Control method and equipment of raisin cleaning equipment and storage medium

Abstract

The invention relates to the technical field of control scheme design of raisin cleaning equipment, in particular to a control method and equipment of the raisin cleaning equipment and a storage medium. The biological membrane thickness, the bacterial colony density and the dominant strain type of microorganisms on the raisin surface are collected in real time through an optical sensor group, and the detection precision is improved by combining wrinkle depth correction and a near-field spectrum technology; calculating a cleaning demand index based on the data, and dynamically setting ozone concentration, ultrasonic power and mechanical stirring frequency; and monitoring the residual quantity of microorganisms by using an inactivation mechanical equation, and optimizing cleaning parameters through a closed-loop feedback cycle until the bacterial colony density reaches the standard. The method has the advantages that the convolutional neural network realizes accurate strain identification, eddy current field analysis optimizes stirring frequency space distribution, and a partition early warning mechanism automatically strengthens the cleaning intensity of a local pollution area. According to the method, the cleaning efficiency and uniformity are remarkably improved, microorganism inactivation thoroughness and raisin quality protection are both considered, and the method is suitable for an automatic cleaning production line.

Description

Technical Field

[0001] This invention relates to the field of control scheme design technology for raisin cleaning equipment, and specifically to a control method, equipment, and storage medium for raisin cleaning equipment. Background Technology

[0002] Raisins are susceptible to microbial contamination during processing. Traditional cleaning methods rely primarily on physical rinsing or chemical soaking with fixed parameters, making it difficult to dynamically adjust for varying levels of contamination. Existing technologies have the following limitations: First, they cannot detect the biofilm thickness, colony density, and toxicity of dominant microbial species in real time, leading to a mismatch between cleaning intensity and contamination levels, resulting in insufficient or excessive cleaning. Second, cleaning parameters (such as ozone concentration and ultrasonic power) are statically set, failing to respond to the spatial differences in the raisin's surface wrinkles and microbial distribution. Third, the lack of a closed-loop feedback mechanism makes it difficult to ensure that the residual colony density reaches a safe threshold after cleaning. Furthermore, conventional optical detection is easily affected by the curvature and wrinkles of the raisin surface, impacting the accuracy of microbial data. Therefore, a control method based on real-time microbial data and dynamic optimization of multi-parameter collaborative cleaning is urgently needed to resolve the conflict between cleaning efficiency and quality protection.

[0003] Therefore, the existing technology still needs further development. Summary of the Invention

[0004] The purpose of this invention is to overcome the above-mentioned technical deficiencies and provide a control method, equipment, and storage medium for a raisin cleaning device to solve the problems existing in the prior art.

[0005] To achieve the above-mentioned technical objectives, according to a first aspect of the present invention, the present invention provides a control method for a raisin washing device, comprising: S1. Real-time acquisition of biofilm thickness of microbial community on raisin surface using optical sensor array. Colony density Dominant bacterial strains ; S2. Calculate the cleaning demand index Q based on microbial data; S3. Dynamically set the ozone concentration of the cleaning solution based on the cleaning demand index Q. Ultrasonic power and mechanical stirring frequency F; S4. Based on closed-loop feedback of surface residual microorganism data, repeat steps S1-S3 until colony density is reached. Less than or equal to the safety threshold .

[0006] Specifically, the method includes: The cleaning demand index Q is calculated based on microbial data. in: Biofilm thickness coefficient; Colony density adjustment coefficient; : Strain virulence weighting coefficient; Biofilm thickness; Colony density; : Strain type identifier; : Virulence function of the strain.

[0007] Specifically, the method includes calculating the ozone concentration of the cleaning solution using the following formula. Ultrasonic power And the mechanical stirring frequency F: in, This is the ozone concentration proportionality constant. The ultrasonic power proportionality constant, This is the stirring frequency proportionality constant.

[0008] Specifically, in step S1, near-field spectral enhancement technology is used to improve detection accuracy and satisfy the optical resolution equation: in, The smallest distinguishable colony spacing; : Center wavelength of the light source; : Numerical aperture of the objective lens; n: Refractive index of the raisin surface.

[0009] Specifically, the biofilm thickness compensation adopts a fold depth correction model: in, : Corrected biofilm thickness; D: Depth of wrinkles on the raisin surface; R: Average radius of curvature of the raisin.

[0010] Specifically, the dominant bacterial species identification uses a convolutional neural network model, with the loss function being: in, : Actual bacterial species label, which is a one-hot encoded vector; : Predicted bacterial species probability vector; L2 regularization coefficient; Network weight matrix.

[0011] Specifically, the dynamic monitoring of microorganisms during the cleaning process satisfies the dynamic equation of inactivation: Where t: cleaning time; : Microbial inactivation rate constant.

[0012] Specifically, spatial optimization of the mechanical stirring frequency is achieved through eddy current field analysis: in, : Optimized frequency at depth z; H: Depth of cleaning tank; z: Depth of current measurement point.

[0013] According to a second aspect of the present invention, a control device for a raisin washing apparatus is provided, comprising: The acquisition module is used to collect the biofilm thickness of the microbial community on the surface of raisins in real time through an optical sensor array. Colony density Dominant bacterial strains ; The control module is used to calculate the cleaning demand index Q based on microbial data; and to dynamically set the ozone concentration of the cleaning solution according to the cleaning demand index Q. Ultrasonic power and mechanical stirring frequency F; For closed-loop feedback based on surface residual microorganism data, repeat steps S1-S3 until colony density is reached. Less than or equal to the safety threshold .

[0014] According to a third aspect of the present invention, a storage medium is provided, comprising: a memory; and a processor, wherein the memory stores computer-readable instructions, which, when executed by the processor, implement the control method of the raisin washing device described above.

[0015] Beneficial effects: This method achieves precise cleaning control through intelligent response to the state of microorganisms. Its main advantages include: 1. Dynamic parameter optimization: Based on the comprehensive calculation of cleaning demand index based on biofilm thickness, colony density and bacterial toxicity, ozone concentration, ultrasonic power and stirring frequency are adjusted in a coordinated manner to efficiently inactivate microorganisms while avoiding nutrient loss caused by over-cleaning.

[0016] 2. Enhanced multidimensional accuracy: Near-field spectral enhancement technology combined with a wrinkle depth correction model overcomes the interference of surface curvature on optical detection, ensuring the accuracy of microbial thickness and colony density measurements; convolutional neural networks accurately identify dominant bacterial species, enhancing the reliability of toxicity assessment.

[0017] 3. Closed-loop quality control: By monitoring the microbial inactivation status in real time (satisfying the inactivation kinetic equation), feedback is cyclically fed back to the parameter adjustment process until the colony density drops to a safe threshold, ensuring thorough cleaning.

[0018] 4. Spatial Adaptability: Eddy current field analysis optimizes the spatial distribution of mechanical stirring frequency to solve the problem of uneven fluid distribution in the cleaning tank; the zoned concentration early warning mechanism automatically increases the ultrasonic power in local contaminated areas to avoid cross-contamination.

[0019] 5. Efficient resource utilization: The ozone concentration adaptive adjustment model, combined with the natural decay rate, dynamically controls the supply, reducing ineffective losses and lowering the risks of energy consumption and chemical residues. Attached Figure Description

[0020] Figure 1 This is a flowchart illustrating the control method of the raisin cleaning equipment provided in a specific embodiment of the present invention; Figure 2 This is a schematic diagram of the control device of the raisin cleaning equipment provided in a specific embodiment of the present invention. Detailed Implementation

[0021] To enable those skilled in the art to better understand the technical solutions of the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Based on the embodiments in this application, other similar embodiments obtained by those skilled in the art without creative effort should all fall within the scope of protection of this application. Furthermore, directional terms mentioned in the following embodiments, such as "up," "down," "left," and "right," are only for reference to the directions in the accompanying drawings; therefore, the directional terms used are for illustrative purposes and not for limiting the invention.

[0022] The present invention will be further described below with reference to the accompanying drawings and preferred embodiments.

[0023] Please see Figure 1 The present invention provides a control method for a raisin washing device, comprising: S1. Real-time acquisition of biofilm thickness of microbial community on raisin surface using optical sensor array. Colony density Dominant bacterial strains .

[0024] It should be further explained that, regarding step S1, the solution designed in this invention includes: ① Optical sensor configuration: A combination of a near-infrared spectrometer (wavelength range 900-1700nm) and a confocal microscope is used to scan the surface of raisins in real time.

[0025] ② Measurement of biofilm thickness δ: The optical path difference caused by the microbial film was measured by laser interferometry (accuracy ±0.1μm).

[0026] ③ Calculation of colony density ρ: Count the number of colonies in a unit area (1mm²), and perform image binarization (threshold: gray value greater than 200 is judged as a colony).

[0027] ④ Identification of dominant microbial species: Based on colony morphology characteristics (roundness greater than 0.85 is judged as yeast, and less than 0.7 is judged as mold).

[0028] S2. Calculate the cleaning demand index Q based on microbial data.

[0029] It should be further explained that, regarding step S2, the solution designed in this invention includes: Formula for calculating the cleaning demand index Q: in: Biofilm thickness coefficient; Colony density adjustment coefficient; : Strain virulence weighting coefficient; Biofilm thickness; Colony density; : Strain type identifier; : Virulence function of the strain.

[0030] It is understandable that: The optimal value for α is 0.6, because biofilm thickness has the highest weight in influencing cleaning difficulty. Experiments show that for every 1 μm increase in δ, the cleaning time needs to be extended by 15%. β is preferably 0.3 because the colony density is linearly correlated after taking the logarithm, and as ρ increases from 10³ to 10³... 5 Time Q increased by 40%; The optimal value for γ is 0.4, based on the toxicity weights: f(θ) = 1.0 (Escherichia coli), 0.5 (yeast), and 0.8 (Aspergillus), set according to the risk level of foodborne diseases.

[0031] S3. Dynamically set the ozone concentration of the cleaning solution based on the cleaning demand index Q. Ultrasonic power And the mechanical stirring frequency F.

[0032] It should be further noted that the method includes calculating the ozone concentration of the cleaning solution using the following formula. Ultrasonic power And the mechanical stirring frequency F: in, This is the ozone concentration proportionality constant. The ultrasonic power proportionality constant, This is the stirring frequency proportionality constant.

[0033] Furthermore, the present invention has implemented the following dynamic parameter settings: Ozone concentration C: , (The quadratic relationship requires an exponential increase in oxidation efficiency due to high pollution levels.) Ultrasonic power P: , (Linear relationships avoid cavitation effect overload); Stirring frequency F: , (The exponential relationship addresses the nonlinear growth of biofilm adhesion.)

[0034] S4. Based on closed-loop feedback of surface residual microorganism data, repeat steps S1-S3 until colony density is reached. Less than or equal to the safety threshold .

[0035] It is understandable that this invention incorporates a closed-loop feedback mechanism: Safety threshold: (Complies with GB4789.2-2016 food safety standards); Termination condition: 3 consecutive tests .

[0036] Furthermore, in step S1, near-field spectral enhancement technology is used to improve detection accuracy and satisfy the optical resolution equation: in, The smallest distinguishable colony spacing; : Center wavelength of the light source; : Numerical aperture of the objective lens; n: Refractive index of the raisin surface.

[0037] It should be further explained that the specific design scheme of this invention includes: Design a near-field spectral enhancement implementation scheme: Specifically, the following equations are designed: It is understandable that: λ0 is preferably 550nm because it is the center wavelength of visible light, which matches the absorption peak of microbial pigments. The preferred NA is 0.8 because a high numerical aperture objective lens improves the resolution to 0.29 μm; The preferred value for n is 1.33, because of the refractive index of the water film on the surface of raisins.

[0038] Understandably, when It can distinguish the smallest colony spacing (common microorganisms have a diameter greater than 0.5 μm).

[0039] Furthermore, a fold depth correction model is used for biofilm thickness compensation: in, : Corrected biofilm thickness; D: Depth of wrinkles on the raisin surface; R: Average radius of curvature of the raisin.

[0040] It should be further explained that the specific design scheme of this invention includes: Design a wrinkle depth correction model: It is understandable that: D is preferably 50 μm because it is the average wrinkle depth of the raisin surface and the statistical value of its microscopic morphology. R is preferably 8mm, based on the radius of curvature of the raisins, which is the geometric mean of the sample.

[0041] Understandably, a correction factor of 0.2 reduces the measurement error from ±15% to ±3% (experimental verification).

[0042] Furthermore, a convolutional neural network model was used for dominant strain identification, with the loss function being: in, : Actual bacterial species label, which is a one-hot encoded vector; : Predicted bacterial species probability vector; L2 regularization coefficient; Network weight matrix.

[0043] It should be further explained that the specific design scheme of this invention includes: Model training steps: Input data: 1000 colony micrographs (256×256 pixels, labeled with 5 dominant bacterial species); Network structure: 4 convolutional layers (3×3 kernels, stride 1) + 2 fully connected layers; Loss function: (L2 regularization coefficient, to prevent overfitting, improves validation set accuracy by 12%) Optimizer: Adam (learning rate 0.001, batch size = 32); Output: This is the probability vector of the bacterial species (Softmax normalized).

[0044] Furthermore, the dynamic monitoring of microorganisms during the cleaning process satisfies the dynamic equation of inactivation: Where t: cleaning time; : Microbial inactivation rate constant.

[0045] It should be further explained that the specific design scheme of this invention includes: Dynamic equations: It is understandable that: Preferably 0.05 min −1 ⋅ppm −1 The reason is that an index of 0.7 reflects the colony aggregation effect (the inactivation rate constant of a single microorganism is 1.0, and the aggregation state is reduced to 0.7).

[0046] Furthermore, spatial optimization of the mechanical stirring frequency is achieved through eddy current field analysis: in, : Optimized frequency at depth z; H: Depth of cleaning tank; z: Depth of current measurement point.

[0047] It should be further explained that the specific design scheme of this invention includes: vortex field optimization formula: parameter: (Deepness of the cleaning tank), z is the height from the bottom of the tank; Reason: Cosine modulation makes the groove bottom ( The frequency was increased by 10%, which helped overcome particle sedimentation (experiments showed that the sedimentation rate was reduced by 22%).

[0048] Furthermore, the adaptive regulation of ozone concentration satisfies the dynamic equation: in: : Ozone supply gain; Current real-time cleaning demand index; Ozone natural decay rate.

[0049] It should be further explained that the specific design scheme of this invention includes: Dynamic equations: It is understandable that: (Response speed matches cleaning cycle); (Ozone half-life is 70 min, which conforms to first-order kinetics).

[0050] Furthermore, a zoned concentration early warning mechanism is set up. When the following is detected: At that time, the ultrasonic power in the corresponding area will be automatically increased by 20%. in: : Colony density of the i-th partition; Overall average colony density; n: Total number of cleaning tank zones.

[0051] It should be further explained that the specific design scheme of this invention includes: Warning conditions: Action: Increase the ultrasonic power of the corresponding zone by 20% ( The reason is that a ratio greater than 2.0 indicates a risk of local contamination spread (verified by microbial migration experiments).

[0052] Please see Figure 2 The present invention provides another embodiment, which provides a control device for a raisin washing equipment, the control device for the raisin washing equipment comprising: The acquisition module 100 is used to collect the biofilm thickness of the microbial community on the surface of raisins in real time through an optical sensor array. Colony density Dominant bacterial strains .

[0053] Specifically, the acquisition module 100 includes: Laser confocal unit, used to obtain biofilm thickness. ; Multispectral imaging unit for identifying bacterial species. ; Impedance chromatography unit, used to calculate colony density. .

[0054] Furthermore, the present invention further describes the acquisition module 100 as follows: Laser confocal unit: This unit uses laser scanning technology to scan the surface of raisins layer by layer to accurately measure the biofilm thickness δ. It should possess high resolution and rapid data processing capabilities to provide real-time biofilm thickness information.

[0055] Multispectral Imaging Unit: Employing multispectral imaging technology, this unit images the surface of raisins using different wavelengths of light to identify the dominant microbial species (θ). This unit should include multiple filters and a high-sensitivity camera to distinguish the spectral characteristics of different microbial species.

[0056] Impedance chromatography unit: This unit calculates colony density by measuring the impedance changes of the microbial community on the surface of raisins. It should possess high-precision impedance measurement capabilities and be able to quickly convert data into colony density information.

[0057] Control module 200 is used to calculate the cleaning demand index Q based on microbial data; and to dynamically set the ozone concentration of the cleaning solution according to the cleaning demand index Q. Ultrasonic power And the mechanical stirring frequency F; used for closed-loop feedback based on surface residual microbial data, repeating steps S1-S3 until the colony density is reached. Less than or equal to the safety threshold .

[0058] Specifically, the control module 200 is used to perform: Cleaning demand index ; Ozone generator control commands: ; Ultrasonic transducer control commands: ; Stirring motor control commands: ; Specifically, the control module 200 includes a feedback adjustment module for real-time comparison. and And triggers a re-cleaning process.

[0059] In a preferred embodiment, this application also provides a storage medium, the electronic device comprising: The computer device includes a memory and a processor, wherein the memory stores computer-readable instructions that, when executed by the processor, implement the control method of the raisin washing apparatus. The computer device can be broadly categorized as a server, terminal, or any other electronic device with the necessary computing and / or processing capabilities. In one embodiment, the computer device may include a processor, memory, network interface, communication interface, etc., connected via a system bus. The processor of the computer device can be used to provide the necessary computing, processing, and / or control capabilities. The memory of the computer device may include a non-volatile storage medium and internal memory. The non-volatile storage medium may store an operating system, computer programs, etc. The internal memory can provide an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface and communication interface of the computer device can be used to connect and communicate with external devices via a network. When the computer program is executed by the processor, it performs the steps of the method of the present invention.

[0060] This invention can be implemented as a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, causes the steps of the methods of embodiments of the invention to be performed. In one embodiment, the computer program is distributed across multiple network-coupled computer devices or processors, such that the computer program is stored, accessed, and executed in a distributed manner by one or more computer devices or processors. A single method step / operation, or two or more method steps / operations, may be executed by a single computer device or processor or by two or more computer devices or processors. One or more method steps / operations may be executed by one or more computer devices or processors, and one or more other method steps / operations may be executed by one or more other computer devices or processors. One or more computer devices or processors may execute a single method step / operation, or execute two or more method steps / operations.

[0061] Those skilled in the art will understand that the method steps of this invention can be performed by a computer program instructing related hardware, such as a computer device or processor, to perform the steps of this invention when executed. Depending on the context, any references herein to memory, storage, databases, or other media may include non-volatile and / or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid-state drive, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0062] The technical features described above can be combined arbitrarily. Although not all possible combinations of these technical features are described, any combination of these technical features should be considered to be covered by this specification, provided that such combination does not contain contradictions.

[0063] The specific embodiments of the present invention described above do not constitute a limitation on the scope of protection of the present invention. Any other corresponding changes and modifications made in accordance with the technical concept of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A control method for a raisin washing device, characterized in that, Includes the following steps: S1. Real-time acquisition of biofilm thickness of microbial community on raisin surface using optical sensor array. Colony density Dominant bacterial strains ; S2. Calculate the cleaning demand index Q based on microbial data; S3. Dynamically set the ozone concentration of the cleaning solution based on the cleaning demand index Q. Ultrasonic power and mechanical stirring frequency F; S4. Based on closed-loop feedback of surface residual microorganism data, repeat steps S1-S3 until colony density is reached. Less than or equal to the safety threshold .

2. The control method for the raisin washing equipment according to claim 1, characterized in that, The method includes: The cleaning demand index Q is calculated based on microbial data. in: Biofilm thickness coefficient; Colony density adjustment coefficient; : Strain virulence weighting coefficient; Biofilm thickness; Colony density; : Strain type identifier; : Virulence function of bacterial strain.

3. The control method for the raisin washing equipment according to claim 2, characterized in that, The method includes calculating the ozone concentration of the cleaning solution using the following formula. Ultrasonic power And the mechanical stirring frequency F: in, This is the proportionality constant for ozone concentration. The ultrasonic power proportionality constant, This is the stirring frequency proportionality constant.

4. The control method for the raisin washing equipment according to claim 1, characterized in that: In step S1, near-field spectral enhancement technology is used to improve detection accuracy and satisfy the optical resolution equation: in, The smallest distinguishable colony spacing; : Center wavelength of the light source; : Numerical aperture of the objective lens; n: Refractive index of the raisin surface.

5. The control method for the raisin washing equipment according to claim 1, characterized in that: Biofilm thickness compensation uses a fold depth correction model: in, : Corrected biofilm thickness; D: Depth of wrinkles on the raisin surface; R: Average radius of curvature of the raisin.

6. The control method for the raisin washing equipment according to claim 1, characterized in that: Dominant strain identification employs a convolutional neural network model, with the following loss function: in, : Actual bacterial species label, which is a one-hot encoded vector; : Predicted bacterial species probability vector; L2 regularization coefficient; Network weight matrix.

7. The control method for the raisin washing equipment according to claim 1, characterized in that: The dynamic monitoring of microorganisms during the cleaning process satisfies the inactivation kinetic equation: Where t: cleaning time; : Microbial inactivation rate constant.

8. The control method for the raisin washing equipment according to claim 1, characterized in that: Spatial optimization of the mechanical stirring frequency is achieved through eddy current field analysis: in, : Optimized frequency at depth z; H: Depth of cleaning tank; z: Depth of current measurement point.

9. A control device for a raisin washing machine, characterized in that, include: The acquisition module is used to collect the biofilm thickness of the microbial community on the surface of raisins in real time through an optical sensor array. Colony density Dominant bacterial strains ; The control module is used to calculate the cleaning demand index Q based on microbial data; and to dynamically set the ozone concentration of the cleaning solution according to the cleaning demand index Q. Ultrasonic power and mechanical stirring frequency F; For closed-loop feedback based on surface residual microorganism data, repeat steps S1-S3 until colony density is reached. Less than or equal to the safety threshold .

10. A storage medium, characterized in that, include: Memory; The device includes a processor, wherein the memory stores computer-readable instructions that, when executed by the processor, implement the control method of the raisin washing device according to any one of claims 1 to 8.

Images