spatial relationships between the elements. Based on the zone control mapping table, the multiple vibration elements within the purification chamber are divided into several independent control groups. Each control group is responsible for cleaning a specific contaminated area, forming a vibration zone control unit. A vibration zone control unit is a collection of physically adjacent vibration elements that logically work together to achieve a specific contaminated area. The division of control units follows the principle of nearest influence, prioritizing the vibration elements closest to the contaminated area to form a control unit. For each vibration zone control unit, the vibration frequency range and vibration intensity coefficient for the corresponding contaminated zone are extracted from the vibration purification intensity parameter table to determine the actual parameter values ​​to be executed. The vibration frequency value is typically the median of the vibration frequency range, while the vibration intensity coefficient is directly based on the value in the parameter table. These parameter values ​​are organized in a time series to form an instruction sequence. Each instruction contains information such as the start time, end time, frequency value, and intensity coefficient, forming a regional vibration control instruction sequence.

[0069] The regional vibration control instruction sequence needs to be converted into a specific electronic signal to drive the vibration element. The instruction sequence is input into the pulse waveform generation module, which is a digital signal processor that can generate an electronic signal with a specific waveform based on the input parameters. The conversion process first converts the frequency value into a period value, calculates the number of sampling points within each period, and then calculates the amplitude of each sampling point based on the specified waveform type (usually a sine wave). Finally, a series of data points representing the voltage change over time is generated, namely a digital pulse sequence. The digital pulse sequence is a low-voltage signal that requires power amplification to drive the vibration element.

[0070] The digital pulse sequence is power amplified and the voltage amplitude and current intensity of the output signal are adjusted so that it can drive the vibration element to produce mechanical vibrations of sufficient intensity. The power amplification process includes two links: voltage amplification and current gain. Voltage amplification increases the low-level control signal to the operating voltage range required by the vibration element (usually 30-150V), and current gain ensures that sufficient drive current is provided (usually 0.5-2A). During the amplification process, the gain level is dynamically adjusted according to the vibration intensity coefficient to output drive energy that matches the instruction requirements. The amplified signal is the vibration element drive signal, which is a high-power electronic signal that can directly drive piezoelectric ceramics or other types of vibration elements to work.

[0071] The vibration element drive signal is transmitted to the corresponding vibration zone control unit via a channelized transmission system. The channelized transmission system is a multiplexed signal transmission network that ensures that different drive signals are accurately sent to the target vibration element, avoiding signal aliasing and interference. Each vibration zone control unit receives a dedicated drive signal and independently controls the vibration state of its respective area, forming a multi-zone independently controlled vibration field. A multi-zone independently controlled vibration field refers to a state in which each area within the purification chamber can vibrate at different frequencies, intensities, and phases. Because the vibration zones may overlap or be close to each other in space, interference will occur between adjacent vibration waves, affecting the purification effect.

[0072] To eliminate interference between vibration waves in adjacent regions, phase synchronization of the multi-region vibration field is required. Phase synchronization calculates the spatial relationship and frequency differences between the vibration regions and assigns a specific phase offset to each vibration element. This allows the vibration waves in adjacent regions to synergistically enhance each other rather than cancel each other out. This adjustment creates a coordinated vibration array, an ordered vibration field structure formed by precisely controlling the phase relationships of multiple vibration sources. This allows for focused or uniform distribution of vibration energy in a specific area.

[0073] Based on the collaborative vibration wave array, the food will constantly move and rotate during the purification process, and the propagation direction of the vibration waves in each area needs to be dynamically adjusted. The monitoring of the position changes of the food is achieved through the photoelectric sensor array installed in the purification chamber. The sensor captures the real-time position and posture information of the food, and calculates the new position relationship of the contaminated block on the surface of the food relative to the vibration element. According to the new position relationship, the optimal propagation direction and phase configuration of the vibration wave are recalculated, and the timing and phase parameters of the driving signal are adjusted to ensure that the vibration energy always acts accurately on the target contaminated area, forming a targeted vibration cleaning waveform. A targeted vibration cleaning waveform refers to a vibration waveform that can be adaptively adjusted according to the pollution distribution characteristics and position changes of the food, and has the characteristics of directionality, focus and time-varying.

[0074] For example, when a batch of carrots passes through a high-frequency vibration purification system, preliminary scanning identifies three major contaminated areas on the carrot surface: the top, middle, and root. A corresponding vibration purification intensity parameter table is generated. Spatial mapping determines the correspondence between the 12 vibration elements within the purification chamber and these three contaminated areas. Based on their spatial locations, vibration elements 1-4 are assigned to control group A, responsible for the top area; vibration elements 5-8 are assigned to control group B, responsible for the middle area; and vibration elements 9-12 are assigned to control group C, responsible for the root area. Control group A is assigned a vibration frequency of 35kHz and an intensity coefficient of 0.8; control group B is assigned a vibration frequency of 28kHz and an intensity coefficient of 0.7; and control group C is assigned a vibration frequency of 42kHz and an intensity coefficient of 0.9. Three different control command sequences are generated. These command sequences are converted into digital pulse signals by a waveform generator, amplified, and then transmitted to the vibration elements in each of the three control groups. Because Groups B and C are spatially close, their vibration waves pose a risk of interference. Therefore, a 45-degree phase shift is applied to Group C's vibration signal to eliminate harmful interference. As the carrots slowly rotate during the purification process, the photoelectric sensor detects that the contaminated root area has shifted away from the vibrating elements in Group C. The control system quickly reallocates the vibrating element combination, shifting element #8 from Group B to Group C and adjusting its vibration frequency and phase to ensure that vibration energy continuously acts on the contaminated root area, achieving comprehensive and efficient cleaning.

[0075] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0076] (1) The water in the purification chamber is sampled at fixed time intervals by using multi-point distributed water turbidity detectors to collect the original data points of water turbidity during the purification process. The original data points of water turbidity are digitally filtered to remove random fluctuations and outlier interference, forming a smoothed turbidity data sequence;

[0077] (2) Divide the smoothed turbidity data sequence into multiple continuous time windows according to the time axis, calculate the average turbidity value in each time window, and obtain the time period turbidity value set;

[0078] (3) Based on the set of turbidity values ​​in each time period, the turbidity difference between adjacent time windows is calculated to obtain the turbidity change data for each time period;

[0079] (4) Dividing the turbidity change data by the corresponding time window length, calculating the turbidity change rate per unit time, and forming the initial separation rate data point;

[0080] (5) Associating the initial detachment rate data points with the current vibration parameters and establishing a corresponding relationship table between turbidity changes and vibration parameters;

[0081] (6) According to the data distribution characteristics in the corresponding relationship table, the functional relationship between the turbidity change rate and the purification time is fitted to generate a turbidity time-varying model. Based on the turbidity time-varying model, combined with the parameters of the purified water volume and the surface area of ​​the food, the pollutant removal rate curve of the pollutant removal mass per unit area changing with time is obtained.

[0082] Specifically, multiple turbidity sensors are installed on the walls of the purification chamber. These are photoelectric sensors that measure the concentration of suspended particulate matter in water. They typically use the scattered light principle, detecting the intensity of incident light scattered by the water to determine turbidity. These sensors are evenly distributed in a circular pattern within the purification chamber, ensuring comprehensive monitoring of the water's condition. After the purification process is initiated, the sensors continuously sample the water within the chamber at fixed intervals (typically 0.1-1 seconds), recording a time series of turbidity values ​​to form a set of raw turbidity data points. Because the actual measurement process is inevitably affected by random factors such as water flow disturbances and air bubble interference, the raw turbidity data often contains noise and outliers, necessitating digital filtering. This digital filtering combines median filtering and moving average filtering. First, a median filter is used to address outliers, replacing the original value with the median of the five points before and after each data point to effectively remove outlier interference. A five-point moving average filter is then applied, calculating the weighted average of the two data points before and after each moment to smooth out random fluctuations. The smoothed turbidity data series obtained after such processing can more accurately reflect the actual change trend of water turbidity.

[0083] The smoothed turbidity data series is divided into multiple consecutive time windows along the time axis. A time window is a fixed-length period, typically set to 5-10 seconds, which can be adjusted based on the food type and the expected rate of contaminant release. The time windows are divided using a sliding window approach, with adjacent windows overlapping by 50%. This overlapping design allows for more detailed capture of turbidity trends. The arithmetic mean of the turbidity data within each time window is calculated to obtain a representative turbidity value for that period. The turbidity values ​​for all time periods form a time-period turbidity set. Compared to the original data series, this time-period turbidity set further reduces the data volume while preserving key characteristics of variation. Based on this time-period turbidity set, the turbidity difference between adjacent time windows is calculated. Specifically, the turbidity delta is calculated by subtracting the average turbidity value of the previous time window from the average turbidity value of the current time window. This difference calculation is repeated for all adjacent time windows, forming a turbidity change data series. The turbidity change data directly reflects the release of contaminants into the water per unit time. Positive values ​​indicate an increase in turbidity (continuous release of contaminants), while negative values ​​indicate a decrease in turbidity (contaminant sedimentation or filtration).

[0084] To obtain a more meaningful desorption rate, the turbidity change data is divided by the corresponding time window length. This calculation converts the turbidity change into a turbidity rate per unit time, measured in NTU / second (turbidity units / second). These rate data form a sequence of initial desorption rate data points, which directly reflect the speed at which contaminants are desorbed from the food surface into the water at different times.

[0085] Correlating the initial detachment rate data point with the current vibration parameters is crucial for understanding vibration effectiveness. Vibration parameters include the frequency, intensity coefficient, and phase configuration of the vibration element at the current moment. By matching timestamps, each initial detachment rate data point is associated with the vibration parameters at that moment, creating a table that correlates turbidity changes with vibration parameters. This table is a multidimensional data structure encompassing information across multiple dimensions, including time, detachment rate, vibration frequency, and vibration intensity, providing the data foundation for subsequent analysis of the relationship between vibration parameters and purification effectiveness.

[0086] Based on the data distribution characteristics in the corresponding relationship table, a functional relationship between the turbidity change rate and purification time is established through mathematical model fitting technology. The fitting process uses polynomial regression or exponential decay model, and the appropriate model function is selected according to the actual data distribution characteristics. Taking the exponential decay model as an example, the relationship between the turbidity change rate and time can be expressed as:

[0087] R T (t) = C0·e -λt +K

[0088] Among them, R T(t) represents the rate of change of turbidity at time t, C0 is the initial rate of change of turbidity, λ is the attenuation coefficient, which is related to the properties of the pollutant and the vibration parameters, and K is the residual rate constant. The model parameters are determined by the least squares method to minimize the sum of squared errors between the fitted curve and the actual data points, thus obtaining a time-varying turbidity model.

[0089] The turbidity time-varying model is a mathematical expression that describes the relationship between turbidity changes and time. However, to obtain the true pollutant separation rate curve, it is necessary to combine the purified water volume and food surface area parameters for conversion. The conversion formula is:

[0090]

[0091] Among them, R C (t) is the mass rate of pollutant removal per unit area (mg / cm 2 ·s), R T (t) is the turbidity change rate (NTU / s), V w is the volume of water in the purification chamber (L), α is the turbidity-mass conversion coefficient (mg / L·NTU), A f is the surface area of ​​the food (cm 2 The turbidity-to-mass conversion factor, α, is a parameter related to the pollutant type and is determined through pre-calibration experiments. For example, for common sediment pollutants, α is approximately 0.8-1.2 mg / L·NTU. This conversion ultimately yields a curve showing the change in pollutant mass per unit area over time, known as the pollutant detachment rate curve.

[0092] For example, when a batch of potatoes was subjected to high-frequency vibration purification, eight turbidity detectors installed around the purification chamber collected data every 0.5 seconds. Within 30 seconds of purification, the raw turbidity data showed a rapid rise from an initial 2 NTU to 15 NTU, but the data contained significant fluctuations and several significant outliers. After digital filtering, the smoothed turbidity curve exhibited a clear rise-plateau-slow decline trend. The data was divided into 5-second time windows, and the average turbidity values ​​for 12 time periods were calculated: 2.1, 6.3, 10.8, 13.5, 14.7, 15.0, 14.9, 14.6, 13.9, 13.2, 12.5, and 11.8 NTU, respectively. Calculating the turbidity differences between adjacent time periods yielded 11 turbidity changes: 4.2, 4.5, 2.7, 1.2, 0.3, -0.1, -0.3, -0.7, -0.7, -0.7, and -0.7 NTU. Dividing by the time window length of 5 seconds, the turbidity change rate is obtained: 0.84, 0.90, 0.54, 0.24, 0.06, -0.02, -0.06, -0.14, -0.14, -0.14, -0.14 NTU / s. These data points are associated with the vibration parameters at the corresponding moments (such as frequency 32kHz, intensity coefficient 0.75), and a corresponding relationship table is established. Through fitting analysis, it is determined that the relationship between the turbidity change rate and time conforms to the exponential decay model, and C0 = 1.2, λ = 0.095, K = -0.15 is calculated. Combined with the water volume of the purification chamber 30L, the surface area of ​​the potato is about 1200cm 2 The turbidity-mass conversion factor is 1.0 mg / L·NTU, and the pollutant removal rate curve is calculated. The curve shows that at the beginning of the purification, about 0.025 mg of pollutants are removed per square centimeter of potato surface per second, and after 30 seconds, the rate drops to 0.005 mg / cm 2 ·s, and basically stabilized at 0.001mg / cm after 60 seconds 2 s or less, indicating that most pollutants have been separated in the first 60 seconds.

[0093] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0094] (1) Calculate the slope of the pollutant separation rate curve, determine the inflection point of the curve, and divide the purification process into the initial acceleration stage, the stable separation stage, and the slowdown tail stage;

[0095] (2) Establish a pollutant separation feature library for each stage based on the characteristics of the initial acceleration stage, stable separation stage, and slowdown tail stage;

[0096] (3) Matching the real-time data points of the pollutant detachment rate curve with the pollutant detachment feature library to determine the stage type of the current purification process. Based on the stage type, the corresponding frequency adjustment coefficient is extracted from the vibration frequency optimization rule set to calculate the current optimal vibration frequency value;

[0097] (4) According to the optimal vibration frequency value and the changing trend of the pollutant separation rate, determine the starting time and basic intensity parameters of water flushing;

[0098] (5) Multiplying the basic intensity parameter by the ratio of the current pollutant detachment rate to the historical peak value, calculating the real-time water flow flushing intensity dynamic adjustment coefficient, combining the optimal vibration frequency value and the water flow flushing intensity dynamic adjustment coefficient into a parameter pair, and generating a vibration-flushing parameter matching table;

[0099] (6) Based on the vibration-flushing parameter matching table, a signal triggering relationship between the vibration control unit and the water flow control unit is established to form a vibration-flushing linkage mechanism.

[0100] Specifically, the slope of the pollutant detachment rate curve is calculated, and the first-order derivative of the curve at each time point, that is, the rate of change of the detachment rate, is calculated by the numerical differentiation method. The slope is calculated using the central difference method. For time point t, the slope value is equal to (RC(t+Δt)-RC(t-Δt)) / (2×Δt), where RC represents the pollutant detachment rate and Δt is the sampling time interval. By analyzing the changing trend of the slope value, the important inflection points in the curve are determined. The inflection point refers to the position where the slope of the curve changes significantly, and is usually identified by the zero point or local extreme value of the second-order derivative. During the purification process, the pollutant detachment rate curve usually shows a trend of first rising and then falling, with two typical inflection points: the first inflection point corresponds to the turning point where the rate rises to the maximum value, and the second inflection point corresponds to the turning point where the rate changes from a rapid decline to a slow decline. Based on these two inflection points, the entire purification process is divided into three consecutive stages: the initial acceleration stage, the stable detachment stage, and the slowdown tail stage. The initial acceleration phase, from the start of purification to the first inflection point, shows a rapid increase in the pollutant detachment rate, indicating that vibration energy is effectively loosening and separating surface pollutants. The stable detachment phase, from the first inflection point to the second, shows a high detachment rate and then begins to decline, indicating that a large amount of loosened pollutants are continuing to detach. The tail-end deceleration phase, from the second inflection point to the end of purification, shows a slow decline and stabilization in the detachment rate, indicating that residual pollutants are gradually detaching.

[0101] Based on the different characteristics of these three phases, a pollutant detachment signature library was established for each phase. This signature library is a data set that records typical detachment characteristic parameters for different food ingredients and different pollution types during each phase, including information such as the phase duration range, detachment rate range, and rate variation pattern. This signature library, constructed through statistical analysis of extensive experimental data, provides a reference benchmark for purification processes under different conditions. For example, for pesticide residues on leafy vegetables, the initial acceleration phase typically lasts 5-15 seconds, with the detachment rate increasing exponentially; the stable detachment phase lasts 20-40 seconds, with the detachment rate initially peaking before gradually decreasing; and the final deceleration phase lasts 30-60 seconds, with the detachment rate decaying exponentially. During real-time purification control, real-time data points of the pollutant detachment rate curve are matched against the pollutant detachment signature library to determine the current stage of the purification process. This matching method utilizes pattern recognition technology to calculate the similarity between the real-time detachment curve and the typical curves for each phase in the signature library. The type with the highest similarity is selected as the current stage. Based on the determined stage type, the corresponding frequency adjustment coefficient is extracted from the vibration frequency optimization rule set. The vibration frequency optimization rule set is a set of preset rules that specifies vibration frequency adjustment strategies for different purification stages. For example, during the initial acceleration phase, a lower frequency (25-30kHz) is beneficial for loosening contaminants; during the stable disengagement phase, a medium frequency (30-40kHz) is beneficial for continued separation; and during the final phase of deceleration, a higher frequency (40-50kHz) is beneficial for removing residual contaminants. The frequency adjustment coefficient for the current stage is obtained through table lookup or interpolation calculation. This coefficient is multiplied by the baseline vibration frequency to calculate the current optimal vibration frequency value.

[0102] Based on the optimal vibration frequency value and the changing trend of the pollutant detachment rate, the starting timing and basic intensity parameters of water flushing are determined. Water flushing is an important means of assisting vibration purification. It accelerates the removal of loosened pollutants by flushing the surface of food with a directional water flow. The starting timing of water flushing is triggered according to the threshold of the pollutant detachment rate, usually when the detachment rate reaches 50-70% of the peak value. At this time, a large amount of pollutants have been loosened by vibration but have not yet been completely detached. The basic intensity parameters of water flushing refer to the combined values ​​of parameters such as water pressure, flow rate and spray angle set under standard conditions, usually expressed as normalized values ​​between 0-100.

[0103] The basic intensity parameters are adjusted dynamically in real time to meet the purification needs at different stages. The calculation formula for the dynamic adjustment coefficient of real-time water flow flushing intensity is:

[0104]

[0105] Among them, γ wf β is the dynamic adjustment coefficient of water flow intensity, ranging from 0 to 1;base R is the basic adjustment coefficient, which is related to the type of food and usually takes a value of 0.5-0.8; C (t) is the pollutant separation rate at the current moment; R C,max is the maximum detachment rate observed in history; α stage is the stage characteristic coefficient, which is 1.2 in the initial acceleration stage, 1.0 in the stable separation stage, and 0.8 in the slowdown tail stage; is the rate of change of the current detachment rate; T stage is the characteristic time scale of the current stage. By comprehensively considering the ratio of the current detachment rate to the peak value, the changing trend of the detachment rate, and the characteristics of the current stage, precise dynamic regulation of the water flow intensity is achieved.

[0106] The calculated optimal vibration frequency and the dynamic adjustment coefficient for water flow intensity are combined into parameter pairs. Each moment corresponds to a set of parameters, which are arranged chronologically to form a vibration-flushing parameter matching table. This matching table is a two-dimensional data structure with time as the horizontal axis and two parameters as the vertical axis: the vibration frequency and the flushing intensity coefficient. The parameters in the matching table are dynamically updated as the purification process progresses and changes phases, enabling precise control of the purification process.

[0107] Based on the vibration-flushing parameter matching table, a signal trigger relationship is established between the vibration control unit and the water flow control unit, forming a vibration-flushing linkage mechanism. The vibration control unit is responsible for driving the vibration element to operate at a specified frequency, while the water flow control unit is responsible for adjusting the water pump output and nozzle angle to control the intensity of the water flow flushing. The two control units coordinate their work through a central controller, following the timing arrangement of the parameter matching table to achieve the synergistic effect of vibration and flushing. The linkage mechanism includes status monitoring and feedback adjustment functions. When it is detected that the actual separation effect does not meet the expectations, it can automatically adjust the value in the parameter matching table to ensure the purification effect.

[0108] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0109] (1) Scanning the surface of the purified food in all directions through a high-resolution image acquisition device at the outlet to obtain a clean state image of the surface of the purified food;

[0110] (2) performing illumination correction and geometric transformation on the clean state image so that it has the same coordinate system and scale as the food contamination area distribution map, forming a standardized post-processing image;

[0111] (3) Overlaying the standardized post-processed image with the food contamination area distribution map at the pixel level, calculating the pollutant removal ratio of each area, and generating a cleanliness distribution matrix;

[0112] (4) Perform statistical analysis on the cleanliness distribution matrix, calculate the average cleanliness and cleanliness variance of each area, and identify unevenly cleaned areas and insufficiently cleaned areas;

[0113] (5) Based on the location information of the unevenly cleaned areas and the insufficiently cleaned areas, the corresponding vibration parameters and flushing parameters are traced back to establish a database associating the cleaning effect with the process parameters;

[0114] (6) Based on the association database, a parameter optimization strategy is formulated for areas where the cleanliness is below the threshold, and vibration frequency correction values ​​and water flow intensity correction values ​​are generated;

[0115] (7) applying the vibration frequency correction value and the water flow intensity correction value to the control parameters of the vibration-flushing linkage mechanism, and updating the vibration-flushing parameter matching table;

[0116] (8) The updated vibration-washing parameter matching table is transmitted to the control center through the parameter feedback channel to adjust the processing parameters of the next batch of food, forming a closed-loop control system for the purification process.

[0117] Specifically, after the food has completed the vibration-rinsing purification process, a high-resolution image acquisition device located at the exit performs a full-scale scan of the cleaned surface. This high-resolution image acquisition device is an industrial camera array with a resolution of at least 20 megapixels, equipped with a circular uniform light source and a multi-angle adjustable bracket, capable of capturing minute details on the food surface. During the image acquisition process, the food is placed on a rotating platform and rotated at a fixed angular velocity. Simultaneously, multiple cameras capture the food surface from different angles, ensuring that the entire surface area is captured. The resulting cleanliness image is a set of high-definition digital images containing complete information about the food surface, directly reflecting the actual state of the purified food. After obtaining the cleanliness image, it undergoes illumination correction and geometric transformation to align its spatial reference with the food contamination distribution map collected at the entrance. Illumination correction involves using image processing algorithms to eliminate brightness differences caused by varying lighting conditions, primarily employing histogram equalization and white balance adjustment techniques. Geometric transformation involves converting the coordinate system of the cleanliness image to the same standard coordinate system as the contamination distribution map using a coordinate mapping function. Geometric transformation includes four basic operations: translation, rotation, scaling, and perspective transformation. The feature point matching algorithm automatically identifies corresponding feature points in the two sets of images (such as the corners of the food outline, obvious marks on the surface, etc.), calculates the optimal transformation matrix, and then applies the transformation matrix to the entire image to generate a standardized post-processed image that accurately corresponds to the spatial position of the contaminated area distribution map.

[0118] The standardized post-processed image and the food contamination area distribution map are subjected to pixel-level corresponding overlay analysis to calculate the pollutant removal ratio of each area. The overlay analysis first accurately aligns the two images according to the pixel position, and then calculates the color and brightness difference values ​​for each corresponding pixel point. For each pixel point marked as a contaminated area in the contaminated area distribution map, its corresponding pixel point features in the standardized post-processed image are compared. If the difference between the two exceeds the preset threshold, it is determined that the pollutant at that point has been removed; if the difference is less than the threshold, it is determined that the pollutant remains. According to this judgment rule, the ratio of the number of pixels where pollutants have been removed to the total number of contaminated pixels in each predefined area is counted to obtain the pollutant removal ratio of the area. The removal ratio values ​​of all areas constitute the cleanliness distribution matrix. The cleanliness distribution matrix is ​​a two-dimensional array. Each element corresponds to the cleanliness level of a specific area on the surface of the food, and the value range is 0-100%.

[0119] Perform statistical analysis on the cleanliness distribution matrix and calculate various key indicators. First, calculate the global average cleanliness, that is, the arithmetic mean of the cleanliness of all areas, to reflect the overall purification effect; then calculate the cleanliness variance to reflect the purification uniformity of each area; finally, identify insufficiently clean areas based on the preset cleanliness threshold (usually 85%), and identify unevenly clean areas based on the variance threshold (usually 10%). Insufficiently clean areas refer to areas where the cleanliness is lower than the preset threshold, indicating that the purification effect of the area does not meet the requirements; unevenly clean areas refer to areas where the difference in cleanliness from adjacent areas is too large, indicating that there is an imbalance in the purification process. The identification results of these two types of areas are represented by area identifiers and coordinate information, which serve as the key targets for subsequent parameter optimization.

[0120] Based on the location information of the identified unevenly cleaned areas and insufficiently cleaned areas, the vibration parameters and flushing parameters used in the purification process of the area are retrospectively queried. Retrospective query means extracting parameter data such as frequency values ​​and intensity coefficients applied to the area from the vibration-flushing parameter matching table through the regional coordinates. Associate the cleanliness data of the area with the corresponding process parameter data, analyze the influence of different parameter combinations on the purification effect, and establish an association database of cleaning effects and process parameters. The association database is a multidimensional data structure that contains three types of data: regional characteristics (location, pollution type, pollution degree), process parameters (vibration frequency, vibration intensity, flushing start time, flushing intensity) and purification effects (cleanliness, uniformity) and their mutual relationships, providing data support for parameter optimization.

[0121] Based on the data patterns accumulated in the associated database, a parameter optimization strategy is formulated for areas where cleanliness is below the threshold. Parameter optimization uses the gradient descent method to analyze the sensitivity relationship between cleanliness and each parameter and determine the direction and magnitude of parameter adjustment. For areas with insufficient cleanliness, vibration frequency correction values ​​and water flow intensity correction values ​​are calculated based on their characteristics. The vibration frequency correction value is usually adjusted within the range of ±5kHz, and whether it is too high or too low depends on the type of pollutants and the cleanliness gap in the area; the water flow intensity correction value is usually adjusted within the range of ±0.2, mainly based on the regional location and cleaning uniformity. The calculation of the correction value comprehensively considers multiple factors such as regional cleanliness, regional location, and pollution type to ensure the targeted and effective adjustment.

[0122] The calculated vibration frequency and water flow intensity corrections are applied to the control parameters of the vibration-flushing linkage mechanism, updating the vibration-flushing parameter matching table. This update process not only adjusts parameters for identified problem areas but also makes appropriate corrections to parameters in adjacent areas, ensuring a smooth transition across the parameter space and preventing new inhomogeneities. The updated parameter matching table contains optimized parameter combinations for specific ingredients and contamination conditions, providing a more precise control basis for subsequent purification batches. The updated vibration-flushing parameter matching table is transmitted to the control center via a parameter feedback channel, completing the final step in closed-loop control. The parameter feedback channel is a data transmission mechanism that ensures the optimized parameters are promptly and accurately applied to the next batch of ingredients. Upon receiving the updated parameter matching table, the control center selects the appropriate parameter combination based on the characteristics of the incoming ingredients, guiding the operation of the vibration element and water flow system, thus forming a closed-loop control system for the purification process. This closed-loop control system continuously improves purification effectiveness and efficiency through real-time monitoring, performance evaluation, parameter optimization, and feedback adjustments.

[0123] The above describes the intelligent control method of the high-frequency vibration food purification device in the embodiment of the present application. The following describes the intelligent control system of the high-frequency vibration food purification device in the embodiment of the present application. Figure 2 In one embodiment of the present application, an intelligent control system for high-frequency vibration food purification equipment includes:

[0124] A scanning module is used to scan the surface of the food for contamination using a scanning device installed at the entrance of the purification equipment, digitize the acquired food surface image, and obtain a food contamination area distribution map;

[0125] a calculation module, configured to quantitatively calculate the area and density of each contaminated area based on the food contamination area distribution map, and obtain a vibration purification intensity parameter table;

[0126] A control module, configured to drive and control the vibration element in the purification chamber through a pulse signal generator based on the vibration purification intensity parameter table to form a targeted vibration cleaning waveform;

[0127] The acquisition module is used to use the water turbidity detector installed on the wall of the purification chamber to collect the turbidity value of the water in real time during the vibration process, perform time series analysis on the continuously collected turbidity data, and obtain the pollutant separation rate curve;

[0128] An adjustment module is used to proportionally adjust the vibration frequency and water flushing intensity according to the pollutant separation rate curve to establish a vibration-flushing linkage mechanism;

[0129] The scanning module is used to re-scan the surface of the processed food through the imaging contrast system at the outlet, compare and analyze the acquired image with the distribution map of the contaminated area of ​​the food, and automatically optimize the operating parameters of the vibration-flushing linkage mechanism according to the difference in cleanliness to form a closed-loop control system for the purification process.

[0130] Through the coordinated cooperation of the above-mentioned components, by setting up a scanning device at the entrance of the purification equipment, the surface contamination of the food is accurately scanned and digitized, and a distribution map of the food contamination area is generated, providing an accurate data basis for subsequent targeted purification; by quantitatively calculating the area and density of each contaminated area, a vibration purification intensity parameter table is obtained, which realizes the refined configuration of purification parameters and avoids the blindness and experience dependence of traditional equipment parameter settings; based on the vibration purification intensity parameter table, the vibration element in the purification chamber is driven and controlled by a pulse signal generator to form a targeted vibration cleaning waveform, which significantly improves the utilization efficiency of purification energy and reduces unnecessary damage to food; the water turbidity detector installed on the wall of the purification chamber is used to control the vibration During the process, the turbidity value of the water body is collected in real time, and the pollutant detachment rate curve is obtained through time series analysis. A real-time monitoring mechanism for the purification process is established, which solves the technical defect that traditional equipment cannot perceive the purification progress; according to the pollutant detachment rate curve, the vibration frequency and water flushing intensity are proportionally adjusted, and a vibration-flushing linkage mechanism is established, which realizes the synergy of multiple purification technologies and greatly improves the ability to remove stubborn pollution; the surface of the processed food is scanned again by the imaging contrast system at the outlet, and compared with the food contamination area distribution map for analysis, and the operating parameters of the vibration-flushing linkage mechanism are automatically optimized according to the difference in cleanliness, forming a closed-loop control system for the purification process, which solves the technical problem that traditional equipment cannot perform effect evaluation and continuous optimization. In particular, when applying a lightweight convolutional neural network algorithm to process food surface images, the algorithm fully considers the characteristics of complex food surface texture and uneven illumination, extracts the features of the contaminated area through multi-layer convolution and pooling operations, and significantly improves the accuracy of pollution identification; when processing pollutant detachment rate data, the Kalman filter algorithm used effectively suppresses noise interference in water turbidity measurement through a prediction-correction mechanism, enhancing data reliability; in vibration-flushing linkage control, the fuzzy logic decision tree algorithm used converts multidimensional information such as food type, pollution characteristics and purification stage into precise control instructions, realizing intelligent decision-making under complex conditions; in purification effect evaluation, the gray correlation analysis method used adapts to the characteristics of small samples and incomplete information, and accurately quantifies the correlation between purification parameters and cleaning effects. The application of these algorithms and models in specific functional links greatly improves the intelligence level and adaptability of the system, enabling the present invention to automatically adjust the optimal purification strategy for food of different types and different pollution levels, significantly improving purification quality and efficiency and reducing energy consumption.

[0131] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3As shown. The computer device includes a processor, memory, display screen, input device, network interface and database connected via a system bus. The processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above method is implemented.

[0132] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0133] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the above-described method when executed by a processor. It is understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0134] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Among them, any reference to memory, storage, database, or other media provided by the present invention and used in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAM bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM.

[0135] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0136] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc., various media that can store program code.

[0137] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent control method for high-frequency vibration food purification equipment, characterized in that: The intelligent control method of the high-frequency vibration food purification equipment includes: The contamination degree of the food surface is scanned by a scanning device installed at the entrance of the purification equipment, and the obtained food surface image is digitized to obtain a food contamination area distribution map; According to the food contamination area distribution map, the area and density of each contaminated area are quantitatively calculated to obtain a vibration purification intensity parameter table; Based on the vibration purification intensity parameter table, the vibration element in the purification chamber is driven and controlled by a pulse signal generator to form a targeted vibration cleaning waveform; The water turbidity detector installed on the wall of the purification chamber is used to collect the turbidity value of the water in real time during the vibration process. The continuously collected turbidity data is analyzed in time series to obtain the pollutant separation rate curve; According to the pollutant separation rate curve, the vibration frequency and the water flushing intensity are proportionally adjusted to establish a vibration-flushing linkage mechanism; The surface of the processed food is scanned again by the imaging contrast system at the outlet, and the acquired image is compared and analyzed with the distribution map of the contaminated area of ​​the food. The operating parameters of the vibration-flushing linkage mechanism are automatically optimized according to the difference in cleanliness, forming a closed-loop control system for the purification process.

2. The intelligent control method of high-frequency vibration food purification equipment according to claim 1, characterized in that: The contamination degree of the food surface is scanned by a scanning device provided at the entrance of the purification equipment, and the obtained food surface image is digitally processed to obtain a food contamination area distribution map, including: The food surface is illuminated in all directions by a multi-spectral lighting unit, and surface reflection data of the food under different lighting conditions is collected to form an original light intensity data set; Based on the original light intensity data set, threshold segmentation is performed on the surface brightness value to filter out data points of suspected contaminated areas that are higher than the background value; Use high-resolution imaging devices to shoot food surfaces from multiple angles to obtain surface color and texture information and establish a food surface benchmark feature library; Comparing the suspected contaminated area data points with the food surface reference feature library, extracting areas with large deviations from the reference features, and obtaining a set of candidate contaminated area points; Performing density clustering on the candidate point set of the polluted area, classifying points whose adjacent distance is less than a preset threshold into the same polluted area, and generating the boundary coordinates of the polluted area; Based on the boundary coordinates of the contaminated area and combined with the color depth value in the contaminated area, the food contaminated area distribution map is generated through coordinate mapping.

3. The intelligent control method of high-frequency vibration food purification equipment according to claim 1, characterized in that: According to the food contamination area distribution map, the area and density of each contaminated area are quantitatively calculated to obtain a vibration purification intensity parameter table, including: Gridding the food contamination area distribution map, dividing the food surface into a number of micro-area units of equal area to form a contamination area grid coordinate system; According to the grid coordinate system of the polluted area, the number of polluted pixels in each micro-area unit is statistically counted to obtain the pollution density value of each micro-area, and the pollution density value of each micro-area is normalized to convert the pollution density into a standardized pollution intensity index of 0-100; Based on the standardized pollution intensity index, adjacent micro-areas are clustered and grouped, and micro-areas with pollution intensity differences less than a threshold are merged into the same polluted block. The total area of ​​each polluted block is calculated by pixel accumulation, and the pollution load value of each polluted block is generated in combination with the standardized pollution intensity index; According to the pollution load value, querying the matching optimal vibration frequency range from the vibration frequency library and querying the matching vibration intensity coefficient from the vibration intensity library; Pairing the optimal vibration frequency range with the vibration intensity coefficient combination to form a vibration parameter combination for each contaminated block; The coordinate position information of each polluted block is associated with the corresponding vibration parameter combination and mapped to generate the vibration purification intensity parameter table.

4. The intelligent control method of high-frequency vibration food purification equipment according to claim 1, characterized in that: Based on the vibration purification intensity parameter table, the vibration element in the purification chamber is driven and controlled by a pulse signal generator to form a targeted vibration cleaning waveform, including: Performing spatial mapping on the vibration parameters of each contaminated block in the vibration purification intensity parameter table to generate a partition control mapping table for the vibration elements in the purification chamber; dividing the multiple vibration elements in the purification chamber into a number of independent control groups according to the partition control mapping table to form vibration area control units; assigning corresponding vibration frequency values ​​and vibration intensity coefficients to the vibration region control units to generate a region-specific vibration control instruction sequence; Inputting the regional vibration control instruction sequence into a pulse waveform generation module to convert it into a digital pulse sequence with a voltage-time relationship; Performing power amplification processing on the digital pulse sequence, adjusting the voltage amplitude and current intensity of the output signal, and generating a vibration element driving signal; The vibration element drive signal is transmitted to the corresponding vibration area control unit through a channel transmission system to form a multi-area independently controlled vibration field, and the phase of the multi-area independently controlled vibration field is synchronously adjusted to eliminate the interference of vibration waves in adjacent areas and establish a collaborative vibration wave array; Based on the cooperatively working vibration wave array, the propagation direction of the vibration waves in each area is dynamically adjusted according to the position changes of the food in the purification chamber to form the targeted vibration cleaning waveform.

5. The intelligent control method of high-frequency vibration food purification equipment according to claim 1, characterized in that: The method utilizes a water turbidity detector installed on the wall of the purification chamber to collect the turbidity value of the water in real time during the vibration process, performs time series analysis on the continuously collected turbidity data, and obtains a pollutant separation rate curve, including: The water in the purification chamber is sampled at fixed time intervals by using multi-point distributed water turbidity detectors to collect original water turbidity data points during the purification process, and the original water turbidity data points are digitally filtered to remove random fluctuations and outlier interference to form a smoothed turbidity data sequence; Dividing the smoothed turbidity data sequence into a plurality of continuous time windows according to the time axis, calculating the average turbidity value in each time window, and obtaining a time period turbidity value set; Based on the set of turbidity values ​​for each time period, calculating the turbidity difference between adjacent time windows to obtain turbidity change data for each time period; Dividing the turbidity change data by the corresponding time window length, calculating the turbidity change rate per unit time, and forming an initial separation rate data point; Associating and marking the initial detachment rate data point with the current vibration parameter to establish a corresponding relationship table between turbidity change and vibration parameter; According to the data distribution characteristics in the correspondence table, the functional relationship between the turbidity change rate and the purification time is fitted to generate a turbidity time-varying model. Based on the turbidity time-varying model, combined with the purified water volume and food surface area parameters, the pollutant detachment rate curve of the pollutant detachment mass per unit area changing with time is converted.

6. The intelligent control method of high-frequency vibration food purification equipment according to claim 1, characterized in that: The vibration frequency and water flushing intensity are proportionally adjusted according to the pollutant separation rate curve to establish a vibration-flushing linkage mechanism, including: Calculating the slope of the pollutant separation rate curve, determining the inflection point of the curve, and dividing the purification process into an initial acceleration stage, a stable separation stage, and a slowdown tail stage; According to the characteristics of the initial acceleration stage, the stable separation stage and the slowdown tail stage, a pollutant separation characteristic library of each stage is established; Matching the real-time data points of the pollutant detachment rate curve with the pollutant detachment feature library to determine the stage type of the current purification process; based on the stage type, extracting the corresponding frequency adjustment coefficient from the vibration frequency optimization rule set to calculate the current optimal vibration frequency value; According to the optimal vibration frequency value and the changing trend of the pollutant separation rate, the start time and basic intensity parameters of the water flushing are determined; Multiplying the basic intensity parameter by the ratio of the current pollutant detachment rate to the historical peak value to calculate the real-time water flow flushing intensity dynamic adjustment coefficient, combining the optimal vibration frequency value and the water flow flushing intensity dynamic adjustment coefficient into a parameter pair, and generating a vibration-flushing parameter matching table; Based on the vibration-flushing parameter matching table, a signal triggering relationship is established between the vibration control unit and the water flow control unit to form the vibration-flushing linkage mechanism.

7. The intelligent control method of high-frequency vibration food purification equipment according to claim 1, characterized in that: The imaging contrast system at the outlet scans the surface of the processed food again, compares and analyzes the acquired image with the distribution map of the contaminated area of ​​the food, and automatically optimizes the operating parameters of the vibration-flushing linkage mechanism according to the difference in cleanliness, forming a closed-loop control system for the purification process, including: The high-resolution image acquisition device at the outlet performs an all-round scan of the surface of the purified food to obtain an image of the clean state of the surface of the purified food; Performing illumination correction and geometric transformation on the clean state image so that it has the same coordinate system and scale as the food contamination area distribution map, thereby forming a standardized post-processing image; Overlaying the standardized post-processed image with the food contamination area distribution map at the pixel level, calculating the contaminant removal ratio of each area, and generating a cleanliness distribution matrix; Performing statistical analysis on the cleanliness distribution matrix, calculating the average cleanliness and cleanliness variance of each area, and determining unevenly cleaned areas and insufficiently cleaned areas; According to the location information of the unevenly cleaned areas and the insufficiently cleaned areas, the corresponding vibration parameters and flushing parameters are traced back to establish a database correlating the cleaning effects and process parameters; Based on the association database, a parameter optimization strategy is formulated for areas where the cleanliness level is below a threshold, and a vibration frequency correction value and a water flow intensity correction value are generated; Applying the vibration frequency correction value and the water flow intensity correction value to the control parameters of the vibration-flushing linkage mechanism to update the vibration-flushing parameter matching table; The updated vibration-washing parameter matching table is transmitted to the control center through the parameter feedback channel to adjust the processing parameters of the next batch of food, thereby forming a closed-loop control system for the purification process.

8. An intelligent control system for high-frequency vibration food purification equipment, used to implement the intelligent control method for high-frequency vibration food purification equipment according to any one of claims 1 to 7, characterized in that: The intelligent control system of the high-frequency vibration food purification equipment includes: A scanning module is used to scan the surface of the food for contamination using a scanning device installed at the entrance of the purification equipment, digitize the acquired food surface image, and obtain a food contamination area distribution map; a calculation module, configured to quantitatively calculate the area and density of each contaminated area based on the food contamination area distribution map, and obtain a vibration purification intensity parameter table; A control module, configured to drive and control the vibration element in the purification chamber through a pulse signal generator based on the vibration purification intensity parameter table to form a targeted vibration cleaning waveform; The acquisition module is used to use the water turbidity detector installed on the wall of the purification chamber to collect the turbidity value of the water in real time during the vibration process, perform time series analysis on the continuously collected turbidity data, and obtain the pollutant separation rate curve; An adjustment module is used to proportionally adjust the vibration frequency and water flushing intensity according to the pollutant separation rate curve to establish a vibration-flushing linkage mechanism; The scanning module is used to re-scan the surface of the processed food through the imaging contrast system at the outlet, compare and analyze the acquired image with the distribution map of the contaminated area of ​​the food, and automatically optimize the operating parameters of the vibration-flushing linkage mechanism according to the difference in cleanliness to form a closed-loop control system for the purification process.

9. A computer device, characterized in that: It includes a memory and a processor, the memory stores a computer program that can be run on the processor, and is characterized in that when the processor executes the computer program, it implements the intelligent control method of high-frequency vibration food purification equipment according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the processor is enabled to execute the intelligent control method for high-frequency vibration food purification equipment according to any one of claims 1 to 7.

Images