Method and equipment for optimizing zinc sulfate industrial production system and medium

Abstract

The invention relates to the technical field of computers, in particular to an optimization method and device for a zinc sulfate industrial production system and a medium. According to the method, real-time images are collected through a visual sensor for analysis, modeling does not need to be conducted depending on historical data, the generalization of pipeline blockage detection is improved, grain deposition detection is conducted in a grain segmentation image superposition mode, and the detection accuracy is improved. The calculation amount is small, the calculation speed is high, the grain deposition detection result can be accurately determined, optical flow calculation is carried out when the grain deposition detection result meets the condition, the situation that the calculation pressure is too large due to continuous real-time optical flow calculation is avoided, the first flow velocity detection result is determined through optical flow calculation, and the calculation efficiency is improved. The pipeline blockage detection result can be more directly and accurately determined according to the flow velocity, the reliability of pipeline blockage detection is improved, then the operation parameters of the crystal slurry pump are optimized according to the first flow velocity detection result, and the reliability of system optimization control is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a zinc sulfate industrial production system optimization method, device and medium. BACKGROUND

[0002] Zinc sulfate is an important inorganic chemical product, which is widely used in electroplating, mineral processing, agriculture and other fields. Its industrial production usually adopts multi-effect evaporation crystallization process. Due to the poor flow stability of the crystal slurry, zinc sulfate crystals are easy to deposit and agglomerate in the crystal slurry conveying pipeline, resulting in pipeline blockage and affecting the continuity of production.

[0003] In the prior art, macroscopic parameter sensors such as pressure and flow are usually used for pipeline blockage detection, and the detection results are determined by combining manual inspection or experience model prediction. However, the manual inspection method needs to consume a large amount of human resources, and the detection results are strongly affected by subjectivity. The experience model prediction method needs to construct an experience model based on historical data, which is difficult to generalize to scenes where the composition of raw materials fluctuates and the aging degree of equipment changes, resulting in low reliability of pipeline blockage detection. It is more difficult to optimize the operating parameters of the crystal slurry pump according to the pipeline blockage detection results.

[0004] Therefore, how to improve the reliability of pipeline blockage detection has become a problem to be solved. SUMMARY

[0005] In view of the above technical problems, the technical scheme adopted by the present application is a zinc sulfate industrial production system optimization method, which comprises the following steps: S101, acquiring initial crystal slurry images respectively collected by a visual sensor deployed in a crystal slurry conveying pipeline of the zinc sulfate industrial production system at M preset time points; S102, for any initial crystal slurry image, inputting the initial crystal slurry image into a trained crystal grain segmentation model to output a crystal grain segmentation image corresponding to the initial crystal slurry image; S103, superimposing M crystal grain segmentation images according to a preset weight vector to obtain a first superimposed image; S104, performing threshold segmentation on the first superimposed image to obtain a first threshold segmentation image; S105, determining a crystal grain deposition detection result according to the distribution information of non-zero pixel points in the first threshold image; S106, when the crystal grain deposition detection result meets a first preset condition, performing optical flow calculation on the M crystal grain segmentation images to obtain a first flow rate detection result; S107, if the first flow rate detection result meets a second preset condition, acquiring initial operating parameters of a crystal slurry pump corresponding to the crystal slurry conveying pipeline; S108, optimizing the initial operation parameter according to the first flow rate detection result to obtain a target operation parameter; S109, controlling the crystal slurry pump according to the target operation parameter.

[0006] The application further provides a zinc sulfate industrial production system optimization device, which comprises: An image acquisition module is configured to acquire initial crystal slurry images collected by a visual sensor arranged in a crystal slurry conveying pipeline of the zinc sulfate industrial production system at M preset time points; An image segmentation module is configured to input any initial crystal slurry image into a trained crystal grain segmentation model and output a crystal grain segmentation image corresponding to the initial crystal slurry image; An image superposition module is configured to superimpose the M crystal grain segmentation images according to a preset weight vector to obtain a first superimposed image; A threshold segmentation module is configured to perform threshold segmentation on the first superimposed image to obtain a first threshold segmentation image; A first detection module is configured to determine a crystal grain deposition detection result according to distribution information of non-zero pixel points in the first threshold image; A second detection module is configured to perform optical flow calculation on the M crystal grain segmentation images to obtain a first flow rate detection result when the crystal grain deposition detection result meets a first preset condition; A parameter acquisition module is configured to acquire initial operation parameters of a crystal slurry pump corresponding to the crystal slurry conveying pipeline when the first flow rate detection result meets a second preset condition; A parameter optimization module is configured to optimize the initial operation parameters according to the first flow rate detection result to obtain a target operation parameter; A parameter control module is configured to control the crystal slurry pump according to the target operation parameter.

[0007] The application further provides a computer device, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the above zinc sulfate industrial production system optimization method when executing the computer program.

[0008] The application further provides a computer readable storage medium, which stores a computer program, and the computer program is executable on a processor to implement the above zinc sulfate industrial production system optimization method.

[0009] The present application has at least the following beneficial effects: the real-time image is collected by the visual sensor for analysis, without relying on historical data modeling, improving the generalization of the pipeline blockage detection, the grain deposition detection is performed through the grain segmentation image superposition mode, the calculation amount is small, the calculation speed is fast, the grain deposition detection result can be accurately determined, the optical flow calculation is performed when the grain deposition detection result meets the condition, avoiding the continuous real-time optical flow calculation and causing the calculation pressure to be too large, the first flow rate detection result is determined through the optical flow calculation, the pipeline blockage detection result can be more directly and accurately determined according to the flow rate, the reliability of the pipeline blockage detection is improved, and then the operation parameters of the crystal slurry pump are optimized according to the first flow rate detection result, and the reliability of the system optimization control is improved. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0011] Figure 1 A flowchart of an optimization method of a zinc sulfate industrial production system provided by the embodiment one of the present application; Figure 2 A structural schematic diagram of an optimization device of a zinc sulfate industrial production system provided by the embodiment two of the present application. DETAILED DESCRIPTION

[0012] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0013] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It can be understood that the above-mentioned terms for distinguishing similar objects can be interchanged under appropriate circumstances, so that the present application can also be implemented in other embodiments than the above-illustrated embodiments or described embodiments. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or server including a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0014] Embodiment one The embodiment one provides a zinc sulfate industrial production system optimization method, which comprises the following steps: Figure 1 As shown in the figure, the embodiment one provides a flowchart of a zinc sulfate industrial production system optimization method, which comprises the following steps: S101, acquiring initial crystal slurry images collected by a visual sensor arranged in a crystal slurry conveying pipeline of the zinc sulfate industrial production system at M preset time points, wherein M is a positive integer; S102, for any initial crystal slurry image, inputting the initial crystal slurry image into a trained grain segmentation model to output a grain segmentation image corresponding to the initial crystal slurry image; S103, superimposing M grain segmentation images according to a preset weight vector to obtain a first superimposed image; S104, performing threshold segmentation on the first superimposed image to obtain a first threshold segmentation image; S105, determining a grain deposition detection result according to distribution information of non-zero pixel points in the first threshold image; S106, when the grain deposition detection result meets a first preset condition, performing optical flow calculation on the M grain segmentation images to obtain a first flow rate detection result; S107, if the first flow rate detection result meets a second preset condition, acquiring initial operation parameters of a crystal slurry pump corresponding to the crystal slurry conveying pipeline; S108, optimizing the initial operation parameters according to the first flow rate detection result to obtain target operation parameters; S109, controlling the crystal slurry pump according to the target operation parameters.

[0015] The zinc sulfate industrial production system can be used to prepare zinc-containing materials into zinc sulfate heptahydrate. The zinc sulfate industrial production system can comprise a two-effect heater, a two-effect crystallization separator, a plate condenser, a zinc sulfate preheater, a hot water heater, a condensate tank, a zinc sulfate machine seal water low-level tank, a zinc sulfate machine seal water high-level tank, a hot water circulating tank, a three-effect heater, a three-effect crystallization separator, a potassium-sodium salt preheater, a potassium-sodium salt machine seal water low-level tank, a potassium-sodium salt machine seal water high-level tank, a cyclone, a secondary mother liquor tank, a two-effect circulating pump, a two-effect crystal slurry pump, a three-effect circulating pump, a three-effect crystal slurry pump, a mixed salt secondary mother liquor pump, a machine seal water pump, a centrifuge, a cooling tower, etc.

[0016] The slurry conveying pipeline can refer to an output pipeline of a two-effect slurry pump or an output pipeline of a three-effect slurry pump. The visual sensor can adopt an industrial waterproof camera, which is matched with an LED light source to avoid interference of crystal reflection. The installation position of the visual sensor can be selected as a straight section of the pipeline to avoid influence of flow field disorder on recognition, and the lens axis is perpendicular to the fluid direction.

[0017] The grain segmentation model can adopt a semantic segmentation model, such as an FCN model, a U-Net model, etc. The architecture and training process of the semantic segmentation model are not described herein again.

[0018] The grain segmentation image contains pixel points belonging to the grain category and pixel points not belonging to the grain category. The pixel value corresponding to the pixel points belonging to the grain category is 1, and the pixel value corresponding to the pixel points not belonging to the grain category is 0.

[0019] The initial operating parameter and the target operating parameter can correspond to the rotating speed of the slurry pump.

[0020] Specifically, the first superimposed image can be threshold segmented by using a preset segmentation threshold. The pixel value greater than the preset segmentation threshold is set to 1, and the pixel value less than or equal to the preset segmentation threshold is set to 0 to obtain a first threshold segmented image. The preset segmentation threshold can be set to 0.85.

[0021] In an embodiment, the optimization method of the zinc sulfate industrial production system further includes the following steps: For any grain segmentation image, the grain segmentation image is divided into a first sub-image and a second sub-image according to a preset column. The first sub-image contains pixel points from the first column to the preset column in the grain segmentation image, and the second sub-image contains pixel points from a column after the preset column to the last column in the grain segmentation image. The number of non-zero pixel points in the first sub-image corresponding to the first preset time point is counted to obtain a first statistical value. The number of non-zero pixel points in the second sub-image corresponding to the first preset time point is counted to obtain a second statistical value. The sum of the first statistical value and the second statistical value is taken as a target statistical value. The second sub-image corresponding to the first preset time point is taken as a first reference sub-image, and the sub-image identifier k is initialized as 2. The second sub-image corresponding to the kth preset time point is taken as a second reference sub-image. The first reference sub-image and the second reference sub-image are added point by point to obtain an intermediate addition image. The number of non-zero pixel points in the intermediate addition image is counted to obtain an intermediate statistical value. If the intermediate statistical value is less than the target statistical value, the intermediate added image is taken as the first reference sub-image, k=k+1 is updated, and the step of taking the second sub-image corresponding to the kth preset time point as the second reference sub-image is executed again; If the intermediate statistical value is greater than or equal to the target statistical value, the value of the current sub-image identifier k is taken as the superimposition number; The superimposition number is taken as the second flow rate detection result; Correspondingly, the step S106 is changed to: when the crystal grain deposition detection result and the second flow rate detection result satisfy the first preset condition, optical flow calculation is performed on the M crystal grain segmentation images to obtain the first flow rate detection result.

[0022] The first preset condition can be that the crystal grain deposition detection result is greater than a preset deposition detection threshold and the second flow rate detection result is greater than a preset reference superimposition number. The reference superimposition number can be a product of a superimposition number determined in the above manner and a reference coefficient under the M historical segmentation images at a known normal flow rate, and the reference coefficient is an integer greater than 1. In the embodiment, the reference coefficient can be set to 1.2.

[0023] The embodiment introduces the second flow rate detection result, and comprehensively judges whether to trigger optical flow detection according to the crystal grain deposition detection result and the second flow rate detection result, so as to avoid false judgment of the crystal grain deposition detection result and improve the reliability of optical flow detection triggering.

[0024] In a specific implementation, the preset weight vector includes a first weight and a second weight; The superimposition of the M crystal grain segmentation images according to the preset first weight to obtain the first superimposed image includes: The crystal grain segmentation image corresponding to the first preset time point is taken as a first temporary image, and a first image identifier i=2 is initialized; The crystal grain segmentation image corresponding to the ith preset time point is taken as a second temporary image; The first temporary image is multiplied by the first weight to obtain a first multiplication result, and the second temporary image is multiplied by the second weight to obtain a second multiplication result; The first multiplication result and the second multiplication result are added to obtain a temporary superimposed image; The temporary superimposed image is taken as the first temporary image, i=i+1 is updated, and the step of taking the crystal grain segmentation image corresponding to the ith preset time point as the second temporary image is executed again until i=M+1, and the final temporary superimposed image is taken as the first superimposed image.

[0025] The sum of the first weight and the second weight is 1, and the second weight is greater than the first weight. In this embodiment, the first weight can be set to 0.2, and the second weight can be set to 0.8. Generally, the second weight should be set to be less than the preset segmentation threshold.

[0026] Specifically, only when the pixel value of a certain pixel point is continuously nonzero. The pixel value of the pixel point in the temporarily superimposed image is higher, and the continuous nonzero pixel value of the pixel point can be considered as the existence of grain deposition at the position corresponding to the pixel point.

[0027] In a specific implementation, the determining of the grain deposition detection result according to the distribution information of the nonzero pixel points in the first threshold image comprises: performing connected domain analysis on the first threshold image to obtain a plurality of initial connected domains; For any initial connected domain, if the number of pixel points contained in the initial connected domain is greater than a preset number threshold, the initial connected domain is determined as a reference connected domain; The sum of the number of pixel points contained in each reference connected domain is calculated, and the calculation result is taken as the grain deposition detection result.

[0028] The preset number threshold can be used to eliminate noise. In this embodiment, the preset number threshold can be set to 5.

[0029] In a specific implementation, the first preset condition is that the grain deposition detection result is greater than a preset deposition detection threshold.

[0030] The preset deposition detection threshold can be determined according to the maximum value of the respective grain deposition detection results of a plurality of groups of M historical segmentation images obtained by using the method of this embodiment under normal flow rate.

[0031] In a specific implementation, the optical flow calculation on the M grain segmentation images to obtain the first flow rate detection result comprises: According to the jth grain segmentation image, the j+1th grain segmentation image and the time interval between adjacent preset time points, a preset optical flow algorithm is used to perform optical flow calculation to obtain the jth reference flow rate, wherein j is an integer in the range of [1, M-1]; Iterate the value of j to obtain M-1 reference flow rates; According to the M-1 reference flow rates, the mean value is calculated, and the obtained mean value calculation result is taken as the first flow rate detection result.

[0032] The preset optical flow algorithm can use Lucas-Kanade optical flow algorithm, FlowNet optical flow neural network, etc.

[0033] Specifically, according to the j-th grain segmentation image, the j+1-th grain segmentation image and the time interval between adjacent preset time points, an instantaneous velocity vector field can be calculated, and the average moving speed of the grain is calculated according to the instantaneous velocity vector field to obtain the reference flow rate.

[0034] In a specific embodiment, the second preset condition is that the first flow rate detection result is less than a preset flow rate detection threshold.

[0035] The preset flow rate detection threshold can be set as a normal flow rate.

[0036] In a specific embodiment, the optimization of the initial operation parameter according to the first flow rate detection result to obtain the target operation parameter includes: determining an optimization target according to the difference between the first flow rate detection result and the preset flow rate detection threshold; optimizing the initial operation parameter according to the optimization target to obtain the target operation parameter.

[0037] The target function can be fitted according to a plurality of groups of initial operation parameters and first flow rate detection results, and the initial operation parameter in the target function is optimized according to the optimization target. The optimization method can be implemented by gradient descent method, genetic algorithm, simulated annealing algorithm, etc. When the optimization target converges, the target operation parameter can be obtained.

[0038] In the first embodiment, the real-time image is collected by the vision sensor for analysis, without relying on historical data modeling, improving the generalization of the pipeline blockage detection. The grain deposition detection is performed by the grain segmentation image superposition method, the calculation amount is small, the calculation speed is fast, and the grain deposition detection result can be accurately determined. When the grain deposition detection result meets the condition, the optical flow calculation is performed, avoiding the continuous real-time optical flow calculation which causes excessive calculation pressure. The first flow rate detection result is determined by the optical flow calculation, and the pipeline blockage detection result can be more directly and accurately determined according to the flow rate, improving the reliability of the pipeline blockage detection. Then, the operation parameter of the crystal slurry pump is optimized according to the first flow rate detection result, improving the reliability of the system optimization control.

[0039] Embodiment two The embodiment two provides an optimization device of a zinc sulfate industrial production system, as shown in the figure, which is a structural schematic diagram of an optimization device of a zinc sulfate industrial production system provided by the embodiment two of the application. The optimization device of the zinc sulfate industrial production system comprises: Figure 2 An image acquisition module 201 is configured to acquire initial crystal slurry images collected by a vision sensor arranged in a crystal slurry conveying pipeline of the zinc sulfate industrial production system at M preset time points, wherein M is a positive integer. An image acquisition module 201 is configured to acquire initial crystal slurry images collected by a vision sensor arranged in a crystal slurry conveying pipeline of the zinc sulfate industrial production system at M preset time points, wherein M is a positive integer. The image segmentation module 202 is configured to input any initial crystal mush image into the trained grain segmentation model, and output a grain segmentation image corresponding to the initial crystal mush image. The image superposition module 203 is configured to superimpose the M grain segmentation images according to a preset weight vector to obtain a first superimposed image. The threshold segmentation module 204 is configured to perform threshold segmentation on the first superimposed image to obtain a first threshold segmentation image. The first detection module 205 is configured to determine a grain deposition detection result according to distribution information of non-zero pixel points in the first threshold image. The second detection module 206 is configured to, when the grain deposition detection result meets a first preset condition, perform optical flow calculation on the M grain segmentation images to obtain a first flow rate detection result. The parameter acquisition module 207 is configured to, if the first flow rate detection result meets a second preset condition, acquire initial operation parameters of a crystal mush pump corresponding to the crystal mush conveying pipeline. The parameter optimization module 208 is configured to optimize the initial operation parameters according to the first flow rate detection result to obtain target operation parameters. The parameter control module 209 is configured to control the crystal mush pump according to the target operation parameters.

[0040] It should be noted that the specific limitations of the optimization device of the zinc sulfate industrial production system can refer to the limitations of the optimization method of the zinc sulfate industrial production system described above, and will not be repeated here. The information interaction and execution process between the above modules can be based on the same concept as the method embodiment, and the specific functions and technical effects brought about can be referred to in the method embodiment part. Here, it will not be repeated.

[0041] Embodiment three The embodiment three provides a computer device, which can be a server. The computer device can include a processor, a memory, a network interface and a database connected by a system bus. The processor of the computer device is configured 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 the computer program in the non-volatile storage medium. The network interface of the computer device is configured to communicate with the external terminal through the network connection. The computer program is executed by the processor to implement an optimization method of a zinc sulfate industrial production system.

[0042] Embodiment four The embodiment four provides a computer readable storage medium, and the computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the optimization method of the zinc sulfate industrial production system in the above embodiment. To avoid repetition, details are not described here. Alternatively, the computer program is executed by the processor to implement the functions of each module / unit in the above embodiment of the zinc sulfate industrial production system optimization device. To avoid repetition, details are not described here.

[0043] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiment methods. Any reference to memory, storage, database or other medium used in each embodiment provided by the present application 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. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0044] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of functional units and modules is exemplified. In actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the above-mentioned functions.

[0045] The above merely describes the preferred embodiments of the present application, and is not intended to limit the present application in any form. Although the present application has been described above with the preferred embodiments, it is not intended to limit the present application, and any person skilled in the art can make some changes or modifications to the above disclosed technical contents without departing from the technical solution of the present application, and the equivalent embodiments with equivalent changes and modifications are still within the scope of the technical solution of the present application.

Claims

1. An optimization method for a zinc sulfate industrial production system, characterized in that, The optimization method for the zinc sulfate industrial production system includes the following steps: S101, acquire the initial crystal slurry images collected by the vision sensor deployed in the crystal slurry conveying pipeline of the zinc sulfate industrial production system at M preset time points, where M is a positive integer; S102, For any initial crystal slurry image, input the initial crystal slurry image into the trained grain segmentation model, and output the grain segmentation image corresponding to the initial crystal slurry image; S103, superimpose the M grain segmentation images according to the preset weight vector to obtain the first superimposed image; S104, perform threshold segmentation on the first superimposed image to obtain a first threshold segmented image; S105, determine the grain deposition detection result based on the distribution information of non-zero pixels in the first threshold image; S106, when the grain deposition detection result meets the first preset condition, optical flow calculation is performed on M grain segmentation images to obtain the first flow velocity detection result; S107, if the first flow rate detection result meets the second preset condition, then obtain the initial operating parameters of the crystal slurry pump corresponding to the crystal slurry conveying pipeline; S108, Optimize the initial operating parameters based on the first flow velocity detection result to obtain the target operating parameters; S109, control the crystal slurry pump according to the target operating parameters.

2. The optimization method for the zinc sulfate industrial production system according to claim 1, characterized in that, The preset weight vector includes a first weight and a second weight; The step of superimposing M grain segmentation images according to a preset first weight to obtain a first superimposed image includes: The first temporary image is initialized with the first image identifier i=2, using the grain segmentation image corresponding to the first preset time point as the first temporary image. The grain segmentation image corresponding to the i-th preset time point is used as the second temporary image; Multiply the first temporary image and the first weight to obtain the first multiplication result, and multiply the second temporary image and the second weight to obtain the second multiplication result; Add the first multiplication result and the second multiplication result to obtain a temporary overlay image; Using the temporary overlay image as the first temporary image, update i=i+1, and return to the step of using the grain segmentation image corresponding to the i-th preset time point as the second temporary image, until i=M+1, to obtain the final temporary overlay image as the first overlay image.

3. The optimization method for the zinc sulfate industrial production system according to claim 1, characterized in that, The step of determining the grain deposition detection result based on the distribution information of non-zero pixels in the first threshold image includes: Connectivity analysis is performed on the first threshold image to obtain several initial connected components; For any initial connected component, if the number of pixels contained in the initial connected component is greater than a preset threshold, then the initial connected component is determined to be a reference connected component. The sum of the number of pixels contained in each reference connected region is calculated, and the calculation result is used as the grain deposition detection result.

4. The optimization method for the zinc sulfate industrial production system according to claim 1, characterized in that, The first preset condition is that the grain deposition detection result is greater than the preset deposition detection threshold.

5. The optimization method for the zinc sulfate industrial production system according to claim 1, characterized in that, The optical flow calculation of M grain segmentation images to obtain the first flow velocity detection result includes: Based on the time interval between the j-th grain segmentation image, the (j+1)-th grain segmentation image and adjacent preset time points, the preset optical flow algorithm is used to calculate the optical flow and obtain the j-th reference flow velocity, where j is an integer in the range [1, M-1]. Iterate through the values ​​of j to obtain M-1 reference flow rates; The average value is calculated based on the M-1 reference flow velocities, and the calculated average value is used as the first flow velocity detection result.

6. The optimization method for the zinc sulfate industrial production system according to claim 1, characterized in that, The second preset condition is: the first flow rate detection result is less than the preset flow rate detection threshold.

7. The optimization method for the zinc sulfate industrial production system according to claim 1, characterized in that, The step of optimizing the initial operating parameters based on the first flow velocity detection result to obtain the target operating parameters includes: The optimization target is determined based on the difference between the first flow velocity detection result and the preset flow velocity detection threshold; The initial operating parameters are optimized according to the optimization objective to obtain the target operating parameters.

8. An optimization device for a zinc sulfate industrial production system, characterized in that, The optimization device for the zinc sulfate industrial production system includes: The image acquisition module is used to acquire initial crystal slurry images collected by the vision sensor deployed in the crystal slurry conveying pipeline of the zinc sulfate industrial production system at M preset time points, where M is a positive integer; The image segmentation module is used to take any initial slurry image, input the initial slurry image into the trained grain segmentation model, and output the corresponding grain segmentation image. The image overlay module is used to overlay M grain segmentation images according to a preset weight vector to obtain a first overlay image; A threshold segmentation module is used to perform threshold segmentation on the first superimposed image to obtain a first threshold segmented image; The first detection module is used to determine the grain deposition detection result based on the distribution information of non-zero pixels in the first threshold image; The second detection module is used to perform optical flow calculation on M grain segmentation images to obtain a first flow velocity detection result when the grain deposition detection result meets the first preset condition. The parameter acquisition module is used to acquire the initial operating parameters of the crystal slurry pump corresponding to the crystal slurry conveying pipeline if the first flow rate detection result meets the second preset condition. The parameter optimization module is used to optimize the initial operating parameters based on the first flow velocity detection result to obtain the target operating parameters; The parameter control module is used to control the crystal slurry pump according to the target operating parameters.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the optimization method of the zinc sulfate industrial production system according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the optimization method for the zinc sulfate industrial production system according to any one of claims 1 to 7.

Images