Aquatic product processing stirring method and device based on multi-data fusion

Through multi-data fusion technology, combined with static nonlinear and dynamic linear control, and the configuration of intelligent controllers and digital feedbacks, the problem of inaccurate parameter control in traditional stirring methods is solved, and the efficiency and stability of the aquatic product processing process is achieved.

CN118707916BActive Publication Date: 2024-11-15DALIAN SHUIYIFANG FOOD CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411218563.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-02
Publication Date
2024-11-15
Estimated Expiration
2044-09-02

AI Technical Summary

Technical Problem

Traditional aquatic product processing and stirring methods lack effective data acquisition and analysis methods, which leads to inability to accurately control the stirring parameters and difficulty in adapting to different product characteristics, resulting in uncertainty in the processing process and unstable quality.

Method used

Using aquatic product processing and stirring methods and devices based on multi-data fusion, the braking mechanism and basic stirring information of the stirring device are read, combined with multi-source stirring records, and the fuzzy stirring process is identified, and static nonlinear control and dynamic linear control are used as The benchmark performs process segmentation and control decision-making, configures intelligent controllers, determines disturbance relationships, establishes digital feedback, and realizes full-cycle control.

Benefits of technology

Accurate and efficient stirring action control is achieved, which can adapt to the stirring needs of different products and improve the stability and consistency of product quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118707916B_ABST
    Figure CN118707916B_ABST
Patent Text Reader

Abstract

The present invention discloses a method and device for aquatic product processing and stirring based on multi-data fusion, and relates to the field of stirring control technology. The method includes: reading the braking mechanism and basic stirring information of the stirring device; retrieving and determining multi-source stirring records, and determining the fuzzy stirring process; identifying the fuzzy stirring process, performing process segmentation and parameter control decision-making, and determining the pre-control strategy; configuring an intelligent controller based on the pre-control strategy; determining stirring disturbance factors and disturbance relationships; establishing a digital feedback device and performing self-calibration adjustment; performing main line control based on an intelligent controller, synchronously monitoring and determining multi-source sensor data, performing multi-source fitting of data and stirring flow field analysis feedback, and performing full-cycle control of aquatic product processing and stirring. The present invention solves the technical problems of low stirring efficiency, inability to accurately control stirring parameters, and difficulty in adapting to different product characteristics in the prior art, and achieves accurate and efficient stirring action control, and can adapt to the stirring requirements of different products.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of stirring control, and in particular to a method and a device for stirring aquatic product processing based on multi-data fusion. Background Art

[0002] In the aquatic product processing industry, stirring is a key operation link. Traditional aquatic product processing stirring methods usually rely on experience and fixed parameter settings. Due to the lack of effective data collection and analysis methods, key parameters in the processing process, such as stirring speed, stirring time, temperature, pressure, etc., cannot be monitored in real time and accurately controlled. This makes the processing process have greater uncertainty and volatility, and it is difficult to ensure the stability and consistency of product quality.

[0003] The existing technology has the technical problems of low stirring efficiency, inability to accurately control stirring parameters, and difficulty in adapting to different product characteristics. Summary of the invention

[0004] The present application provides a method and device for aquatic product processing stirring based on multi-data fusion, which is used to solve the technical problems in the prior art of low stirring efficiency, inability to accurately control stirring parameters, and difficulty in adapting to different product characteristics.

[0005] In view of the above problems, the present application provides a method and device for aquatic product processing and stirring based on multi-data fusion.

[0006] In a first aspect of the present application, a method for aquatic product processing and stirring based on multi-data fusion is provided, the method comprising:

[0007] Read the braking mechanism and basic stirring information of the stirring device, including stirring base materials and quality standards; retrieve and determine multi-source stirring records, combine the braking mechanism and the basic stirring information, determine the fuzzy stirring process, and the fuzzy stirring process includes multiple process stages; identify the fuzzy stirring process, and perform process segmentation and parameter control decision-making based on static nonlinear control and dynamic linear control to determine the pre-control strategy, and the pre-control strategy includes a stirring control function; configure an intelligent controller based on the pre-control strategy, and the intelligent controller includes a linear block and a nonlinear block, and the linear block includes a cascade control unit. The cascade control unit includes a direct control inner loop and an indirect control outer loop; determines the stirring disturbance factor, performs single-factor disturbance analysis and multi-factor coordinated disturbance analysis, and determines the disturbance relationship; combines the disturbance relationship with the correction mechanism to establish a digital feedback device, which is used for self-calibration and adjustment; performs main line control based on the intelligent controller, synchronously monitors and determines multi-source sensor data, and transmits it back to the digital feedback device for multi-source data fitting and stirring flow field analysis feedback, so as to perform full-cycle control of aquatic product processing stirring, wherein the multi-source sensor data is acquired based on the monitoring of the multi-source sensor installed on the stirring device.

[0008] The second aspect of the present application provides a water product processing stirring device based on multi-data fusion, the device comprising:

[0009] An information reading module, the information reading module is used to read the braking mechanism and basic stirring information of the stirring device, including stirring base materials and quality standards; a fuzzy stirring process determination module, the fuzzy stirring process determination module is used to retrieve and determine multi-source stirring records, combine the braking mechanism and the basic stirring information, determine the fuzzy stirring process, and the fuzzy stirring process includes multiple process stages; a pre-control strategy determination module, the pre-control strategy determination module is used to identify the fuzzy stirring process, and perform process segmentation and parameter control decision-making based on static nonlinear control and dynamic linear control to determine the pre-control strategy, and the pre-control strategy includes a stirring control function; an intelligent controller configuration module, the intelligent controller configuration module configures an intelligent controller based on the pre-control strategy, and the intelligent controller includes a linear block and a nonlinear block, and the linear The block includes a cascade control unit, which includes a direct control inner loop and an indirect control outer loop; a disturbance relationship determination module, which is used to determine the stirring disturbance factors, perform single-factor disturbance analysis and multi-factor coordinated disturbance analysis, and determine the disturbance relationship; a digital feedback device establishment module, which is used to combine the disturbance relationship with the correction mechanism to establish a digital feedback device, and the digital feedback device is used to perform self-calibration adjustment; a full-cycle control module, which performs main line control based on the intelligent controller, synchronously monitors and determines multi-source sensor data, and transmits it back to the digital feedback device for multi-source data fitting and stirring flow field analysis feedback, so as to perform full-cycle control of aquatic product processing stirring, wherein the multi-source sensor data is obtained based on the monitoring of the multi-source sensor installed on the stirring device.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] Read the braking mechanism and basic stirring information of the stirring device, including stirring base materials and quality standards; retrieve and determine multi-source stirring records, determine the fuzzy stirring process, and the fuzzy stirring process includes multiple process stages; identify the fuzzy stirring process, and perform process segmentation and parameter control decisions based on static nonlinear control and dynamic linear control, and determine the pre-control strategy; configure the intelligent controller based on the pre-control strategy; determine the stirring disturbance factors and the disturbance relationship; combine the disturbance relationship with the correction mechanism to establish a digital feedback device; perform main line control based on the intelligent controller, synchronously monitor and determine multi-source sensor data, and send it back to the digital feedback device for multi-source data fitting and stirring flow field analysis feedback, so as to perform full-cycle control of aquatic product processing stirring. It achieves accurate and efficient stirring action control, and can adapt to the stirring requirements of different products. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in 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 only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 A schematic diagram of a process flow of aquatic product processing and stirring method based on multi-data fusion provided in an embodiment of the present application;

[0014] Figure 2 A schematic diagram of the structure of aquatic product processing stirring device based on multi-data fusion provided in an embodiment of the present application.

[0015] Explanation of the accompanying drawings: information reading module 10, fuzzy mixing process determination module 20, pre-control strategy determination module 30, intelligent controller configuration module 40, disturbance relationship determination module 50, digital feedback device establishment module 60, full-cycle control module 70. DETAILED DESCRIPTION

[0016] The present application provides a method and device for aquatic product processing stirring based on multi-data fusion, which is used to solve the technical problems in the prior art of low stirring efficiency, inability to accurately control stirring parameters, and difficulty in adapting to different product characteristics.

[0017] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0018] Embodiment 1

[0019] like Figure 1 As shown, the present application provides a method for aquatic product processing and stirring based on multi-data fusion, the method comprising:

[0020] Step S100: Read the braking mechanism and basic stirring information of the stirring device, including stirring base material and quality standards.

[0021] Specifically, start the relevant data reading program or interface and connect to the database, file or sensor storing the relevant information of the stirring device. For the braking mechanism of the stirring device, read its braking mode in detail, such as mechanical braking, electromagnetic braking or hydraulic braking. At the same time, obtain the relevant parameters of braking, such as the response time of braking, the size and adjustment range of braking force, the frequency limit of braking, etc. Regarding basic stirring information, clarify the type of base material used for stirring, including the composition, characteristics and proportion of various aquatic product raw materials. For example, fresh fish, shrimp, or aquatic products that have been processed to a certain extent, as well as their texture, viscosity and other characteristics. In terms of quality standards, read the specific requirements for stirring uniformity, such as stipulating that within a certain detection range, the deviation of the component distribution of the base material cannot exceed a certain value; the standard of particle size after stirring, such as the limitation of the maximum particle diameter or the average particle diameter; and the temperature change range and humidity requirements of the material after stirring, as well as the special standards related to food safety and quality, such as microbial content limit, nutrient retention degree, etc. During the reading process, the acquired data is preliminarily checked for validity and format conversion to ensure the accuracy and availability of the data, prepare for subsequent processing and analysis, and help to achieve accurate and stable stirring action control.

[0022] Step S200: Retrieve and determine multi-source mixing records, combine the braking mechanism with the basic mixing information, and determine a fuzzy mixing process, wherein the fuzzy mixing process includes multiple process stages.

[0023] Specifically, the search program is started to search for mixing records related to the current mixing task from multiple data sources (such as past production databases, industry standard libraries, operation records of similar equipment, etc.). These multi-source mixing records contain mixing process data under various conditions, such as historical mixing operation records using similar mixing devices, the same or similar mixing base materials, and similar quality standards. After obtaining these multi-source mixing records, they are comprehensively compared and analyzed with the braking mechanism of the current mixing device (including braking mode, parameters, etc.) and basic mixing information (characteristics of the mixing base materials, specific requirements of quality standards, etc.). Through the integration and processing of multi-source data, a rough, not precise, but fuzzy mixing process covering the main steps and stages is preliminarily determined. This fuzzy mixing process takes into account the needs of different process stages, including the raw material pretreatment stage, the initial mixing stage, the intensive mixing stage, the mixing uniformity detection stage, etc. For example, for some base materials that are easy to agglomerate, a slower mixing speed is required in the initial stage to loosen them, and then the mixing speed is gradually increased in the subsequent stages; for products with high requirements for particle size, specific grinding steps are also required during the mixing process. In the process of determining the fuzzy mixing process, the mutual influence and restriction relationship of various factors are fully considered, which provides a preliminary framework and foundation for further refinement and optimization.

[0024] Step S300: Identify the fuzzy mixing process, perform process segmentation and parameter control decision-making based on static nonlinear control and dynamic linear control, and determine a pre-control strategy, wherein the pre-control strategy includes a mixing control function.

[0025] Specifically, the previously determined fuzzy mixing process is deeply analyzed and understood to identify the key features and requirements of each process stage, including the changing trend of the mixing speed, the length of the mixing time, the transformation of the material state, etc. With static nonlinear control theory and dynamic linear control theory as the basic reference framework and criteria, static nonlinear control is used to deal with those mixing links that show nonlinear characteristics under specific conditions, such as when the viscosity of the mixing material changes significantly nonlinearly with the mixing process. Dynamic linear control is applicable to those mixing parameters that show linear changes in the time dimension, such as the gradual increase or decrease of the mixing speed. Based on these two control theories, the fuzzy mixing process is carefully segmented. The entire mixing process is divided into several smaller sub-processes with relatively independent control requirements. At the same time, for each sub-process, a decision is made to participate in the control, and the key parameters that need to be adjusted and controlled and their control methods are determined. On this basis, a preliminary control strategy is determined. This pre-control strategy contains specific mixing control functions, which describe the mathematical relationship between the various control parameters of the mixing device (such as speed, mixing time, braking force, etc.) and the mixing process in each sub-process. For example, the stirring control function of a sub-process is expressed as a nonlinear function of speed and time to achieve a specific stirring effect, while the control function of another sub-process is linear to maintain a stable stirring state. Through such process segmentation, parameter control decision-making and determination of stirring control function, the foundation is laid for achieving accurate and efficient stirring control.

[0026] Step S400: configuring an intelligent controller based on the pre-control strategy, wherein the intelligent controller includes a linear block and a nonlinear block, wherein the linear block includes a cascade control unit, and wherein the cascade control unit includes a direct control inner loop and an indirect control outer loop.

[0027] Specifically, the intelligent controller is divided into a linear block and a nonlinear block. The linear block is used to handle the part of the mixing process that presents a linear change law, while the nonlinear block is specifically used to deal with the links with nonlinear characteristics. In the linear block, a cascade control unit is set. This cascade control unit consists of a direct control inner loop and an indirect control outer loop. The direct control inner loop can respond quickly and accurately to small deviations and changes. It directly acts on the controlled object and has high control sensitivity and rapidity. The indirect control outer loop is mainly responsible for handling a larger range of deviations and the overall control effect. It adjusts the set value of the inner loop by monitoring the output of the inner loop and the overall state of the system to achieve more macro and stable control. For example, in the control of the mixing speed, if the slight deviation between the actual speed and the set speed occurs within the range of the direct control inner loop, the inner loop will immediately make a quick adjustment. When the deviation is large or lasts for a long time, the indirect control outer loop will intervene and reset the control target of the inner loop to ensure that the mixing speed can eventually stabilize within the ideal range. With such a configuration, the intelligent controller can flexibly use linear and nonlinear control methods, as well as the synergistic effect of the inner and outer loops of the cascade control unit according to the different characteristics and requirements of the mixing process, to achieve accurate, efficient and stable control of the mixing process.

[0028] Step S500: determine stirring disturbance factors, perform single-factor disturbance analysis and multi-factor coordinated disturbance analysis, and determine disturbance relationships.

[0029] Specifically, various factors that may interfere with and affect the mixing process are comprehensively sorted out and determined. These disturbance factors may include, but are not limited to, mechanical wear of the mixing device, fluctuations in the power supply voltage, uneven feeding of materials, changes in ambient temperature and humidity, etc. For each determined disturbance factor, a single factor disturbance analysis is performed. This means that the influence of the change of this factor on the mixing process is studied separately while other conditions remain unchanged. For example, under the premise of fixing other conditions, gradually increase or decrease the power supply voltage, observe its specific influence on the mixing speed and mixing effect, and record the relevant data and change trends. Next, a multi-factor synergistic disturbance analysis is performed. At this time, each factor is no longer viewed in isolation, but the values ​​or states of multiple disturbance factors are changed at the same time to study the comprehensive influence of their combined action on the mixing process. For example, the feed rate and ambient temperature are changed at the same time to observe how they interact and affect the uniformity and quality of mixing. Determine the relationship between the various disturbance factors. This relationship may be linear, nonlinear, or a complex functional relationship. For example, it is found that there is a certain nonlinear correlation between the fluctuation of the power supply voltage and mechanical wear, or the synergistic influence of the feed rate and ambient humidity on the mixing effect presents a specific functional form. Through such in-depth and comprehensive disturbance analysis, we can clearly understand the individual effects of each disturbance factor and the synergistic effects between them, providing a solid basis for subsequent effective control and compensation measures, enabling more precise adjustments and compensation, and improving the stability and consistency of the mixing process.

[0030] Step S600: combining the disturbance relationship with the correction mechanism to establish a digital feedback device, wherein the digital feedback device is used for self-calibration adjustment.

[0031] Specifically, the determined disturbance relationship is studied and understood in depth. It is clear how each disturbance factor individually and synergistically affects the mixing process from the expected impact. Based on the pre-designed correction mechanism, that is, the corrective and adjustment measures to be taken for different types and degrees of disturbances. Based on a clear understanding of the disturbance relationship and the correction mechanism, a digital feedback device is established. The working principle of the digital feedback device is illustrated by the PID (proportional-integral-differential) control algorithm: During the mixing process, the digital feedback device sets a desired mixing output value (such as the desired mixing speed, mixing uniformity, etc.). It monitors the actual mixing output value in real time. The proportional link (P) in the PID algorithm quickly produces a control action based on the deviation between the desired output value and the actual output value multiplied by a proportional coefficient. For example, the larger the deviation, the greater the control action to quickly reduce the deviation. The integral link (I) integrates the deviation, that is, accumulates the size and duration of the deviation. Even if the deviation is small, if it persists, the integral action will gradually increase the control action to eliminate steady-state errors and ensure long-term accuracy. The differential link (D) produces a control action based on the rate of change of the deviation. When the rate of change of the deviation is large, the differential action will produce a larger control effect to suppress the rapid change of the deviation and improve the stability of the system. For example, assuming that the desired stirring speed is 100 rpm, the current actual speed is 80 rpm, the proportional coefficient is 0.5, the integral coefficient is 0.1, the differential coefficient is 0.2, and the sampling time is 1 second. Proportional action = (100-80) × 0.5 = 10, integral action = previously accumulated integral value + (100-80) × 0.1 × 1 = previously accumulated integral value + 2, differential action = (80-last speed) × 0.2, the final control action = proportional action + integral action + differential action, this control action will be used to adjust the input of the stirring device (such as motor power, stirring blade angle, etc.) to make the actual stirring speed close to or reach the desired 100 rpm. Through continuous sampling, calculation and adjustment, the PID algorithm enables the digital feedback device to effectively self-calibrate and adjust the stirring process. By establishing such a digital feedback device, real-time, accurate and automatic calibration and adjustment of the stirring process can be achieved to ensure the stability and reliability of the stirring results.

[0032] Step S700: Based on the intelligent controller, main line control is performed, multi-source sensor data is synchronously monitored and determined, and the data is sent back to the digital feedback device for multi-source data fitting and stirring flow field analysis feedback, so as to perform full-cycle management and control of aquatic product processing stirring, wherein the multi-source sensor data is obtained based on the monitoring of the multi-source sensor installed on the stirring device.

[0033] Specifically, the intelligent controller starts to execute its pre-configured mainline control function. It precisely controls and adjusts the key components and operations of the stirring device according to the previously determined control strategy and parameters. While the intelligent controller is working, multiple different types of sensors installed on the stirring device are also running synchronously. These multi-source sensors include but are not limited to speed sensors for measuring stirring speed, torque sensors for detecting stirring torque, temperature sensors for monitoring material temperature, humidity sensors for sensing material humidity, etc. These sensors obtain various physical quantities and state information about the stirring process in real time, and convert them into digital signals, which are determined as multi-source sensing data. These multi-source sensing data are quickly transmitted back to the digital feedback device. After receiving these data, the digital feedback device uses data multi-source fitting technology to integrate and correlate multiple data from different sensors. At the same time, the digital feedback device also analyzes the stirring flow field to study the flow pattern, velocity distribution, mixing degree, etc. of the material during the stirring process. Based on the results of data multi-source fitting and stirring flow field analysis, the digital feedback device generates feedback information. These feedback information includes an evaluation of the current stirring state, indication of possible problems or deviations, and corresponding adjustment suggestions. These feedback information are passed to the intelligent controller again, and the intelligent controller optimizes and adjusts the control strategy and parameters in real time according to the feedback information, so as to achieve full-cycle and all-round effective control of the aquatic product processing and mixing. Through such a continuous monitoring, feedback and adjustment cycle, it is ensured that the mixing process is always in the optimal state to meet the high quality and high efficiency requirements of aquatic product processing.

[0034] In a possible implementation, step S200 further includes:

[0035] Step S210: traverse the multi-source stirring records to determine a first process node, where the first process node is a dynamic control process or a static control process.

[0036] Step S220: Based on the first process node, clustering processing is performed on the mapping record part to determine a first clustering result.

[0037] Step S230: traverse the first clustering results, determine the clustering result with the largest number of clusters and perform fuzzy conversion, and determine the first fuzzy mixing process.

[0038] Step S240: combining the braking mechanism with the basic mixing information, performing confidence verification and adaptive adjustment on the first fuzzy mixing process.

[0039] Specifically, each record in the multi-source mixing record is carefully reviewed and analyzed one by one. In each mixing record, the process nodes are identified and determined according to the pre-set standards and characteristics. For each process node, whether it is a dynamic control process or a static control process is distinguished by judging whether its control parameters change significantly with time, mixing progress, material status and other factors during the mixing process. For example, if the mixing speed of a process node is adjusted in real time according to the real-time viscosity of the material, it is identified as a dynamic control process; and if the mixing speed remains constant at a certain process stage and is not affected by other factors, it is a static control process. After traversing all the multi-source mixing records, the type of each first process node (dynamic control process or static control process) is clearly marked and determined to prepare for subsequent processing and analysis.

[0040] After clarifying whether the first process node is a dynamic control process or a static control process, the types of these process nodes are used as key features to cluster the related mapping records in the multi-source mixing records. Use appropriate clustering algorithms, such as K-Means algorithm, hierarchical clustering algorithm, etc. The algorithm will divide the related mapping records into different clusters according to the similarity of the types of process nodes. In the clustering process, multiple factors such as the duration of the process, the range of control parameters, and the characteristics of the materials involved are considered to ensure the accuracy and rationality of the clustering. After clustering, multiple different clusters are obtained, each cluster represents a group of mapping records with similar characteristics. These clusters together constitute the first clustering result, which provides the basis and basis for further analysis and determination of the fuzzy mixing process.

[0041] Each cluster in the first clustering result is checked and analyzed in turn. In this process, the number of elements contained in each cluster, that is, the number of mapping records, is counted. From all the clusters, the cluster with the largest number of mapping records is accurately found. Although the mapping records in this largest cluster are similar, there are still some differences. In order to eliminate these differences and make the final mixing process applicable to the entire cluster, not just some records, fuzzy conversion is required. In the fuzzy conversion process, some specific parameters, conditions or boundaries will be appropriately adjusted and fuzzified. For example, the original precise values ​​of time, speed, temperature, etc. may be converted into a range, or the original clear stage division may become relatively vague but more inclusive. After the fuzzy conversion is completed, the result of the fuzzy conversion will be verified and compensated according to the characteristics of this mixing itself, such as the characteristics of the mixing materials, quality requirements, equipment performance, etc. Through verification, check whether the converted results are reasonable and feasible; through compensation, correct and improve the possible deviations or deficiencies to improve the fit between the final first fuzzy mixing process and the current mixing task. After the above series of operations, the first fuzzy mixing process that meets the requirements is finally determined.

[0042] First, the braking mechanism and basic stirring information of the stirring device are obtained. The braking mechanism includes detailed parameters and characteristics in terms of braking mode, response time, braking force, etc. The basic stirring information covers key contents such as the composition, properties, quality standards of the stirring base material, and the expected stirring effect. Then, these braking mechanisms and basic stirring information are comprehensively compared and analyzed with the first fuzzy stirring process previously determined. In the confidence verification link, the reliability and rationality of the first fuzzy stirring process in achieving the expected stirring effect, meeting quality requirements, and cooperating with the braking mechanism are evaluated based on the existing theoretical models, empirical data, and industry standards. Check whether the various steps and parameter settings in the process are within the feasible range, and whether there are problems that may cause equipment overload, uneven stirring, material damage, etc. For example, theoretical model comparison, the key parameters and operating steps in the first fuzzy stirring process are compared with the relevant theoretical models. For example, check whether the change law of the stirring speed conforms to the theoretical principles of fluid mechanics or material mixing, and whether the stirring time matches the theoretical calculation of material reaction or mixing. For empirical data reference, consult the actual empirical data of similar stirring tasks in the past. Compare successful cases with the same or similar materials, equipment and process conditions to see whether the parameter settings and processes in the first fuzzy mixing process are within the reasonable range of empirical data. If there are deviations, analyze their causes and possible impacts. If problems or uncertainties are found in the confidence check, enter the adaptive adjustment stage. According to the actual performance of the braking mechanism and the specific requirements of the basic mixing information, the parameters such as the mixing speed, time, and braking intervention point in the first fuzzy mixing process are modified and optimized in a targeted manner. For example, if the response speed of the braking mechanism is slow, it is necessary to appropriately extend the deceleration stage in the mixing process; if the basic mixing information has higher requirements for the uniformity of the material, it is necessary to increase the mixing time or adjust the mixing method. Through continuous confidence checks and adaptive adjustments, the first fuzzy mixing process can fully combine the braking capacity of the mixing device and the basic mixing requirements to ensure that the final mixing process is efficient, stable and meets quality standards.

[0043] In one possible implementation, step S300 includes:

[0044] Step S310: The stirring control function includes: ,in, is the static nonlinear part, which is the direct parameter control type. is the dynamic linear part, Contains direct parameter control classes and linear relationships , ,in, For the Initial direct control of the process stage, is a constant, For the The phase progression of the process phases.

[0045] Step S320: In combination with the stirring control function, traverse the multiple process stages to perform process positive serialization integration and determine the pre-control strategy.

[0046] Specifically, the stirring control function includes: , It partially reflects the static nonlinear characteristics of the mixing process. It is related to some nonlinear physical or chemical properties of the mixing materials. Its change law is relatively complex and non-linear. It belongs to the direct parameter control type and can directly exert control influence on the mixing process. It is the dynamic linear part, including direct parameter control and linear relationship , which describes the linear change law of stirring control parameters with the change of time or other linear variables. Indicates The initial direct parameter control of the process stage is a fixed starting control parameter value. It is a constant and is related to the equipment characteristics or material characteristics. For the The stage progress of a process stage reflects the degree of advancement of the process stage.

[0047] Traverse multiple process stages. For each process stage, determine the specific role and value of the static nonlinear part, dynamic linear part and direct parameter control class in this stage according to the corresponding relationship between each part in the stirring control function and the process stage. According to the sequence of the processes, the control parameters and relationships of each process stage are positively serialized and integrated. This means that in the order from the initial process to the final process, the control requirements and characteristics of each stage are considered in turn, and the role of the stirring control function of each stage is comprehensively considered to finally determine the entire pre-control strategy. In this way, the different control requirements and characteristics in multiple process stages can be fully considered, so as to formulate a pre-control strategy that can effectively achieve the stirring target.

[0048] In one possible implementation, step S400 includes:

[0049] Step S410: Based on the pre-control strategy, Nonlinear block programmable settings based on The linear block is programmable.

[0050] Step S420: wherein performing the programmable setting of the linear block includes:

[0051] Based on the linear relationship , configure an indirect control outer loop, establish a connection between the direct control inner loop and the indirect control outer loop, and constitute the cascade control unit, wherein the indirect control outer loop is used to perform direct control constraints on the inner loop.

[0052] Step S430: constructing the linear block based on the cascade control unit.

[0053] Specifically, the programmable setting of nonlinear blocks and linear blocks based on the pre-control strategy is to convert the pre-control strategy into a specific executable program to achieve precise control of the relevant system or process. In the process of configuring the intelligent controller, the pre-control strategy should be used as the basis. First, it is clear that the stirring control function involved in the pre-control strategy includes two parts, F(A) and F(B), where F(A) is the static nonlinear part and F(B) is the dynamic linear part and includes the direct parameter control class and the linear relationship f(B). Then, for the programmable setting of the nonlinear block, the static nonlinear characteristics represented by F(A) are deeply analyzed, including its related parameters, function form and specific role in stirring control. Based on these understandings, F(A) is converted into specific programming instructions to ensure that the nonlinear block can accurately realize the requirements of nonlinear control in the pre-control strategy. For example, it is necessary to implement the corresponding algorithm in programming according to the specific function form of F(A) to accurately control the stirring parameters related to nonlinearity. At the same time, for the programmable setting of the linear block, detailed planning is carried out based on F(B). Carefully study the direct parameter control class and linear relationship f(B) contained in F(B), where , R is the initial direct parameter control of the i-th process stage, k is a constant, and x is the stage progress of the i-th process stage. According to these parameters and relationships, the programming logic of the linear block is determined so that the linear block can effectively implement the provisions on linear control in the pre-control strategy. For example, it is necessary to set the corresponding control loop and parameters according to the linear relationship f(B) to ensure the stability and accuracy of the linear block in stirring control.

[0054] According to the linear relationship contained in F(B) in the stirring control function , to configure the indirect control outer loop. This means that the linear relationship needs to be carefully analyzed to determine the relevant parameters and control strategies of the indirect control outer loop. For example, the control target of the outer loop, the processing method of the feedback signal, and the calculation method of the control output are determined according to the linear relationship. By reasonably configuring the indirect control outer loop, it can effectively respond to changes in the system and provide necessary support and constraints for the direct control inner loop. Establish a connection between the direct control inner loop and the indirect control outer loop. The establishment of this connection is a key step in realizing cascade control. Through a specific communication method or signal transmission mechanism, the relevant information of the direct control inner loop is transmitted to the indirect control outer loop, and the control instructions of the indirect control outer loop are also transmitted to the direct control inner loop. In this way, the inner and outer loops can work together to achieve precise control of the mixing process.

[0055] In the cascade control unit, the main function of the indirect control outer loop is to constrain the direct control behavior of the direct control inner loop. The indirect control outer loop can adjust and optimize the control parameters of the direct control inner loop according to the overall performance indicators, operating status and external interference of the system. For example, when subject to large interference, the indirect control outer loop can appropriately reduce the control gain of the direct control inner loop to avoid excessive response of the inner loop and cause system instability. In addition, the indirect control outer loop can also limit the control range of the direct control inner loop to ensure that the control behavior of the inner loop does not exceed a reasonable range, thereby improving reliability and safety.

[0056] The performance and characteristics of the cascade control unit are analyzed in depth to determine the requirements for the construction of the linear block. Considering the nonlinear factors that may exist in the mixing process, such as changes in the characteristics of the material and the nonlinear response of the mixing device, it is necessary to design a corresponding nonlinear control strategy. Next, according to the analysis results, a suitable nonlinear model or algorithm is selected to construct the nonlinear block. Taking the construction of the nonlinear block based on the neural network as an example, a large amount of empirical data related to the mixing process is collected. These data include input variables (such as mixing speed, material characteristics, etc.) and corresponding output variables (such as mixing effect, quality indicators, etc.). Then, these data are divided into a training set and a test set. The training set is used to train the neural network, and the network can learn the nonlinear relationship between the input variables and the output variables by adjusting the weights and biases of the network. During the training process, the neural network automatically extracts features from the data and establishes a mapping between the input and output. Through continuous iterative training, the network is gradually optimized and the prediction ability of unknown data is improved. After the training is completed, the test set is used to evaluate the performance of the neural network to ensure that it can accurately predict the nonlinear behavior in the mixing process. In practical applications, the trained neural network is integrated into the entire control system as a nonlinear block. When new mixing parameters are input, the neural network can quickly and accurately give the corresponding control output to achieve nonlinear control of the mixing process. Through the nonlinear block based on the neural network, the empirical data can be fully utilized to achieve effective control of complex nonlinear systems and improve the quality and efficiency of aquatic product processing mixing.

[0057] In one possible implementation, step S500 includes:

[0058] Step S510: reading the historical control records of the stirring device, mining stirring disturbance factors, and mining standards to meet the preset frequency.

[0059] Step S520: determining a first variable for the stirring disturbance factor, performing stirring disturbance analysis based on a unit variable, and determining a single factor disturbance relationship, wherein the first variable is any one of the stirring disturbance factors.

[0060] Step S530: determining a second variable for the stirring disturbance factor, performing a stirring disturbance analysis of multiple variables in coordination, and determining a multi-factor coordinated disturbance relationship, wherein the second variable is any at least two factors of the stirring disturbance factor.

[0061] Step S540: Combining the single-factor disturbance relationship with the multi-factor collaborative disturbance relationship to determine the disturbance relationship.

[0062] Specifically, the historical control records of the stirring device are obtained. These records contain various relevant data of the stirring device during its past operation, such as stirring speed, stirring time, material characteristics, environmental conditions and other information. Then, through in-depth analysis and mining of these historical data, try to find out the factors that may interfere with or affect the stirring process. These factors are called stirring disturbance factors. When mining these disturbance factors, certain mining standards need to be followed, that is, the frequency of these factors appearing in historical records must reach a preset frequency. Only factors that meet this preset frequency will be identified as valid stirring disturbance factors, and thus be further analyzed and processed. Such a setting can ensure that the disturbance factors mined have a certain stability and representativeness, and can provide valuable reference for subsequent stirring control and optimization.

[0063] After determining the stirring disturbance factors, select one of these factors as the first variable. This first variable can be any one of the stirring disturbance factors. Next, conduct stirring disturbance analysis based on unit variables. This means that only the disturbance effect of this first variable on the stirring process is considered, and other factors are temporarily ignored. Through in-depth analysis of this single variable, the relationship between it and the stirring disturbance, that is, the single-factor disturbance relationship, is determined. This analysis can help us understand how each individual stirring disturbance factor specifically affects the stirring process, thereby providing a more specific basis for subsequent control and adjustment. For example, if the first variable determined is the stirring speed, then a special analysis will be made on how changes in the stirring speed lead to stirring disturbances, as well as the specific mathematical relationship or law between them.

[0064] Similarly, for the previously determined stirring disturbance factors, at least two factors are selected as the second variable. The difference is that here we focus on the synergistic effect of multiple factors. Then, a stirring disturbance analysis of multi-factor variables is carried out, that is, the disturbance effect of these selected multiple factors on the stirring process is comprehensively considered. Through this analysis, the purpose is to determine the synergistic disturbance relationship of multiple factors, that is, to clarify the comprehensive influence mode and degree of these factors on the stirring disturbance when they interact with each other. For example, if the stirring disturbance factors include stirring speed, material concentration and temperature, then the second variable may be a combination of stirring speed and material concentration, or a combination of stirring speed, material concentration and temperature. By analyzing the impact of these multi-factor combinations on stirring disturbances, the synergistic relationship between them can be revealed, providing a basis for a more comprehensive understanding and control of the stirring process.

[0065] The previously obtained disturbance analysis results of a single stirring disturbance factor (single-factor disturbance relationship) and the analysis results of the synergistic effect of multiple stirring disturbance factors (multi-factor synergistic disturbance relationship) are integrated. Analyze the single-factor disturbance relationship to understand how each individual stirring disturbance factor specifically affects the stirring process. For example, it is found that an increase in stirring speed will lead to an increase in stirring power, or a change in material concentration will affect the uniformity of stirring. Next, study the multi-factor synergistic disturbance relationship to explore the comprehensive impact of multiple stirring disturbance factors on the stirring process when they interact. For example, it is found that when the stirring speed and material concentration change at the same time, their effects on the stirring effect are not simply superimposed, but there is a certain complex interaction. Then, we will combine these single-factor and multi-factor analysis results. In the process of combination, we need to consider the relationship and weight between various factors. For example, some factors may have a more significant impact on the disturbance relationship and need to be given a higher weight. Through this combination and analysis, a comprehensive disturbance relationship can be determined, which can accurately reflect the impact of various factors on the disturbance during the stirring process. This disturbance relationship will provide an important basis for our subsequent control and optimization of the stirring device. For example, we can adjust the operating parameters of the stirring device according to this disturbance relationship to minimize the adverse effects of the disturbance on the stirring effect and improve the stability and quality of the stirring.

[0066] In one possible implementation, step S700 includes:

[0067] Step S710: constructing a flow field space based on the built-in stirring space of the stirring device.

[0068] Step S720: setting multiple step sizes, and determining a verification flow field point cloud based on the flow field space.

[0069] Step S730: Based on the multi-source sensing data, traverse the verification flow field point cloud, perform same-position data fitting, and determine the real-time flow field.

[0070] Step S740: performing expected over-limit determination and feedback analysis on the real-time flow field, wherein sensor trigger management is performed at key stirring nodes.

[0071] Specifically, the built-in stirring space of the stirring device is measured and analyzed in detail, including the shape (such as cylindrical, square, etc.), size (length, width, height, etc.), internal structure (such as the position and shape of the stirring paddle, etc.) and other physical properties related to the stirring space (such as material, surface roughness, etc.). After obtaining this information, computer-aided design (CAD) software or other related modeling tools are used to accurately build a model of the built-in stirring space of the stirring device in a virtual environment based on the actual measured data. Next, based on the principles of fluid mechanics and mathematical models (such as the Navier-Stokes equations, which are motion equations that describe the conservation of momentum of viscous incompressible fluids, which can better describe the flow of fluids in the stirring space. The equations include the mass conservation equation and the momentum conservation equation. By solving these equations, the distribution of parameters such as velocity and pressure of the fluid in the flow field can be obtained.) The flow field space is a virtual space used to simulate the flow of fluids in the stirring space. It includes information such as the velocity field, pressure field, and temperature field of the fluid. When building a flow field space, many factors need to be considered, such as the properties of the fluid (density, viscosity, etc.), the rotation speed and mode of the stirring paddle, the inlet and outlet conditions of the fluid, etc. By setting appropriate boundary conditions and initial conditions, numerical calculation methods (such as finite element method, finite difference method, etc.) are used to solve the fluid mechanics equations to obtain the flow state of the fluid in the flow field space. Through the above steps, the flow field space was successfully built based on the built-in stirring space of the stirring device.

[0072] Set multiple step sizes. The step sizes are set to enable more accurate sampling and analysis in the flow field space. These step sizes can be determined based on specific needs and computing resources, and usually include different size levels to accommodate different accuracy requirements. Then, based on the constructed flow field space, use the set step sizes to determine the calibration flow field point cloud. Starting from the starting position of the flow field space, points are gradually selected in the space according to the size of the step sizes. These selected points form the calibration flow field point cloud, which is distributed at various locations in the flow field space for subsequent calibration and analysis of the flow field. In the process of determining the calibration flow field point cloud, factors such as the shape and size of the flow field space and the flow characteristics of the fluid need to be considered to ensure that the point cloud can fully cover the key areas of the flow field and accurately reflect the changes in the flow field.

[0073] Utilize sensor data from multiple sources, such as data obtained by velocity sensors, pressure sensors, temperature sensors, etc. Then, check each point of the flow field point cloud one by one in a certain order. For each point of the flow field point cloud, find the data at the same position in the corresponding multi-source sensor data. Then, fit these data at the same position. Through fitting, a relationship model between the data can be established to determine the real-time flow field state. Throughout the stirring process, the main goal is to ensure that the stirring effect meets expectations. In other words, as long as the stirring effect finally achieved can meet the expected requirements, some subtle parameter deviations that have little effect on the overall stirring effect can be ignored. Here, it is based on the state of the flow field to determine whether the stirring effect meets expectations. If the analysis of the real-time flow field finds that it does not meet expectations, the feedback control mechanism will be activated. For example, the speed of the stirring device, the angle of the stirring paddle, or the stirring time may be adjusted to make the stirring effect meet the expected requirements again. In general, this process aims to ensure the achievement of the stirring effect by real-time monitoring and analysis of flow field data, and to adjust and optimize when necessary.

[0074] For the determined real-time flow field, its various parameters are compared with the pre-set expected value range to determine whether there is a situation beyond the expected range. These parameters include flow rate, pressure, temperature, etc. When making an expected over-limit judgment, focus on the relevant parameters of the key mixing nodes. The key mixing node refers to the position in the mixing device that has an important impact on the flow field state and the mixing effect. For these key mixing nodes, real-time monitoring is carried out through sensors installed at the corresponding positions, and their sensor data is used as the basis for triggering management to avoid reactive monitoring and loss. If the parameters of the real-time flow field exceed the expected range, the feedback analysis mechanism will be triggered. The feedback analysis will deeply explore the reasons for the over-limit, such as improper setting of the operating parameters of the mixing device, external interference factors, or failure of the internal components of the device. Based on the results of the feedback analysis, formulate corresponding adjustment strategies and measures. For example, if it is an operating parameter problem, it is necessary to adjust the mixing speed, the angle of the mixing paddle, etc.; if it is an external interference, it is necessary to take measures to isolate or eliminate the interference source; if it is a component failure, it is necessary to repair or replace it. By using sensor trigger management at key mixing nodes and conducting expected over-limit judgment and feedback analysis on the real-time flow field, problems can be discovered and solved in a timely manner, ensuring the stability and efficiency of the mixing process.

[0075] In one possible implementation, step S700 includes:

[0076] Step S710: traverse the flow field space and randomly determine a first number of initial point clouds.

[0077] Step S720: Based on the multi-level step size levels, a first step size level is randomly determined, and the step size is expanded based on the initial point cloud to determine a second point cloud.

[0078] Step S730: performing point cloud iteration until a first number of iterations is met, integrating the initial point cloud, the second point cloud, and the Nth point cloud to determine the verification flow field point cloud.

[0079] Specifically, the flow field space is comprehensively scanned and inspected. During the traversal process, a first number of position points are randomly selected in the flow field space using a random algorithm or a random number generator. These randomly selected position points constitute the initial point cloud. It should be noted that the random selection must ensure a certain degree of randomness and uniformity so that the initial point cloud can be relatively evenly distributed in the flow field space, thereby providing a representative data basis for subsequent analysis and processing.

[0080] On the basis of setting multiple step sizes, one is randomly selected from these step sizes and defined as the first step size. Starting from the randomly determined initial point cloud, the selected first step size is used as the expansion distance basis to expand in all directions. For example, assuming that the coordinates of a point in the initial point cloud are (x, y, z), and the first step size is d, then with this point as the center, add or subtract d in the x, y, and z directions respectively to obtain new point coordinates, and these new points constitute the second point cloud. By expanding based on the initial point cloud and according to the randomly determined step size, the coverage of the point cloud can be further increased, providing richer data for subsequent analysis and processing.

[0081] Repeat the operation of determining new point clouds in the previous steps continuously, that is, perform the iterative process of the point cloud. Based on the point cloud obtained last time (which may be the initial point cloud or the point cloud generated by the previous iteration), randomly determine the step size level and expand the step size to obtain a new point cloud (such as the third point cloud, the fourth point cloud, etc.). This iterative process will continue until the preset number of first iterations is reached. When the iteration is completed, the initial point cloud that was randomly determined initially, as well as the second point cloud, the third point cloud obtained in each iteration... until the Nth point cloud are all integrated together. These integrated point clouds constitute the verification flow field point cloud, which is used for subsequent analysis, verification and related processing of the flow field of the stirring device.

[0082] Embodiment 2

[0083] Based on the same inventive concept as the aquatic product processing stirring method based on multi-data fusion in the aforementioned embodiment, Figure 2 As shown, the present application provides a water product processing stirring device based on multi-data fusion, and the device and method embodiments in the present application are based on the same inventive concept. Among them, the device includes:

[0084] The information reading module 10 is used to read the braking mechanism and basic stirring information of the stirring device, including stirring base materials and quality standards.

[0085] The fuzzy mixing process determination module 20 is used to retrieve and determine the multi-source mixing records, combine the braking mechanism with the basic mixing information, and determine the fuzzy mixing process, wherein the fuzzy mixing process includes multiple process stages.

[0086] The pre-control strategy determination module 30 is used to identify the fuzzy mixing process, perform process segmentation and parameter control decision-making based on static nonlinear control and dynamic linear control, and determine the pre-control strategy, which includes a mixing control function.

[0087] The intelligent controller configuration module 40 configures an intelligent controller based on the pre-control strategy, wherein the intelligent controller includes a linear block and a nonlinear block, wherein the linear block includes a cascade control unit, and wherein the cascade control unit includes a direct control inner loop and an indirect control outer loop.

[0088] The disturbance relationship determination module 50 is used to determine the stirring disturbance factors, perform single factor disturbance analysis and multi-factor coordinated disturbance analysis, and determine the disturbance relationship.

[0089] The digital feedback device establishment module 60 is used to combine the disturbance relationship and the correction mechanism to establish a digital feedback device, and the digital feedback device is used to perform self-calibration adjustment.

[0090] The full-cycle control module 70 performs main line control based on the intelligent controller, synchronously monitors and determines multi-source sensor data, and transmits the data back to the digital feedback device for multi-source data fitting and stirring flow field analysis feedback, so as to perform full-cycle control of aquatic product processing stirring, wherein the multi-source sensor data is obtained based on the monitoring of the multi-source sensor installed on the stirring device.

[0091] Furthermore, the fuzzy mixing process determination module 20 also includes:

[0092] The first process node determination unit is used to traverse the multi-source stirring record and determine a first process node, wherein the first process node is a dynamic control process or a static control process.

[0093] The first clustering result determining unit performs clustering processing on the mapping record part based on the first process node to determine a first clustering result.

[0094] The first fuzzy mixing process determining unit is used to traverse the first clustering results, determine the clustering results with the maximum number of clusters and perform fuzzy conversion, and determine the first fuzzy mixing process.

[0095] A confidence verification unit is used to combine the braking mechanism with the basic mixing information to perform confidence verification and adaptive adjustment on the first fuzzy mixing process.

[0096] Furthermore, the pre-control strategy determination module 30 also includes:

[0097] The stirring control function comprises: ,in, is the static nonlinear part, which is the direct parameter control type. is the dynamic linear part, Contains direct parameter control classes and linear relationships , ,in, For the Initial direct control of the process stage, is a constant, For the The phase progression of the process phases.

[0098] In combination with the stirring control function, the multiple process stages are traversed to perform positive process serialization integration and determine the pre-control strategy.

[0099] Furthermore, the intelligent controller configuration module 40 also includes:

[0100] Based on the pre-control strategy, based on Nonlinear block programmable settings based on The linear block is programmable.

[0101] The step of performing programmable setting of the linear block includes:

[0102] Based on the linear relationship , configure an indirect control outer loop, establish a connection between the direct control inner loop and the indirect control outer loop, and constitute the cascade control unit, wherein the indirect control outer loop is used to perform direct control constraints on the inner loop.

[0103] Based on the cascade control unit, the linear block is constructed.

[0104] Furthermore, the disturbance relationship determination module 50 further includes:

[0105] A stirring disturbance factor mining unit is used to read the historical control records of the stirring device, mine stirring disturbance factors, and the mining standard meets the preset frequency.

[0106] The first variable determination unit is used to determine the first variable for the stirring disturbance factor, perform stirring disturbance analysis based on the unit variable, and determine the single-factor disturbance relationship. The first variable is any one of the stirring disturbance factors.

[0107] The second variable determination unit is used to determine the second variable for the stirring disturbance factor, perform a stirring disturbance analysis of multiple variables in coordination, and determine the multi-factor coordinated disturbance relationship. The second variable is any at least two of the stirring disturbance factors.

[0108] A disturbance relationship determination unit, wherein the disturbance relationship determination unit is used to combine the single-factor disturbance relationship with the multi-factor collaborative disturbance relationship to determine the disturbance relationship.

[0109] Furthermore, the full-cycle control module 70 also includes:

[0110] A flow field space building module is used to build a flow field space based on the built-in stirring space of the stirring device.

[0111] A multi-step level setting module is used to set the multi-step level and determine the verification flow field point cloud based on the flow field space.

[0112] A real-time flow field determination unit is provided. The real-time flow field determination unit traverses the verification flow field point cloud based on the multi-source sensing data, performs same-position data fitting, and determines the real-time flow field.

[0113] A feedback analysis unit is used to perform expected over-limit judgment and feedback analysis on the real-time flow field, wherein sensor trigger management is performed at key stirring nodes.

[0114] Furthermore, the full-cycle control module 70 also includes:

[0115] An initial point cloud determining unit is used to traverse the flow field space and randomly determine a first number of initial point clouds.

[0116] The second point cloud determination unit randomly determines a first step size level based on the multi-step size levels, and performs step size expansion based on the initial point cloud to determine a second point cloud.

[0117] The point cloud iteration unit is used to perform point cloud iteration until a first number of iterations is met, and integrate the initial point cloud, the second point cloud, and the Nth point cloud to determine the verification flow field point cloud.

[0118] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0119] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0120] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. Aquatic product processing and stirring method based on multi-data fusion, characterized in that: The method comprises: Read the braking mechanism and basic mixing information of the mixing device, including mixing base and quality standards; Retrieve and determine multi-source mixing records, combine the braking mechanism with the basic mixing information, and determine a fuzzy mixing process, wherein the fuzzy mixing process includes multiple process stages; Identify the fuzzy mixing process, perform process segmentation and parameter control decision-making based on static nonlinear control and dynamic linear control, and determine a pre-control strategy, wherein the pre-control strategy includes a mixing control function; Based on the pre-control strategy, an intelligent controller is configured, wherein the intelligent controller includes a linear block and a nonlinear block, wherein the linear block includes a cascade control unit, and wherein the cascade control unit includes a direct control inner loop and an indirect control outer loop; Determine stirring disturbance factors, conduct single factor disturbance analysis and multi-factor coordinated disturbance analysis, and determine the disturbance relationship; Combining the disturbance relationship with the deviation correction mechanism, a digital feedback device is established, and the digital feedback device is used for self-calibration adjustment; Based on the intelligent controller, main line control is performed, multi-source sensor data is synchronously monitored and determined, and the data is sent back to the digital feedback device for multi-source data fitting and stirring flow field analysis feedback, so as to perform full-cycle control of aquatic product processing and stirring, wherein the multi-source sensor data is obtained based on monitoring of the multi-source sensor installed on the stirring device; The fuzzy mixing process is determined, and the fuzzy mixing process includes multiple process stages, including: Traversing the multi-source stirring records, determining a first process node, wherein the first process node is a dynamic control process or a static control process; Based on the first process node, clustering processing is performed on the mapping record part to determine a first clustering result; Traversing the first clustering results, determining the clustering result with the largest number of clusters and performing fuzzy conversion, and determining a first fuzzy mixing process; Combining the braking mechanism with the basic mixing information, performing confidence verification and adaptive adjustment on the first fuzzy mixing process; Wherein, the pre-control strategy includes a stirring control function, including: The stirring control function comprises: ,in, is the static nonlinear part, which is the direct parameter control type. is the dynamic linear part, Contains direct parameter control classes and linear relationships , ,in, For the Initial direct control of the process stage, is a constant, For the The stage progression of the process phases; In combination with the stirring control function, the multiple process stages are traversed to perform positive process serialization integration and determine the pre-control strategy.

2. The method according to claim 1, characterized in that Configuring an intelligent controller based on the pre-control strategy includes: Based on the pre-control strategy, based on Nonlinear block programmable settings based on Performing programmable setting of the linear block; The step of performing programmable setting of the linear block includes: Based on the linear relationship , configuring an indirect control outer loop, establishing a connection between the direct control inner loop and the indirect control outer loop, and forming the cascade control unit, wherein the indirect control outer loop is used to perform direct control constraints on the inner loop; Based on the cascade control unit, the linear block is constructed.

3. The method according to claim 1, characterized in that The single factor disturbance analysis and multi-factor coordinated disturbance analysis include: Read the historical control records of the stirring device, dig out the stirring disturbance factors, and dig out the standard to meet the preset frequency; For the stirring disturbance factor, determine a first variable, perform stirring disturbance analysis based on a unit variable, and determine a single factor disturbance relationship, wherein the first variable is any one of the stirring disturbance factors; For the stirring disturbance factor, determine a second variable, perform a stirring disturbance analysis of multi-factor variables in coordination, and determine a multi-factor coordinated disturbance relationship, wherein the second variable is any at least two factors of the stirring disturbance factor; The single-factor disturbance relationship and the multi-factor coordinated disturbance relationship are combined to determine the disturbance relationship.

4. The method according to claim 1, characterized in that Conduct multi-source data fitting feedback, including: Taking the built-in stirring space of the stirring device as a reference, constructing the flow field space; Setting multiple step sizes, and determining a verification flow field point cloud based on the flow field space; Based on the multi-source sensor data, traverse the verification flow field point cloud, perform same-position data fitting, and determine the real-time flow field; The real-time flow field is subjected to expected over-limit judgment and feedback analysis, wherein sensor trigger management is performed at key stirring nodes.

5. The method according to claim 4, characterized in that The step of setting multiple step sizes and determining the verification flow field point cloud based on the flow field space includes: Traversing the flow field space, and randomly determining a first number of initial point clouds; Based on the multi-level step size levels, randomly determine a first step size level, and perform step size expansion based on the initial point cloud to determine a second point cloud; The point cloud iteration is performed until a first number of iterations is met, and the initial point cloud and the second point cloud are integrated until the Nth point cloud to determine the verification flow field point cloud.

6. Aquatic product processing stirring device based on multi-data fusion, characterized in that: The device is used to implement the method according to any one of claims 1 to 5, and the device comprises: An information reading module, the information reading module is used to read the braking mechanism and basic stirring information of the stirring device, including stirring base materials and quality standards; A fuzzy mixing process determination module, the fuzzy mixing process determination module is used to retrieve and determine multi-source mixing records, combine the braking mechanism with the basic mixing information, and determine the fuzzy mixing process, the fuzzy mixing process includes multiple process stages; A pre-control strategy determination module, the pre-control strategy determination module is used to identify the fuzzy mixing process, perform process segmentation and parameter control decision-making based on static nonlinear control and dynamic linear control, and determine the pre-control strategy, the pre-control strategy includes a mixing control function; An intelligent controller configuration module, wherein the intelligent controller configuration module configures an intelligent controller based on the pre-control strategy, wherein the intelligent controller includes a linear block and a nonlinear block, wherein the linear block includes a cascade control unit, and wherein the cascade control unit includes a direct control inner loop and an indirect control outer loop; A disturbance relationship determination module, which is used to determine stirring disturbance factors, perform single-factor disturbance analysis and multi-factor coordinated disturbance analysis, and determine disturbance relationships; A digital feedback device establishment module, the digital feedback device establishment module is used to combine the disturbance relationship and the correction mechanism to establish a digital feedback device, and the digital feedback device is used to perform self-calibration adjustment; A full-cycle control module performs main line control based on the intelligent controller, synchronously monitors and determines multi-source sensor data, and transmits the data back to the digital feedback device for multi-source data fitting and stirring flow field analysis feedback, so as to perform full-cycle control of aquatic product processing stirring, wherein the multi-source sensor data is obtained based on monitoring of the multi-source sensors installed on the stirring device.