A product quality risk management and control method and system based on inspection detection data

Abstract

The application discloses a product quality risk management and control method and system based on inspection detection data, and relates to the technical field of product quality risk management and control. The product quality risk management and control method based on inspection detection data comprises the following steps: preprocessing risk management and control efficiency analysis, pre-marinating risk management and control efficiency analysis, and main marinating risk management and control efficiency analysis. The application performs preprocessing efficiency analysis on preprocessing detection data to determine whether to perform fluid flow optimization, then performs pre-marinating efficiency analysis on pre-marinating detection data to determine whether to perform filter matching coefficient optimization, and finally performs main marinating efficiency analysis on kneading and rolling machine motor load to determine whether to perform kneading and rolling machine load optimization, so that the accuracy of microbial contamination risk management and control in the preparation process of luncheon meat canner raw and auxiliary materials is improved, and the problem of low accuracy of microbial contamination risk management and control in the preparation process of luncheon meat canner raw and auxiliary materials in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of product quality risk management technology, and in particular to a product quality risk management method and system based on inspection and testing data. Background Technology

[0002] During the production process, enterprises collect a large amount of data through various inspection and testing methods. Traditional data processing methods are difficult to effectively handle such massive and complex data and cannot fully extract the information contained in the data. In addition, traditional quality management methods often focus on the inspection of the final product while neglecting the monitoring and risk control of the production process. They rely on manual experience judgment and simple statistical analysis methods for product quality risk control, making it difficult for enterprises to accurately assess product quality risks. In order to achieve refined and scientific quality management, innovative methods based on inspection and testing data have emerged, and a digital quality control system for the product production process has been built.

[0003] In existing technologies, by recording and managing various data in the production process, and using algorithms such as data mining and machine learning, potential risk patterns and rules can be discovered from a large amount of data. By detecting and analyzing various performance indicators of products, potential problems in products can be identified in a timely manner. Enterprises can achieve accurate prediction and control of product quality risks by establishing an information management system.

[0004] For example, the invention patent announcement CN118485309B, concerning a method and system for processing dairy product quality data based on traceability information, includes: acquiring traceability information and sensor information from multiple stages corresponding to the target dairy product; identifying predicted risk stages with quality risks based on traceability information using a neural network algorithm; selecting high-risk stages and their corresponding risk types from all predicted risk stages based on sensor information and a preset information verification algorithm; and generating monitoring instructions for the high-risk stages and sending them to the corresponding devices based on the high-risk stages and their corresponding risk types.

[0005] For example, the invention patent announcement CN114240386B, concerning a risk point management system and method based on quality control, includes: a central processor, a data acquisition terminal, an interface terminal, and a database. The central processor includes processing strategies and verification strategies for checking the processing process. The data acquisition terminal is used to collect actual processing measures and actual evidence, as well as to allow users to input optimized control measures and optimized control evidence to update the initial countermeasures. The interface terminal is used to interface with an ERP system to obtain inbound and outbound data of products and raw materials from the ERP system to form the first change point. The database is used to store the initial countermeasures and historical data of risk points.

[0006] However, in the process of implementing the inventive technical solution in the embodiments of this application, it was found that the above-mentioned technology has at least the following technical problems:

[0007] In existing technologies, most existing systems are based on correlation analysis, which performs simple statistical analysis on the relationship between detection indicators and risks. However, they lack the ability to explore complex relationships, such as processing time, temperature, and additive concentration. The synergistic or antagonistic effects between these parameters affect product quality, leading to inaccurate risk assessment results. Consequently, they cannot fully reflect the microbial contamination risk status of the entire production process, resulting in low reliability of microbial contamination risk control during the preparation of luncheon meat canned raw materials and finished products. Summary of the Invention

[0008] This application provides a product quality risk management method and system based on inspection and testing data, which solves the problem of low reliability of microbial contamination risk management in the preparation of luncheon meat canned raw materials and finished products in the prior art, and improves the reliability of microbial contamination risk management in the preparation of luncheon meat canned raw materials and finished products.

[0009] This application provides a product quality risk control method based on inspection and testing data, including the following steps: Step 1, based on the acquired pretreatment test data, perform a pretreatment efficiency analysis on the microbial contamination risk control process of a specified batch of raw and auxiliary materials, obtain the pretreatment efficiency analysis results, and simultaneously determine whether to optimize the fluid flow rate based on the pretreatment efficiency analysis results. The pretreatment efficiency analysis is used to measure the microbial contamination risk control efficiency of the specified batch of raw and auxiliary materials during the pretreatment process. Fluid flow rate optimization means improving the microbial contamination risk control efficiency during the pretreatment process by adjusting the centrifugal pump speed; Step 2, if the pretreatment is determined to be qualified, perform a pre-curing efficiency analysis on the microbial contamination risk control process of the raw and auxiliary material samples based on the acquired pre-curing test data, obtain the pre-curing efficiency analysis results, and simultaneously determine whether to optimize the fluid flow rate based on the pre-curing efficiency analysis results. If the pre-marinating efficiency analysis is used to measure the efficiency of microbial contamination risk control of raw and auxiliary material samples during the pre-marinating process, the filter matching coefficient optimization means improving the efficiency of microbial contamination risk control during the pre-marinating process by adjusting the fan air volume and fan air pressure. Step 3: If the pre-marinating is deemed qualified, the main marinating efficiency analysis is performed on the microbial contamination risk control process of the raw and auxiliary material semi-finished products based on the obtained tumbling machine motor load. The main marinating efficiency analysis results are obtained, and the tumbling machine load optimization is determined based on the main marinating efficiency analysis results. The main marinating efficiency analysis is used to measure the efficiency of microbial contamination risk control of raw and auxiliary material semi-finished products during the main marinating process. The tumbling machine load optimization means improving the efficiency of microbial contamination risk control during the main marinating process by adjusting the tumbling shaft pressure and tumbling interval duration.

[0010] This application provides a system for applying a product quality risk control method based on inspection and testing data, including: a pretreatment efficiency analysis module, a pre-curing efficiency analysis module, and a main curing efficiency analysis module; wherein, the pretreatment efficiency analysis module is used to perform pretreatment efficiency analysis on the microbial contamination risk control process of a specified batch of raw and auxiliary materials based on the acquired pretreatment testing data, obtain the pretreatment efficiency analysis result, and determine whether to optimize the fluid flow rate based on the pretreatment efficiency analysis result; the pre-curing efficiency analysis module is used to perform pre-curing efficiency analysis on the microbial contamination risk control process of raw and auxiliary material samples based on the acquired pre-curing testing data if the pretreatment is deemed qualified, obtain the pre-curing efficiency analysis result, and determine whether to optimize the filter matching coefficient based on the pre-curing efficiency analysis result; the main curing efficiency analysis module is used to perform main curing efficiency analysis on the microbial contamination risk control process of semi-finished raw and auxiliary materials based on the acquired tumbler motor load if the pre-curing is deemed qualified, obtain the main curing efficiency analysis result, and determine whether to optimize the tumbler load based on the main curing efficiency analysis result.

[0011] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0012] 1. By analyzing the pre-processing efficiency through pre-processing detection data to determine whether fluid flow optimization is needed, and then by analyzing the pre-marinating efficiency through pre-marinating detection data to determine whether filter matching coefficient optimization is needed, and finally by analyzing the main marinating efficiency through the tumbler motor load to determine whether tumbler load optimization is needed, the accuracy of microbial contamination risk control in the preparation of luncheon meat canning raw materials is improved, solving the problem of low accuracy in microbial contamination risk control in the preparation of luncheon meat canning raw materials in existing technologies.

[0013] 2. By processing the obtained sample conveying shear force change amount, the conveying shear force change amount coefficient is obtained. At the same time, the obtained conveying shear force change amount coefficient, screw propeller speed change amount coefficient and cutting machine blade spacing change amount coefficient are inversely proportionally processed and coupled to obtain the pretreatment control efficiency index. This improves the accuracy of obtaining the pretreatment control efficiency index, thereby improving the stability of the pretreatment quality and the continuity of production of a specified batch of raw and auxiliary materials.

[0014] 3. By processing the vacuum pump pumping rate of the obtained raw and auxiliary material samples, the vacuum pump pumping rate coefficient is obtained. At the same time, the obtained vacuum pump pumping rate coefficient, the stirring frequency coefficient of the vacuum marinating tank, and the pH value coefficient of the marinating liquid are coupled and processed to obtain the pre-marinating control efficiency index. This improves the accuracy of obtaining the pre-marinating control efficiency index, thereby improving the uniformity and efficiency of the marinating process. Attached Figure Description

[0015] Figure 1 A flowchart illustrating a product quality risk management method based on inspection and testing data, provided as an embodiment of this application;

[0016] Figure 2 A logical framework diagram of a product quality risk management method based on inspection and testing data provided in this application embodiment;

[0017] Figure 3 A flowchart for preprocessing efficiency analysis and determination provided in the embodiments of this application;

[0018] Figure 4 A flowchart for the analysis and determination of pre-marinating efficiency provided in the embodiments of this application;

[0019] Figure 5 The flowchart for the main pickling efficiency analysis and determination provided in the embodiments of this application;

[0020] Figure 6 This is a schematic diagram of a product quality risk management system based on inspection and testing data, provided as an embodiment of this application. Detailed Implementation

[0021] This application provides a product quality risk control method and system based on inspection and testing data, solving the problem of low reliability in the control of microbial contamination risk during the preparation of luncheon meat canned raw materials and finished products in the prior art. By using acquired pretreatment testing data, the method analyzes the pretreatment efficiency of the microbial contamination risk control process for a specified batch of raw materials and obtains the pretreatment efficiency analysis results. Based on the pretreatment efficiency analysis results, it determines whether to optimize the fluid flow rate. If the pretreatment is deemed qualified, it then analyzes the pre-marinating efficiency of the raw material samples based on acquired pre-marinating testing data, obtaining the pre-marinating efficiency analysis results. Based on the pre-marinating efficiency analysis results, it determines whether to optimize the filter matching coefficient. If the pre-marinating is deemed qualified, it then analyzes the main marinating efficiency of the semi-finished raw material products based on acquired tumbler motor load, obtaining the main marinating efficiency analysis results. Based on the main marinating efficiency analysis results, it determines whether to optimize the tumbler load. This improves the accuracy of microbial contamination risk control during the preparation of luncheon meat canned raw materials and solves the problem of low accuracy in the control of microbial contamination risk during the preparation of luncheon meat canned raw materials in the prior art.

[0022] The technical solution in this application aims to address the problem of low accuracy in controlling the risk of microbial contamination during the preparation of raw and auxiliary materials for canned luncheon meat. The overall approach is as follows:

[0023] By analyzing the pre-processing efficiency using pre-processing detection data to determine whether fluid flow optimization is needed, and then analyzing the pre-marinating efficiency using pre-marinating detection data to determine whether filter matching coefficient optimization is needed, and finally analyzing the main marinating efficiency using the tumbler motor load to determine whether tumbler load optimization is needed, the accuracy of microbial contamination risk control during the preparation of luncheon meat canned raw materials is improved.

[0024] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0025] like Figure 1 The diagram shows a flowchart of a product quality risk control method based on inspection and testing data provided in this application embodiment. The method includes the following steps: Step 1: Based on the acquired pretreatment testing data, perform a pretreatment efficiency analysis on the microbial contamination risk control process of a specified batch of raw and auxiliary materials to obtain the pretreatment efficiency analysis results. Simultaneously, based on the pretreatment efficiency analysis results, determine whether to optimize the fluid flow rate. The pretreatment efficiency analysis is used to measure the microbial contamination risk control efficiency of the specified batch of raw and auxiliary materials during the pretreatment process. Fluid flow rate optimization refers to improving the microbial contamination risk control efficiency during the pretreatment process by adjusting the centrifugal pump speed. Step 2: If the pretreatment is deemed qualified, perform a pre-curing efficiency analysis on the microbial contamination risk control process of the raw and auxiliary material samples based on the acquired pre-curing testing data to obtain the pre-curing efficiency analysis results. The pre-marinating efficiency analysis results are used to determine whether filter matching coefficient optimization is needed. The pre-marinating efficiency analysis is used to measure the efficiency of microbial contamination risk control of raw and auxiliary material samples during the pre-marinating process. Filter matching coefficient optimization means adjusting the fan air volume and fan pressure to improve the efficiency of microbial contamination risk control during the pre-marinating process. Step 3: If the pre-marinating is deemed qualified, the main marinating efficiency analysis is performed on the microbial contamination risk control process of the raw and auxiliary material semi-finished products based on the obtained tumbling machine motor load. The main marinating efficiency analysis results are used to determine whether tumbling machine load optimization is needed. The main marinating efficiency analysis is used to measure the efficiency of microbial contamination risk control of raw and auxiliary material semi-finished products during the main marinating process. Tumbling machine load optimization means adjusting the tumbling shaft pressure and tumbling interval time to improve the efficiency of microbial contamination risk control during the main marinating process.

[0026] The pretreatment detection data includes changes in conveying shear force, changes in screw propeller speed, and changes in the blade spacing of the cutting machine. The change in conveying shear force represents the absolute value of the difference between the actual conveying shear force of a specified batch of raw and auxiliary materials at the end of the pretreatment risk control period and the initial conveying shear force at the beginning of the pretreatment risk control period. The change in screw propeller speed represents the absolute value of the difference between the actual screw propeller speed of a specified batch of raw and auxiliary materials at the end of the pretreatment risk control period and the initial screw propeller speed at the beginning of the pretreatment risk control period. The change in the blade spacing of the cutting machine represents the absolute value of the difference between the actual blade spacing of a specified batch of raw and auxiliary materials at the end of the pretreatment risk control period and the initial blade spacing of the cutting machine at the beginning of the pretreatment risk control period.

[0027] The pre-marinating test data includes the vacuum pump extraction rate, the stirring frequency of the vacuum marinating tank, and the pH value of the marinating solution. The vacuum pump extraction rate is used to quantify the extraction speed of the vacuum pump for the raw and auxiliary material samples during the pre-marinating risk control period. The stirring frequency of the vacuum marinating tank indicates the operating frequency of the stirring paddle for the raw and auxiliary material samples during the pre-marinating risk control period. The pH value of the marinating solution is used to quantify the change in hydrogen ion concentration in the marinating solution for the raw and auxiliary material samples during the pre-marinating risk control period. The tumbling machine motor load indicates the actual working load borne by the tumbling machine motor during the operation of the tumbling machine for the raw and auxiliary material semi-finished products during the main marinating risk control period.

[0028] In this embodiment, the change in shear force is measured by a pressure sensor, the change in screw propeller speed is measured by a speed sensor, the change in blade spacing of the dicing machine is measured by a laser rangefinder, the vacuum pump pumping rate is measured by a gas flow meter, the stirring frequency of the vacuum marinating tank is read by the frequency converter built into the marinating tank stirring control system, the pH value of the marinating liquid is monitored in real time by a pH electrode and a pH transmitter, and the load of the tumbler motor is monitored by a power transmitter.

[0029] like Figure 2The diagram shown is a logical framework diagram of a product quality risk control method based on inspection and testing data provided in this application embodiment. The specific design logic is as follows: Based on the acquired pretreatment testing data, a pretreatment efficiency analysis is performed on the microbial contamination risk control process of a specified batch of raw and auxiliary materials, generating a pretreatment efficiency analysis result. Based on the pretreatment efficiency analysis result, it is determined whether fluid flow optimization is needed. If the pretreatment is unqualified, a corresponding optimization process is triggered. After the pretreatment is qualified, the pre-marinating risk control efficiency analysis is activated. Based on the acquired pre-marinating testing data, the microbial contamination risk of the raw and auxiliary material samples is assessed. The risk control process involves pre-marinating efficiency analysis, generating pre-marinating efficiency analysis results. Based on these results, it is determined whether filter matching coefficient optimization is needed. If pre-marinating fails, a corresponding optimization process is triggered. Once pre-marinating is successful, the main marinating risk control efficiency analysis is activated. Based on the acquired tumbler motor load data, the main marinating efficiency analysis is performed on the microbial contamination risk control process of raw materials and semi-finished products, generating main marinating efficiency analysis results. Based on these results, it is determined whether tumbler load optimization is needed. If main marinating fails, a corresponding optimization process is triggered.

[0030] like Figure 3 The diagram shown is a flowchart of the pretreatment efficiency analysis and judgment process provided in this application embodiment. The specific design logic is as follows: The process begins by acquiring pretreatment detection data and performing pretreatment efficiency analysis on a specified batch of raw and auxiliary materials during the pretreatment risk control period based on the acquired pretreatment detection data. Based on the pretreatment efficiency analysis results, it is determined whether to optimize the fluid flow rate. If so, the centrifugal pump speed is adjusted; otherwise, pre-marinating detection data is acquired.

[0031] This example is data-driven, precisely capturing key parameters such as fluid flow rate, filter matching coefficient, and tumbler load for different risk control periods in raw material pretreatment, pre-marinating, and main marinating. Efficiency analysis is performed using data from each stage to achieve phased and precise risk identification and targeted optimization. By dynamically optimizing production parameters, the production process in the three key stages of pretreatment, pre-marinating, and main marinating is ensured to be more efficient and stable, avoiding resource waste caused by extensive control throughout the entire process. This improves production efficiency and product quality stability, while reducing energy consumption and equipment wear and tear, significantly enhancing the refined management and intelligent decision-making capabilities of the production process.

[0032] Furthermore, based on the obtained sample pretreatment and testing data, the pretreatment efficiency of the microbial contamination risk control process for a specified batch of raw and auxiliary materials is analyzed. The specific process is as follows:

[0033] First, at the end of the pretreatment risk control period, the obtained sample transport shear force change is compared with the preset transport shear force change in the database, and the difference between the two is calculated. Simultaneously, a correction process is performed using the transport shear force change calibration factor to obtain the transport shear force change coefficient. The specific constraint expression for the transport shear force change coefficient DPS1 is as follows: In the formula, DPS1 represents the coefficient of conveying shear force change corresponding to the end of the pretreatment risk control period for a specified batch of raw and auxiliary materials, α1 represents the calibration factor of conveying shear force change, F1 represents the conveying shear force change corresponding to the end of the pretreatment risk control period for a specified batch of raw and auxiliary materials, and F10 represents the preset conveying shear force change. The preset conveying shear force change is represented by summing the historical conveying shear force changes corresponding to the end of the historical pretreatment risk control period and then calculating their average value.

[0034] Then, the obtained propeller speed change is compared with the preset propeller speed change in the database, the difference between the two is calculated, and a correction is performed using a propeller speed change calibration factor to obtain the propeller speed change coefficient. The specific constraint expression for the propeller speed change coefficient DPS2 is as follows: In the formula, DPS2 represents the screw propeller speed change coefficient corresponding to the end of the pretreatment risk control period for a specified batch of raw and auxiliary materials, α2 represents the screw propeller speed change calibration factor, F2 represents the screw propeller speed change corresponding to the end of the pretreatment risk control period for a specified batch of raw and auxiliary materials, and F20 represents the preset screw propeller speed change. The preset screw propeller speed change is obtained by summing the historical screw propeller speed changes corresponding to the end of the historical pretreatment risk control period and then calculating their average value.

[0035] Next, the obtained change in the blade spacing of the block cutter is compared with the preset change in the blade spacing of the block cutter in the database, and the difference between the two is calculated. At the same time, the change in the blade spacing is corrected by the calibration factor of the change in the blade spacing of the block cutter, and the change coefficient of the blade spacing of the block cutter is obtained. The specific constraint expression of the change coefficient of the blade spacing of the block cutter, DPS3, is as follows: In the formula, DPS3 represents the coefficient of change in the blade spacing of the cutting machine corresponding to the end of the pretreatment risk control period for a specified batch of raw and auxiliary materials, α3 represents the calibration factor of the change in the blade spacing of the cutting machine, F3 represents the change in the blade spacing of the cutting machine corresponding to the end of the pretreatment risk control period for a specified batch of raw and auxiliary materials, and F30 represents the preset change in the blade spacing of the cutting machine. The preset change in the blade spacing of the cutting machine is represented by summing the historical changes in the blade spacing of the cutting machine corresponding to the end of the historical pretreatment risk control period and then calculating its average value.

[0036] Finally, the obtained coefficients for changes in conveying shear force, screw propeller speed, and cutter blade spacing are processed by inverse proportional calculation. The results of this inverse proportional calculation are then coupled to obtain the pretreatment control efficiency index. This index reflects the effectiveness of pretreatment detection data in controlling microbial contamination risk during the pretreatment risk control period. The specific constraint expression for the pretreatment control efficiency index (DPS) is as follows: In the formula, DPS represents the pre-processing control efficiency index at the end of the pre-processing risk control period. The inverse proportional treatment here refers to performing mathematical operations on the coefficients of change of conveying shear force, change of screw propeller speed, and change of cutter blade spacing to achieve the effect that the adjusted variables are inversely proportional to the pre-processing control efficiency index.

[0037] In this example, the calibration factors for changes in conveyor shear force, propeller speed, and cutter blade spacing are pre-defined in the database, representing the degree of impact of these changes on the risk management of a specified batch of raw and auxiliary materials during pretreatment. The database pre-stores preset calibration factors closely related to the pretreatment management efficiency index. These calibration factors, along with the changes in conveyor shear force, propeller speed, and cutter blade spacing, are mapped using clear rules based on business needs and system characteristics. This mapping can be a one-to-one correspondence between a single parameter and a calibration factor, or a combination of multiple parameters corresponding to a single calibration factor. For example, during pretreatment efficiency analysis, the system can collect real-time values ​​of the changes in conveyor shear force, propeller speed, and cutter blade spacing, and call the preset mapping rules to accurately match and extract the corresponding calibration factors.

[0038] Most importantly, to ensure the consistency of the evaluation process and the comparability of the evaluation results, this example limits the values ​​of the calibration factors for the changes in conveyor shear force, the changes in propeller speed, and the changes in the spacing between the dicing machine blades to between 0 and 1, and the sum of the three is always equal to 1.

[0039] In this embodiment, the pre-processing control efficiency index decreases as the changes in conveying shear force, screw propeller speed, and cutter blade spacing increase. Specifically, when the screw propeller speed increases, the corresponding change in screw propeller speed also increases, the raw meat moves faster within the equipment, and its relative motion with the water flow becomes more intense, leading to an increase in the force exerted by the water flow on the raw meat and an increase in the change in conveying shear force. When the change in conveying shear force increases, the pre-cutting and loosening of the raw meat is strengthened, making the structure of the raw meat more uniform. At this time, the change in cutter blade spacing increases to adapt to the state of the raw meat. When the change in cutter blade spacing increases, the resistance experienced by the raw meat during the cutting process increases, and the change in screw propeller speed also increases.

[0040] This example considers the interrelationships between changes in conveyor shear force, propeller speed, and blade spacing of the dicing machine, and performs inverse proportional and coupling calculations. By taking into account the complexity of the production process and avoiding one-sided conclusions caused by single-parameter analysis, it accurately identifies key risk drivers by quantifying the correlation between parameters. This helps to enhance the predictability of risk management and effectively solves the problem of low accuracy in the risk management of microbial contamination during the preparation of raw materials for luncheon meat canning in existing technologies.

[0041] Furthermore, based on the pretreatment efficiency analysis results, it is determined whether to optimize the fluid flow rate. The specific process is as follows: Determine the numerical relationship between the obtained pretreatment control efficiency index and the preset pretreatment control efficiency index: If the obtained pretreatment control efficiency index is not less than the preset pretreatment control efficiency index, the pretreatment efficiency analysis result is recorded as qualified, and raw material samples (i.e., the specified batch of raw materials corresponding to qualified pretreatment) are obtained and pre-marinating efficiency analysis is performed; If the obtained pretreatment control efficiency index is less than the preset pretreatment control efficiency index, the pretreatment efficiency analysis result is recorded as unqualified, and fluid flow rate optimization is performed.

[0042] In this process, fluid flow optimization involves using the sum of the obtained pretreatment control efficiency index deviation and the fluid flow coefficient deviation as the centrifugal pump speed adjustment amount to dynamically adjust the centrifugal pump's displacement. The pretreatment control efficiency index deviation measures the difference between the obtained pretreatment control efficiency index and the preset pretreatment control efficiency index in the database; that is, the difference between the obtained pretreatment control efficiency index and the preset pretreatment control efficiency index. The fluid flow coefficient deviation represents the absolute value of the difference between the fluid flow coefficient of the specified batch of raw materials and auxiliary materials in the pipeline corresponding to the specified batch of raw materials and auxiliary materials at the end of the pretreatment risk control period and the preset fluid flow coefficient. After each fluid flow optimization, the pretreatment control efficiency index is re-obtained, and the obtained... If the increase in the pretreatment control efficiency index is not less than the set increase in the pretreatment control efficiency index, it indicates that the fluid flow optimization is effective and a pre-curing efficiency analysis is performed. Otherwise, the system prompts the personnel to adjust the ambient humidity by the set range. The increase in the pretreatment control efficiency index represents the difference between the pretreatment control efficiency index obtained after a fluid flow optimization and the pretreatment control efficiency index obtained before the fluid flow optimization. The set increase in the pretreatment control efficiency index is represented by the sum of the historical increases in the pretreatment control efficiency index after the historical fluid flow optimization in the database. The set range represents the result obtained by mapping the sum of the deviation of the pretreatment control efficiency index and the deviation of the ambient humidity in the database.

[0043] In this embodiment, the fluid flow coefficient represents the ratio of the absolute value of the difference between the fluid flow rate of the specified batch of raw and auxiliary materials in the pipeline at the end of the pretreatment risk control period and the preset fluid flow rate to the preset fluid flow rate. The PID (Proportional-Integral-Derivative) control algorithm in the raw and auxiliary material pipeline controller takes the calculated centrifugal pump speed adjustment as input and dynamically adjusts the centrifugal pump speed through the synergistic action of proportional, integral, and derivative steps to improve the stability of fluid flow rate. The preset pre-curing control efficiency index is represented by the sum and average of the pretreatment control efficiency indices of the specified batch of raw and auxiliary materials in the database at the end of the pretreatment risk control period. The preset fluid flow rate is represented by the sum and average of the fluid flow rates of the specified batch of raw and auxiliary materials in the database at the end of the pretreatment risk control period.

[0044] This example monitors the deviation between the current state and the target state in real time by calculating the deviation of the pretreatment control efficiency index and the fluid flow coefficient. It dynamically adjusts the centrifugal pump speed. This fluid flow optimization setting uses dynamic closed-loop adjustment and a multi-dimensional risk linkage mechanism to accurately adjust the centrifugal pump discharge through dual dynamic feedback of the pretreatment control efficiency index deviation and the fluid flow coefficient deviation. If the increase in efficiency index deviation after optimization meets the standard, it can directly enter the risk relay control of the pre-marinating stage to ensure that the risk of microbial contamination continues to decrease as the process progresses. If it does not meet the standard, it will link the adjustment of environmental humidity. Through the deviation mapping mechanism, the abstract risk signal is transformed into a specific environmental parameter adjustment command, avoiding risk retention caused by the failure of optimization in a single link, ensuring that the fluid flow is stable at the preset value, avoiding low flow rate or local stagnation, and reducing the chance of microbial growth.

[0045] like Figure 4 The diagram shown is a flowchart of the pre-marinating efficiency analysis and judgment provided in the embodiment of this application. The specific design logic is as follows: The process begins by acquiring pre-marinating test data and performing pre-marinating efficiency analysis on raw and auxiliary material samples during the pre-marinating risk control period based on the acquired pre-marinating test data. Based on the pre-marinating efficiency analysis results, it is determined whether to optimize the filter matching coefficient. If so, the fan air volume and fan air pressure are adjusted; otherwise, the tumbling machine motor load is acquired.

[0046] Furthermore, based on the acquired pre-curing test data, the pre-curing efficiency of the microbial contamination risk control process for raw material samples was analyzed. The specific process is as follows:

[0047] First, at the end of the pre-marinating risk control period, the vacuum pump evacuation rate of the obtained raw material samples is compared with the preset vacuum pump evacuation rate in the database, and the difference between the two is calculated (i.e., Simultaneously, a correction process is performed using the vacuum pump pumping rate calibration factor to obtain the vacuum pump pumping rate coefficient. The specific limiting expression for the vacuum pump pumping rate coefficient PMI1 is: PMI1 = In the formula, PMI1 represents the vacuum pumping coefficient of the raw material sample at the end of the pre-marinating risk control period, β1 represents the vacuum pumping rate calibration factor, P1 represents the vacuum pumping rate of the raw material sample at the end of the pre-marinating risk control period, and P10 represents the preset vacuum pumping rate. The preset vacuum pumping rate is obtained by summing the historical vacuum pumping rates corresponding to the end of the historical pre-marinating risk control period and then calculating their average value.

[0048] Then, the stirring frequency of the vacuum marinating tank of the obtained raw and auxiliary material samples was compared with the preset stirring frequency of the vacuum marinating tank in the database, and the difference between the two was calculated (i.e., Simultaneously, a correction process is performed using the vacuum marinating tank stirring frequency calibration factor to obtain the vacuum marinating tank stirring frequency coefficient. The specific constraint expression for the vacuum marinating tank stirring frequency coefficient PMI2 is as follows: In the formula, PMI2 represents the stirring frequency coefficient of the vacuum marinating tank corresponding to the end of the pre-marinating risk control period for the raw and auxiliary material samples, β2 represents the calibration factor of the stirring frequency of the vacuum marinating tank, P2 represents the stirring frequency of the vacuum marinating tank corresponding to the end of the pre-marinating risk control period for the raw and auxiliary material samples, and P20 represents the preset stirring frequency of the vacuum marinating tank. The preset stirring frequency of the vacuum marinating tank is obtained by summing the stirring frequencies of each historical vacuum marinating tank corresponding to the end of the historical pre-marinating risk control period and then calculating its average value.

[0049] Next, the pH value of the obtained raw material sample pickling solution is compared with the preset pH value of the pickling solution in the database, and the difference between the two is calculated (i.e., Simultaneously, the pH value of the pickling solution is corrected by combining the pH calibration factor, resulting in the pH coefficient of the pickling solution. The specific constraint expression for the pH coefficient PMI3 is as follows: In the formula, PMI3 represents the pH value coefficient of the pickling solution corresponding to the end of the pre-pickled risk control period of the raw and auxiliary material sample, β3 represents the pH value calibration factor of the pickling solution, P3 represents the pH value of the pickling solution corresponding to the end of the pre-pickled risk control period of the raw and auxiliary material sample, and P30 represents the preset pH value of the pickling solution. The preset pH value of the pickling solution is obtained by summing the pH values ​​of each historical pickling solution corresponding to the end of the historical pre-pickled risk control period and then calculating its average value.

[0050] Finally, the obtained vacuum pump pumping rate coefficient, vacuum pickling tank stirring frequency coefficient, and pickling liquid pH coefficient are coupled and processed to obtain the pre-pickled control efficiency index. The pre-pickled control efficiency index is used to reflect the effect of pre-pickled detection data on the control of microbial contamination risk during the pre-pickled risk control period. The specific limiting expression of the pre-pickled control efficiency index (PMI) is as follows: In the formula, PMI represents the pre-marinating control efficiency index corresponding to the end of the pre-marinating risk control period for raw and auxiliary material samples.

[0051] In this example, the vacuum pump extraction rate calibration factor, the vacuum marinating tank stirring frequency calibration factor, and the marinating solution pH value calibration factor represent the pre-set impacts of these parameters on the risk management of pre-marinating raw material samples. The database pre-stores preset calibration factors closely related to the pre-marinating control efficiency index. These calibration factors, along with the vacuum pump extraction rate, vacuum marinating tank stirring frequency, and marinating solution pH value, are mapped using clear rules based on business needs and system characteristics. This mapping can be a one-to-one correspondence between a single parameter and a calibration factor, or a combination of multiple parameters corresponding to a single calibration factor. For example, during pre-marinating efficiency analysis, the system can collect real-time values ​​of the vacuum pump extraction rate, vacuum marinating tank stirring frequency, and marinating solution pH value, and then call the preset mapping rules to accurately match and extract the corresponding calibration factors.

[0052] Most importantly, to ensure the consistency of the evaluation process and the comparability of the evaluation results, this example limits the values ​​of the vacuum pump pumping rate calibration factor, the vacuum marinating tank stirring frequency calibration factor, and the marinating liquid pH value calibration factor to between 0 and 1, and the sum of the three is always equal to 1.

[0053] In this embodiment, the pre-marinating control efficiency index increases as the deviation of the vacuum pump's pumping rate (i.e., |P1-P10|), the deviation of the stirring frequency of the vacuum marinating tank (i.e., |P2-P20|), and the deviation of the pH value of the marinating liquid (i.e., |P3-P30|) decrease. Specifically, when the deviation of the stirring frequency of the stirring paddle in the vacuum marinating tank increases, the agitation of the corresponding raw and auxiliary material samples and fluids will hinder the vacuum pump from extracting gas from the tank, resulting in an increase in the actual pumping rate deviation. When the deviation of the pH value of the marinating liquid increases, microbial reproduction is significantly inhibited, and the stirring frequency deviation decreases, reducing mechanical energy consumption. When the deviation of the vacuum pump's pumping rate increases, it generates greater resistance to the stirring shaft seal, causing the stirring frequency deviation of the stirring paddle in the vacuum marinating tank to increase.

[0054] This example, by considering the aforementioned interaction mechanisms, helps to achieve multi-parameter collaborative optimization to accurately quantify microbial contamination risks, dynamically respond to environmental fluctuations and quickly adjust parameters to maintain efficient control, while ensuring batch-to-batch quality consistency through standardized production, balancing energy consumption and microbial inhibition effects to reduce operating costs, and helps to improve the ability to control microbial risks in the pre-marinating stage of raw materials and auxiliary materials. Thus, it effectively solves the problem of low accuracy in controlling microbial contamination risks in the preparation of luncheon meat canning raw materials in existing technologies.

[0055] Furthermore, based on the pre-marinating efficiency analysis results, it is determined whether to optimize the filter matching coefficient. The specific process is as follows: Determine the numerical relationship between the obtained pre-marinating control efficiency index and the preset pre-marinating control efficiency index: If the obtained pre-marinating control efficiency index is not less than the preset pre-marinating control efficiency index, the pre-marinating efficiency analysis result is recorded as qualified pre-marinating, and the raw and auxiliary semi-finished products (i.e., the raw and auxiliary material samples corresponding to qualified pre-marinating) are obtained and the main marinating efficiency analysis is performed; if the obtained pre-marinating control efficiency index is less than the preset pre-marinating control efficiency index, the pre-marinating efficiency analysis result is recorded as unqualified pre-marinating and the filter matching coefficient is optimized.

[0056] The primary filter matching coefficient optimization includes primary fan airflow optimization and primary fan pressure optimization. This means that the average of the obtained pre-curing contamination risk index deviation and fan airflow deviation is used as the fan airflow adjustment amount to dynamically adjust the filter fan speed. Simultaneously, the pre-curing contamination risk index deviation and fan pressure deviation are used as the fan pressure adjustment amount to dynamically adjust the air valve opening. The pre-curing contamination risk index deviation measures the difference between the obtained pre-curing control efficiency index and the preset pre-curing control efficiency index in the database; that is, the difference between the obtained pre-curing control efficiency index and the preset pre-curing control efficiency index in the database. The fan airflow deviation represents the difference between the preset fan airflow corresponding to the raw materials and semi-finished products at the end of the pre-curing risk control period and the obtained fan airflow. The fan airflow adjustment amount represents the improvement of the filter's filtration capacity for contaminants by adjusting the filter fan speed. The air pressure deviation represents the difference between the preset fan air pressure and the acquired fan air pressure at the end of the pre-marinating risk control period for raw materials and semi-finished products. The fan air pressure adjustment amount represents the change in the fan inlet pressure by adjusting the opening of the regulating valve. After one filter matching coefficient optimization, it is determined whether the increase in the acquired pre-marinating control efficiency index is not less than the set increase in the pre-marinating control efficiency index. If so, it indicates that the filter matching coefficient optimization is effective and the main marinating efficiency analysis is performed. Otherwise, the preset personnel are prompted to replace the filter screen. The increase in the pre-marinating control efficiency index represents the difference between the pre-marinating control efficiency index re-acquired after one filter matching coefficient optimization and the pre-marinating control efficiency index acquired before the filter matching coefficient optimization. The set increase in the pre-marinating control efficiency index is represented by the sum and average of the historical increases in the pre-marinating control efficiency index after the historical filter matching coefficient optimization in the database.

[0057] In this embodiment, the PID control algorithm in the filter fan controller takes the calculated fan air volume adjustment and fan air pressure adjustment as inputs, and improves the filter's ability to filter pollutants through the synergistic effect of proportional, integral and derivative steps. The preset pre-curing control efficiency index is represented by the sum and average of the pre-curing control efficiency indices of historical raw and auxiliary material samples in the database at the end of the pre-curing risk control period.

[0058] This example establishes a "dual-deviation-driven adjustment + effect verification closed-loop" mechanism by integrating the deviation of risk control effect with the deviation of equipment operating parameters. The deviation of the pre-curing contamination risk index is linked to the deviation of fan air volume and air pressure for dynamic control. It can quickly respond to the risk of microbial contamination by coordinating the adjustment of speed and air valve opening, and construct a complete risk control link by quantitatively verifying the deviation of the optimized efficiency index. This further ensures that the filter maintains a stable pollutant retention capacity under different operating conditions.

[0059] like Figure 5 The diagram shown is a flowchart of the main marinating efficiency analysis and judgment provided in the embodiment of this application. The specific design logic is as follows: The process begins by acquiring the main marinating detection data and performing a main marinating efficiency analysis on the raw and auxiliary semi-finished products during the main marinating risk control period based on the acquired main marinating detection data. Based on the main marinating efficiency analysis results, it is determined whether the tumbling machine load optimization has been performed. If so, the tumbling shaft pressure and tumbling interval time are adjusted; otherwise, the reliability of microbial contamination risk control during the preparation of luncheon meat canned raw and auxiliary finished products is improved.

[0060] Furthermore, based on the main marinating efficiency analysis results, it is determined whether to optimize the tumbling machine load. The specific process is as follows: Determine the numerical change between the obtained tumbling machine motor load and the preset tumbling machine motor load: If the obtained tumbling machine motor load is not less than the preset tumbling machine motor load, then the main marinating efficiency analysis result is recorded as the main marinating result is qualified and the analysis of the efficiency of microbial contamination risk control of the specified batch of raw and auxiliary materials is completed; if the obtained tumbling machine motor load is less than the preset tumbling machine motor load, then the main marinating efficiency analysis result is recorded as the main marinating is unqualified and the tumbling shaft pressure is optimized.

[0061] The optimization of the kneading roller pressure involves the following steps: The average sum of the obtained kneading roller motor load deviation and the kneading roller pressure deviation is used as the kneading roller pressure adjustment value. The kneading roller motor load deviation measures the difference between the obtained kneading roller motor load and the preset kneading roller motor load in the database; that is, the absolute value of the difference between the obtained kneading roller motor load and the preset kneading roller motor load. The kneading roller pressure deviation represents the absolute value of the difference between the kneading roller pressure corresponding to the raw materials and semi-finished products at the end of the main marinating risk control period and the preset kneading roller pressure. After one kneading roller pressure optimization, it is determined whether the increase in the obtained kneading roller motor load deviation is not less than the set increase in the kneading roller motor load deviation. The increase in the kneading roller motor load deviation represents the difference between the kneading roller motor load re-obtained after one kneading roller pressure optimization and the kneading roller motor load obtained before the kneading roller pressure optimization. The set increase in the kneading roller motor load deviation is determined by using historical kneading roller pressure optimization data from the database. The sum of the increases in the load deviation of the tumbling machine motor indicates that if the result is positive, it means that the optimization of the tumbling shaft pressure is effective and the efficiency of controlling the risk of microbial contamination during the main marinating process of raw materials and semi-finished products has been improved. Otherwise, the tumbling interval time is optimized. The optimization of the tumbling interval time means that the sum of the tumbling machine motor load deviation and the tumbling interval time deviation is used as the adjustment value of the tumbling interval time to dynamically adjust the stirring frequency of the minced meat in the chopping chamber, reducing the reproduction of microorganisms in the residual minced meat. The tumbling interval time deviation represents the absolute value of the difference between the tumbling interval time corresponding to the end of the risk control period of the main marinating of raw materials and semi-finished products and the preset tumbling interval time. After one optimization of the tumbling shaft pressure, it is judged whether the increase in the load deviation of the tumbling machine motor is not less than the set increase in the load deviation of the tumbling machine motor. If so, it means that the optimization of the tumbling interval time is effective and the efficiency of controlling the risk of microbial contamination during the main marinating process of raw materials and semi-finished products has been improved. Otherwise, it prompts the preset personnel to clean the tumbling machine equipment.

[0062] In this embodiment, both the load deviation of the kneading machine motor and the pressure deviation of the kneading shaft are the results after de-unitization processing; the PID control algorithm in the kneading machine motor controller takes the calculated kneading shaft pressure adjustment value and the kneading interval duration adjustment value as inputs, and achieves dynamic and precise adjustment of microbial risk control through the synergistic effect of proportional, integral and derivative steps; the preset kneading machine motor load is represented by the summation and average of the kneading machine motor loads corresponding to the historical raw materials and semi-finished products at the end of the main pickling risk control period in the database.

[0063] This example reduces the retention time of residual meat paste by adjusting the stirring frequency, forming a dual physical dry prevention line. It not only achieves precise control of microbial growth conditions in the main marinating stage through data closed-loop, but also deeply binds equipment maintenance needs with process parameter optimization through standardized effect judgment rules, avoiding the accumulation of microbial base due to insufficient equipment cleaning. Ultimately, it builds a comprehensive microbial risk prevention and control system to ensure the safety and process stability of the main marinating process.

[0064] like Figure 6 The diagram shown is a structural schematic of a product quality risk management system based on inspection and testing data provided in this application embodiment. This application embodiment provides a product quality risk management system based on inspection and testing data, including: a pretreatment efficiency analysis module, a pre-marinating efficiency analysis module, and a main marinating efficiency analysis module. The pretreatment efficiency analysis module is used to perform pretreatment efficiency analysis on the microbial contamination risk management process of a specified batch of raw and auxiliary materials based on the acquired pretreatment testing data, obtaining pretreatment efficiency analysis results, and simultaneously determining whether to optimize fluid flow based on the pretreatment efficiency analysis results. The pre-marinating efficiency analysis module is used to perform pre-marinating efficiency analysis on the microbial contamination risk management process of raw and auxiliary material samples based on the acquired pre-marinating testing data if the pretreatment is deemed qualified, obtaining pre-marinating efficiency analysis results, and simultaneously determining whether to optimize the filter matching coefficient based on the pre-marinating efficiency analysis results. The main marinating efficiency analysis module is used to perform main marinating efficiency analysis on the microbial contamination risk management process of the semi-finished raw and auxiliary materials based on the acquired tumbler motor load if the pre-marinating is deemed qualified, obtaining main marinating efficiency analysis results, and simultaneously determining whether to optimize the tumbler load based on the main marinating efficiency analysis results.

[0065] In this embodiment, by dynamically linking the detection data from the three stages of pretreatment, pre-marinating, and main marinating with the key parameters of the corresponding links, a closed-loop control system of "detection and analysis - parameter optimization - effect verification" is constructed. Each stage is guided by the efficiency analysis results and the equipment operating parameters are adjusted in a targeted manner to achieve layer-by-layer filtration and precise suppression of microbial contamination risks. This phased and hierarchical control mode not only avoids the waste of resources in the extensive control of the whole process, but also ensures that the risks of each link are controllable through standardized qualification judgment rules. Finally, a progressive microbial risk prevention and control system from raw materials to semi-finished products is formed, which significantly improves product quality safety and process stability.

[0066] In summary, this application embodiment analyzes preprocessing efficiency using preprocessing detection data to determine whether fluid flow optimization is needed. Then, it analyzes pre-marinating efficiency using pre-marinating detection data to determine whether filter matching coefficient optimization is needed. Finally, it analyzes main marinating efficiency using tumbler motor load to determine whether tumbler load optimization is needed. This achieves the effect of improving the accuracy of microbial contamination risk control during the preparation of luncheon meat canning raw materials, and solves the problem of low accuracy in microbial contamination risk control during the preparation of luncheon meat canning raw materials in the prior art.

[0067] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0068] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0069] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0070] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1The steps of the function specified in one or more boxes.

[0071] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0072] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A product quality risk management method based on inspection and testing data, characterized in that, Includes the following steps: Step 1: Based on the acquired pretreatment detection data, perform a pretreatment efficiency analysis on the microbial contamination risk control process of a specified batch of raw and auxiliary materials, obtain the pretreatment efficiency analysis results, and determine whether to optimize the fluid flow rate based on the pretreatment efficiency analysis results. The preprocessed detection data includes changes in conveying shear force, changes in propeller speed, and changes in the blade spacing of the dicing machine; Step 2: If the pretreatment is deemed qualified, the pre-curing efficiency analysis of the microbial contamination risk control process of the raw and auxiliary material samples is performed based on the obtained pre-curing test data to obtain the pre-curing efficiency analysis results. At the same time, it is determined whether to optimize the filter matching coefficient based on the pre-curing efficiency analysis results. Step 3: If the pre-marinating is deemed qualified, the main marinating efficiency analysis is performed on the microbial contamination risk control process of raw materials and semi-finished products based on the obtained tumbler motor load. The main marinating efficiency analysis results are obtained, and the tumbler load optimization is determined based on the main marinating efficiency analysis results. The specific process for determining whether to optimize fluid flow rate based on pretreatment efficiency analysis results is as follows: Determine the numerical relationship between the acquired preprocessing control efficiency index and the preset preprocessing control efficiency index: If the obtained pretreatment control efficiency index is not less than the preset pretreatment control efficiency index, the pretreatment efficiency analysis result will be recorded as qualified pretreatment, and raw and auxiliary material samples will be obtained and pre-marinating efficiency analysis will be performed. If the obtained pretreatment control efficiency index is less than the preset pretreatment control efficiency index, the pretreatment efficiency analysis result will be recorded as unqualified and fluid flow optimization will be performed. The filter matching coefficient optimization process involves the following steps: The sum of the obtained pre-curing contamination risk index deviation and the fan air volume deviation is used as the fan air volume adjustment amount to dynamically adjust the filter fan speed. Simultaneously, the sum of the pre-curing contamination risk index deviation and the fan air pressure deviation is used as the fan air pressure adjustment amount to dynamically adjust the air valve opening. The pre-curing contamination risk index deviation is used to measure the degree of difference between the obtained pre-curing control efficiency index and the preset pre-curing control efficiency index in the database; that is, the difference between the obtained pre-curing control efficiency index and the preset pre-curing control efficiency index in the database. The fan air volume deviation represents the difference between the preset fan air volume and the obtained fan air volume corresponding to the raw material semi-finished product at the end of the pre-curing risk control period. The fan air pressure deviation represents the difference between the preset fan air pressure and the obtained fan air pressure corresponding to the raw material semi-finished product at the end of the pre-curing risk control period. After one filter matching coefficient optimization, it is determined whether the increase in the obtained pre-marinating control efficiency index is not less than the set increase in the pre-marinating control efficiency index. If so, it indicates that the filter matching coefficient optimization is effective and the main marinating efficiency analysis is performed. Otherwise, the preset personnel are prompted to replace the filter screen. The one filter matching coefficient optimization includes primary fan air volume optimization and primary fan air pressure optimization.

2. The product quality risk management method based on inspection and testing data as described in claim 1, wherein the pretreatment efficiency analysis of the microbial contamination risk management process for a specified batch of raw and auxiliary materials based on the acquired pretreatment testing data is as follows: At the end of the pre-processing risk control period, the change in conveying shear force of the specified batch of raw and auxiliary materials is compared with the preset change in conveying shear force in the database. The difference between the two is calculated, and the change in conveying shear force is corrected by combining the calibration factor of the change in conveying shear force to obtain the coefficient of change in conveying shear force. The obtained change in propeller speed is compared with the preset change in propeller speed in the database, the difference between the two is calculated, and the change in propeller speed is corrected by combining the calibration factor of the change in propeller speed to obtain the coefficient of change in propeller speed. The obtained change in the blade spacing of the block cutter is compared with the preset change in the blade spacing of the block cutter in the database. The difference between the two is calculated. At the same time, the change in the blade spacing of the block cutter is corrected by combining the calibration factor of the change in the blade spacing of the block cutter to obtain the coefficient of the change in the blade spacing of the block cutter. The obtained coefficients of change in conveying shear force, change in screw propeller speed, and change in blade spacing of the block cutter are processed by inverse proportional calculation. The results of the inverse proportional calculation are then coupled to obtain the pretreatment control efficiency index. The pretreatment control efficiency index is used to reflect the effect of pretreatment detection data on the control of microbial contamination risk during the pretreatment risk control period.

3. The product quality risk management method based on inspection and testing data as described in claim 1, characterized in that, The fluid flow rate optimization process involves the following steps: The summation and average of the obtained pretreatment control efficiency index deviation and fluid flow coefficient deviation are used as the centrifugal pump speed adjustment amount to dynamically adjust the centrifugal pump displacement. The pretreatment control efficiency index deviation is used to measure the degree of difference between the obtained pretreatment control efficiency index and the preset pretreatment control efficiency index in the database. After optimizing the fluid flow rate, the pretreatment control efficiency index is re-acquired. At the same time, it is determined whether the increase in the acquired pretreatment control efficiency index is not less than the set increase in the pretreatment control efficiency index. If so, it indicates that the fluid flow rate optimization is effective and a pre-curing efficiency analysis is performed. Otherwise, the preset personnel are prompted to adjust the environmental humidity by a preset range. The preset range represents the result obtained by mapping the sum of the deviation of the pretreatment control efficiency index and the deviation of the environmental humidity in the database.

4. The product quality risk management method based on inspection and testing data as described in claim 1, characterized in that, The pre-marinating test data includes the vacuum pump pumping rate, the stirring frequency of the vacuum marinating tank, and the pH value of the marinating solution; The process of analyzing the pre-curing efficiency of the microbial contamination risk control of raw material samples based on the acquired pre-curing test data is as follows: At the end of the pre-marinating risk control period, the vacuum pump evacuation rate of the obtained raw and auxiliary material samples is compared with the preset vacuum pump evacuation rate in the database. The difference between the two is calculated, and the vacuum pump evacuation rate calibration factor is used for correction to obtain the vacuum pump evacuation rate coefficient. The stirring frequency of the vacuum marinating tank of the obtained raw and auxiliary material samples is compared with the preset stirring frequency of the vacuum marinating tank in the database. The difference between the two is calculated. At the same time, the stirring frequency calibration factor of the vacuum marinating tank is used for correction to obtain the stirring frequency coefficient of the vacuum marinating tank. The pH value of the marinating solution obtained from the raw and auxiliary material samples is compared with the preset pH value of the marinating solution in the database. The difference between the two is calculated. At the same time, the pH value of the marinating solution is corrected by combining the pH value calibration factor of the marinating solution to obtain the pH value coefficient of the marinating solution. The obtained vacuum pump pumping rate coefficient, vacuum pickling tank stirring frequency coefficient, and pickling liquid pH value coefficient are coupled and processed to obtain the pre-pickled control efficiency index. The pre-pickled control efficiency index is used to reflect the effect of pre-pickled detection data on the control of microbial contamination risk during the pre-pickled risk control period.

5. The product quality risk management method based on inspection and testing data as described in claim 4, characterized in that, The specific process for determining whether to optimize the filter matching coefficient based on the pre-marinating efficiency analysis results is as follows: Determine the numerical relationship between the obtained pre-marinating control efficiency index and the preset pre-marinating control efficiency index: If the obtained pre-marinating control efficiency index is not less than the preset pre-marinating control efficiency index, the pre-treatment efficiency analysis result will be recorded as qualified pre-marinating, and the raw and auxiliary semi-finished products will be obtained and the main marinating efficiency analysis will be performed. If the obtained pre-curing control efficiency index is less than the preset pre-curing control efficiency index, the pre-treatment efficiency analysis result will be recorded as unqualified pre-curing and the filter matching coefficient will be optimized.

6. The product quality risk management method based on inspection and testing data as described in claim 1, characterized in that, The specific process for determining whether to optimize the load on the tumbler based on the main marinating efficiency analysis results is as follows: Determine the relationship between the obtained kneading machine motor load and the preset kneading machine motor load: If the obtained tumbler motor load is not less than the preset tumbler motor load, then the main marinating efficiency analysis result is recorded as the main marinating qualified and the preparation of raw and auxiliary materials finished products is completed. If the obtained tumbler motor load is less than the preset tumbler motor load, the main marinating efficiency analysis result will be recorded as unqualified main marinating and the tumbler shaft pressure will be optimized.

7. The product quality risk management method based on inspection and testing data as described in claim 6, characterized in that, The optimization of the kneading roller pressure involves the following steps: The average sum of the obtained kneading machine motor load deviation and kneading shaft pressure deviation is used as the kneading shaft pressure adjustment value to dynamically adjust the output pressure of the kneading shaft. The kneading machine motor load deviation is used to measure the degree of difference between the obtained kneading machine motor load and the preset kneading machine motor load in the database. After optimizing the kneading roller pressure, it is determined whether the increase in the load deviation of the kneading roller motor is not less than the set increase in the load deviation of the kneading roller motor. If so, it indicates that the kneading roller pressure optimization is effective and the preparation of raw materials and finished products is completed. Otherwise, the preset personnel are prompted to clean the kneading roller equipment.

8. A system applying the product quality risk management method based on inspection and testing data as described in any one of claims 1-7, characterized in that, include: Pretreatment efficiency analysis module, pre-marinating efficiency analysis module, and main marinating efficiency analysis module; The pretreatment efficiency analysis module is used to perform pretreatment efficiency analysis on the microbial contamination risk control process of a specified batch of raw and auxiliary materials based on the acquired pretreatment detection data, obtain the pretreatment efficiency analysis results, and determine whether to optimize the fluid flow rate based on the pretreatment efficiency analysis results. The pre-curing efficiency analysis module is used to perform pre-curing efficiency analysis on the microbial contamination risk control process of raw and auxiliary material samples based on the acquired pre-curing test data if the pre-treatment is deemed qualified, and to obtain the pre-curing efficiency analysis results. At the same time, it is used to determine whether to optimize the filter matching coefficient based on the pre-curing efficiency analysis results. The main marinating efficiency analysis module is used to perform a main marinating efficiency analysis on the microbial contamination risk control process of raw materials and semi-finished products based on the obtained tumbler motor load if the pre-marinating is deemed qualified, and to obtain the main marinating efficiency analysis results. At the same time, it determines whether to optimize the tumbler load based on the main marinating efficiency analysis results.

Images