A yogurt product assembly line processing monitoring system and method based on artificial intelligence

Through the yogurt product assembly line processing monitoring system based on artificial intelligence, the problems of low manual monitoring efficiency and poor accuracy in yogurt processing are solved, and the full monitoring and control of raw milk and yogurt are realized, the quality and yield of yogurt are improved, and the quality and output of yogurt are reduced. Production costs and risks.

CN117762111BActive Publication Date: 2024-11-22湖南南山牧业有限公司
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202311806908.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-12-26
Publication Date
2024-11-22
Estimated Expiration
2043-12-26

AI Technical Summary

Technical Problem

During the existing yogurt processing process, manual or semi-automated monitoring efficiency is low and the accuracy is poor, and comprehensive, real-time and dynamic monitoring of raw milk and yogurt cannot be achieved, resulting in the inability to detect and deal with abnormal situations in a timely manner, and the inability to meet large-scale, high-speed and high-efficiency production requirements.

Method used

Design a yogurt product assembly line processing monitoring system based on artificial intelligence, including raw milk collection, processing, fermentation and filling modules, and realize the raw milk and yogurt through sampling robots, detection modules, diversion modules, data collection and transmission modules. Full-process monitoring and control, and use cloud platform for data storage, analysis and optimization.

Benefits of technology

The full monitoring and control of raw milk and yogurt is achieved, the quality and output are improved, the production costs and risks are reduced, and the quality and safety of yogurt are ensured.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117762111B_ABST
    Figure CN117762111B_ABST
Patent Text Reader

Abstract

The present invention discloses a yogurt product assembly line processing monitoring system based on artificial intelligence, which belongs to the field of food processing technology. The system includes a raw milk collection monitoring part, a raw milk processing monitoring part, a yogurt fermentation monitoring part, a yogurt filling monitoring part and a cloud platform part. Each part transmits and controls data through the Internet of Things, and the cloud platform part processes and feeds back the data through artificial intelligence technology. The system can automatically monitor and control the sampling, detection, shunting, sorting, filling and other processes of raw milk and yogurt, improve the quality and efficiency of yogurt, and reduce costs and risks. The beneficial effects of the present invention are that it realizes comprehensive, real-time and dynamic monitoring of raw milk and yogurt, realizes automated shunting, sorting and other operations of raw milk and yogurt, realizes effective analysis and optimization of data, and uses artificial intelligence technology to improve the quality and efficiency of yogurt and reduce costs and risks.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of yogurt processing, and in particular to an artificial intelligence-based yogurt product assembly line processing monitoring system. Background Art

[0002] Yogurt has the advantages of being rich in nutrition, easy to digest, and promoting intestinal health. The yogurt production process mainly includes the collection, processing and fermentation of raw milk, as well as the testing, sorting and filling of yogurt. In these steps, it is necessary to monitor various quality indicators of raw milk and yogurt, such as density, fat content, protein content, lactic acid bacteria content, antibiotic residues, harmful microorganisms, acidity, viscosity, moisture, protein content, etc., to ensure the quality and safety of yogurt. At present, the monitoring of raw milk and yogurt mainly adopts manual or semi-automatic methods, which have the following problems and shortcomings:

[0003] (1) Manual monitoring is inefficient, poorly accurate, and easily affected by human factors. Manual monitoring requires the use of various instruments and equipment, such as acidity meters, thermometers, and density meters, to measure multiple indicators. The operation and reading of these instruments and equipment must be completed manually, which is not only time-consuming and labor-intensive, but also prone to errors and deviations. In addition, manual monitoring is also affected by factors such as the technical level, experience, judgment, and attitude of personnel, which may lead to inaccurate and inconsistent results;

[0004] (2) It is not possible to achieve comprehensive, real-time, and dynamic monitoring of raw milk and yogurt, to detect and handle abnormal situations in a timely manner, and to effectively use data for analysis and optimization. Manual or semi-automatic monitoring methods cannot adapt to the production process and cannot meet the requirements of large-scale, high-speed, and efficient production. Manual or semi-automatic monitoring methods usually require sampling, preparation, analysis, and other steps, and cannot achieve online, continuous, and non-destructive monitoring, cannot provide timely feedback on monitoring results, cannot conduct real-time regulation of the production process, and cannot automatically store, process, analyze, and optimize monitoring data.

[0005] Therefore, how to design and develop a system that can conduct comprehensive, real-time and dynamic monitoring of various quality indicators of raw milk and yogurt is a technical problem that needs to be solved urgently. Summary of the invention

[0006] In view of the above problems, the present invention provides a yogurt product assembly line processing monitoring system based on artificial intelligence, which can realize full-process monitoring and control of raw milk and yogurt, and improve the quality and output of yogurt.

[0007] To achieve the above object, the technical solution adopted by the present invention is:

[0008] A yogurt product assembly line processing monitoring system based on artificial intelligence, comprising:

[0009] The raw milk collection and monitoring module includes a raw milk sampling module, a raw milk detection module, a raw milk diversion module, a raw milk data acquisition module and a raw milk data transmission module. This part regularly samples and detects the raw milk through the raw milk sampling module and the raw milk detection module, diverts and stores the raw milk through the raw milk diversion module, and uploads the raw milk data to the cloud platform through the raw milk data acquisition module and the raw milk data transmission module;

[0010] The raw milk processing monitoring module includes a raw milk receiving module, a raw milk sterilization module, a raw milk blending module, a raw milk processing data acquisition module and a raw milk processing data transmission module. This part receives and distributes the raw milk through the raw milk receiving module, sterilizes the raw milk at high temperature through the raw milk sterilization module, blends and adds additives to the raw milk in proportion through the raw milk blending module, and uploads the raw milk processing data to the cloud platform through the raw milk processing data acquisition module and the raw milk processing data transmission module;

[0011] Yogurt fermentation monitoring module, which includes a yogurt inoculation module, a yogurt fermentation module, a yogurt detection module, a yogurt sorting module, a yogurt data acquisition module and a yogurt data transmission module. This part inoculates lactic acid bacteria into raw milk through the yogurt inoculation module, ferments the inoculated raw milk at a constant temperature and humidity through the yogurt fermentation module, performs quality inspection on the fermented yogurt through the yogurt detection module, sorts qualified and unqualified yogurt through the yogurt sorting module, and uploads relevant data of yogurt to the cloud platform through the yogurt data acquisition module and the yogurt data transmission module;

[0012] Yogurt filling monitoring module, which includes a yogurt filling module, a filling data acquisition module and a filling data transmission module. This part fills and caps the yogurt through the yogurt filling module, and uploads the relevant filling data to the cloud platform part through the filling data acquisition module and the filling data transmission module;

[0013] The cloud platform part includes a data storage module, a data analysis module, a data display module, and a data application module. This part stores and backs up the system data through the data storage module, analyzes the system data through the data analysis module, generates visual reports for the system data through the data display module, and optimizes the system data and provides decision support through the data application module;

[0014] The raw milk collection monitoring module, the raw milk processing monitoring module, the yogurt fermentation monitoring module, and the yogurt filling monitoring module are connected in sequence. The cloud platform part transmits data with each of the above modules. The above data transmission is transmitted through the Internet of Things. The PLC control system is used between the modules to realize automatic parameter adjustment, process control and result feedback.

[0015] The beneficial effect of the present invention is that the system can realize the whole process monitoring and control of raw milk and yogurt.

[0016] As a further improvement of the above scheme: the raw milk sampling module includes a sampling robot and a sampler, the sampling robot extracts a set amount of raw milk from the raw milk storage tank according to the set sampling time and frequency, the sampler packs the raw milk sample into sampling bottles, and sends the sampling bottles to the raw milk detection module; the raw milk detection module takes out a preset amount of raw milk sample from the sampling bottle according to the preset detection items and standards, and performs physical, chemical and microbiological tests on the raw milk sample, including density, fat content, protein content, lactic acid bacteria content, antibiotic residue, and harmful microorganism content, and the test results are uploaded to the cloud platform part through the raw milk data acquisition module and the raw milk data transmission module; the raw milk diversion module includes a diversion robot and a diversion valve, the diversion robot sends qualified raw milk samples back to the raw milk storage tank according to the test results, and sends unqualified raw milk samples to the waste treatment equipment, and the diversion valve controls the flow direction of the raw milk according to the test results, and sends qualified raw milk to the raw milk processing monitoring module, and sends unqualified raw milk to the waste treatment equipment.

[0017] The beneficial effects of the present invention are as follows: the present invention improves the efficiency and accuracy of raw milk sampling and detection, and reasonably diverts and stores the raw milk according to the processing results.

[0018] As a further improvement of the above scheme: the raw milk receiving module includes a receiving robot and a receiving valve, the receiving robot receives a fixed amount of raw milk from the raw milk storage tank according to a preset receiving time and quantity, the receiving valve controls the flow of raw milk, and transports the raw milk to the raw milk sterilization module; the raw milk sterilization module controls the sterilization equipment to sterilize the raw milk according to a preset sterilization temperature and time, and the sterilized raw milk uploads the sterilization data to the cloud platform part through the raw milk processing data acquisition module and the raw milk processing data transmission module, and is transported to the raw milk blending module; the raw milk blending module blends the raw milk in proportion and adds additives according to a preset blending ratio and additive types, and the blended raw milk uploads the blending data to the cloud platform part through the raw milk processing data acquisition module and the raw milk processing data transmission module, and is transported to the yogurt fermentation monitoring module.

[0019] The beneficial effects of the present invention are: the raw milk is sterilized and prepared appropriately according to the quality and demand of the raw milk, so as to facilitate the next fermentation operation.

[0020] As a further improvement of the above scheme: the yogurt inoculation module inoculates the raw milk with lactic acid bacteria according to a preset inoculation amount and type of lactic acid bacteria, and the raw milk after inoculation uploads the inoculation data to the cloud platform part through the yogurt data acquisition module and the yogurt data transmission module, and is then transported to the yogurt fermentation module; the yogurt fermentation module ferments the raw milk according to a preset fermentation temperature, humidity and time, and the fermented yogurt is tested by the yogurt detection module, including the yogurt temperature, pH value, lactic acid bacteria content, coagulation time and coagulation degree before and after fermentation, and the fermentation data is uploaded to the cloud platform part through the yogurt data acquisition module and the yogurt data transmission module; the yogurt sorting module controls the flow direction of the yogurt according to the test results, and transports the qualified yogurt to the yogurt filling monitoring module, and transports the unqualified yogurt to the waste treatment equipment; the yogurt filling module fills and caps the yogurt according to the preset filling amount and filling container, and the yogurt after filling uploads the filling data to the cloud platform part through the filling data acquisition module and the filling data transmission module, and is then transported to the packaging equipment.

[0021] The beneficial effects of the present invention are: appropriately inoculating and fermenting raw milk according to the requirements of different yogurt specifications, thereby improving the yogurt output rate.

[0022] As a further improvement of the above scheme: the cloud platform data storage module receives and stores the transmission data of the raw milk data storage module, the yogurt data storage module, and the filling data storage module, the data analysis module analyzes and processes the data, the data application module feeds back the results of the data analysis to the yogurt fermentation module in the form of a control signal, and the data display module displays the results of the data analysis and the results after feedback control to the customer in the form of charts.

[0023] The beneficial effects of the present invention are: using artificial intelligence technology to analyze and apply data on raw milk and yogurt, feedback adjusting yogurt fermentation parameters, improving yogurt quality and output, and reducing production costs and risks.

[0024] As a further improvement of the above technical solution: the production model represents Y=β0+β1X1+β2X2+...+β n X n +ò Among them, β0 is the intercept term, β1 to β n is the regression coefficient, ò is the error term, Y is the yogurt production, X1, X2,,, X n It is a factor that affects the yield of yogurt; the quality index of the yogurt is expressed as: Q=w1P+w2F+w3A+w4V+w5N, where P is the protein content, F is the fat content, A is the acidity, V is the viscosity, N is the total number of colonies, and w1, w2, w3, w4, and w5 are weight coefficients.

[0025] The beneficial effects of the present invention are: the production model and quality index are digitized, and the yogurt yield and quality are predicted more intuitively.

[0026] The present invention also provides a yogurt product assembly line processing monitoring method based on artificial intelligence, comprising the following steps:

[0027] S1 Raw milk monitoring: Raw milk is sampled and tested, including density, fat content, protein content, lactic acid bacteria content, antibiotic residues, and harmful microorganisms. According to the national food safety standard: fermented milk is judged to be qualified. Qualified raw milk is transported to the next step, and unqualified raw milk is transported to waste treatment facilities and the collected data is transmitted to the cloud platform;

[0028] S2 Raw milk processing: sterilize and blend qualified raw milk. The data collection module collects data including raw milk temperature, pressure, flow, total colony count before and after sterilization, raw milk density, fat content, protein content, and lactic acid bacteria content before and after blending. The processed raw milk is transported to the next step and the collected data is transmitted to the cloud platform.

[0029] S3 Fermentation: Inoculate and ferment the processed raw milk, and test the fermented yogurt, including the yogurt temperature before and after inoculation, pH value, type and amount of additives, density, fat content, protein content, lactic acid bacteria content, organic acid content, water content, and harmful microorganism content. The collected data is transmitted to the cloud platform, and the yogurt is judged to be qualified according to the national food safety standard: fermented milk. Qualified yogurt is sent to the next step;

[0030] S4 Yogurt filling: Fill and cap qualified yogurt and transmit filling data to the cloud platform;

[0031] S5 Result Display The cloud platform performs data analysis based on the received data. The analysis results are fed back to the yogurt fermentation module in the form of control signals through the data application module to adjust the parameters, establish a yogurt production model, and calculate the yogurt quality index. The analysis results and feedback results are displayed to the user in the form of charts.

[0032] The beneficial effects of the present invention are: comprehensive, real-time and dynamic monitoring of various quality indicators of raw milk and yogurt, such as density, fat content, protein content, lactic acid bacteria content, antibiotic residue, harmful microorganism content, acidity, viscosity, moisture, quality index, etc., to ensure the quality and safety of yogurt, avoid the outflow of unqualified products, and improve consumer satisfaction and trust. The results are presented to users in the form of charts to improve the user experience.

[0033] As a further improvement of the above technical solution: S3 fermentation includes the following steps:

[0034] S31 inoculation: according to the requirements of different yogurt specifications, the inoculation amount and lactic acid bacteria type are set, the raw milk is inoculated, the inoculation data is uploaded to the cloud platform, and the inoculated raw materials are transported to the yogurt fermentation module;

[0035] S32 fermentation, according to the set fermentation temperature, humidity and time, ferment the inoculated raw milk, collect yogurt temperature, pH value, lactic acid bacteria content, density, fat content, protein content, lactic acid bacteria content, organic acid content, water content, harmful microorganism content in real time, upload the fermentation data to the cloud platform, after data analysis, the cloud platform feeds back the control signal to the yogurt fermentation module, adjusts the fermentation temperature, humidity and time in real time, and tests the fermented yogurt, including pH value, additive type and amount, density, fat content, protein content, lactic acid bacteria content, organic acid content, water content, harmful microorganism content, to determine whether it meets the national food safety standard: fermented milk;

[0036] S33 Yogurt diversion: Control the flow direction of yogurt according to the test results, convey qualified yogurt to the yogurt filling monitoring module, and convey unqualified yogurt to the waste treatment equipment.

[0037] The beneficial effects of the present invention are: comprehensive, real-time and dynamic monitoring of various quality indicators in the yogurt fermentation process, and the cloud platform adjusts the fermentation parameters in real time to ensure the quality and safety of yogurt fermentation and avoid the outflow of unqualified products.

[0038] As a further improvement of the above technical solution: the sterilization temperature and time of the raw milk sterilization module are determined by the following formula: Among them, T k is the sterilization time, N0 is the initial number of microorganisms in the raw milk, N k is the number of microorganisms remaining after sterilization, k is the sterilization rate constant, C p is the specific heat capacity of raw milk, ΔT is the sterilization temperature difference, Q h The fermentation temperature, humidity and time of the yogurt fermentation module are determined by the following formula: T f =h(L k ), H f =i(L k ), Among them, T f is the fermentation temperature, H f is the fermentation humidity, t f is the fermentation time, N f is the number of lactic acid bacteria after fermentation, N i is the number of lactic acid bacteria inoculated, r is the growth rate of lactic acid bacteria, L k is the type of lactic acid bacteria, h and i are the functions of fermentation temperature and humidity, respectively, given by the following formula: h(L k )=a k T0+b k , i(L k )=c k H0+d k Among them, a k ,b k is the temperature coefficient of the kth bacterial species, c k ,b k is the humidity coefficient of the kth bacterial species, T0 is the ambient temperature, and H0 is the ambient humidity.

[0039] The beneficial effects of the present invention are: the sterilization temperature and time, the fermentation temperature, humidity and time are quantified, and the sterilization and fermentation of yogurt are controlled more accurately.

[0040] As a further improvement of the above technical solution: the decision model is expressed as: Among them, w0, w1, w2, w3, w4 are decision parameters, T, pH, L and D are the temperature, pH value, lactic acid bacteria content and density of yogurt respectively, and y indicates whether the fermentation parameters need to be adjusted.

[0041] The beneficial effect of the present invention is that artificial intelligence technology is used to make a decision on whether to adjust the yogurt fermentation parameters, thereby optimizing the yogurt fermentation environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a schematic diagram of the system structure of the yogurt product assembly line processing monitoring system;

[0043] Figure 2 This is the workflow diagram of the yogurt product assembly line processing monitoring system. DETAILED DESCRIPTION

[0044] In order to enable those skilled in the art to better understand the technical solution, the technical solution is described in detail below in conjunction with the embodiments. The description in this section is only exemplary and explanatory and should not have any limiting effect on the scope of protection of the present application.

[0045] Embodiment 1:

[0046] Figure 1 The system structure diagram of the present invention is shown in the figure. As shown in the figure, the present invention is a yogurt product assembly line processing monitoring system based on artificial intelligence, including:

[0047] The raw milk collection and monitoring module includes a raw milk sampling module, a raw milk detection module, a raw milk diversion module, a raw milk data acquisition module and a raw milk data transmission module. This part regularly samples and detects the raw milk through the raw milk sampling module and the raw milk detection module, diverts and stores the raw milk through the raw milk diversion module, and uploads the raw milk data to the cloud platform through the raw milk data acquisition module and the raw milk data transmission module;

[0048] The raw milk processing monitoring module includes a raw milk receiving module, a raw milk sterilization module, a raw milk blending module, a raw milk processing data acquisition module and a raw milk processing data transmission module. This part receives and distributes the raw milk through the raw milk receiving module, sterilizes the raw milk at high temperature through the raw milk sterilization module, blends and adds additives to the raw milk in proportion through the raw milk blending module, and uploads the raw milk processing data to the cloud platform through the raw milk processing data acquisition module and the raw milk processing data transmission module;

[0049] Yogurt fermentation monitoring module, which includes a yogurt inoculation module, a yogurt fermentation module, a yogurt detection module, a yogurt sorting module, a yogurt data acquisition module and a yogurt data transmission module. This part inoculates lactic acid bacteria into raw milk through the yogurt inoculation module, ferments the inoculated raw milk at a constant temperature and humidity through the yogurt fermentation module, performs quality inspection on the fermented yogurt through the yogurt detection module, sorts qualified and unqualified yogurt through the yogurt sorting module, and uploads relevant data of yogurt to the cloud platform through the yogurt data acquisition module and the yogurt data transmission module;

[0050] Yogurt filling monitoring module, which includes a yogurt filling module, a filling data acquisition module and a filling data transmission module. This part fills and caps the yogurt through the yogurt filling module, and uploads the relevant filling data to the cloud platform part through the filling data acquisition module and the filling data transmission module;

[0051] The cloud platform part includes a data storage module, a data analysis module, a data display module, and a data application module. This part stores and backs up the system data through the data storage module, analyzes the system data through the data analysis module, generates visual reports for the system data through the data display module, and optimizes the system data and provides decision support through the data application module;

[0052] The raw milk collection monitoring module, the raw milk processing monitoring module, the yogurt fermentation monitoring module, and the yogurt filling monitoring module are connected in sequence. The cloud platform part transmits data with each of the above modules. The above data transmission is transmitted through the Internet of Things. The PLC control system is used between the modules to realize automatic parameter adjustment, process control and result feedback.

[0053] Specifically, the raw milk sampling module includes a sampling robot and a sampler. The sampling robot extracts a set amount of raw milk from the raw milk storage tank according to the set sampling time and frequency. The sampler packs the raw milk sample into sampling bottles and sends the sampling bottles to the raw milk detection module; the raw milk detection module takes out a preset amount of raw milk sample from the sampling bottle according to preset detection items and standards, and performs physical, chemical and microbiological tests on the raw milk sample, including density, fat content, protein content, lactic acid bacteria content, antibiotic residue, and harmful microorganism content. The test results are uploaded to the cloud platform part through the raw milk data acquisition module and the raw milk data transmission module; the raw milk diversion module includes a diversion robot and a diversion valve. The diversion robot sends qualified raw milk samples back to the raw milk storage tank according to the test results, and sends unqualified raw milk samples to the waste treatment equipment. The diversion valve controls the flow direction of the raw milk according to the test results, and sends qualified raw milk to the raw milk processing monitoring module, and sends unqualified raw milk to the waste treatment equipment.

[0054] Specifically, the raw milk receiving module includes a receiving robot and a receiving valve. The receiving robot receives a fixed amount of raw milk from the raw milk storage tank according to a preset receiving time and quantity. The receiving valve controls the flow of the raw milk and transports the raw milk to the raw milk sterilization module; the raw milk sterilization module controls the sterilization equipment to sterilize the raw milk according to a preset sterilization temperature and time. The sterilized raw milk uploads the sterilization data to the cloud platform part through the raw milk processing data acquisition module and the raw milk processing data transmission module, and is transported to the raw milk blending module; the raw milk blending module blends the raw milk in proportion and adds additives according to a preset blending ratio and additive types. The blended raw milk uploads the blending data to the cloud platform part through the raw milk processing data acquisition module and the raw milk processing data transmission module, and is transported to the yogurt fermentation monitoring module.

[0055] Specifically, the yogurt inoculation module inoculates the raw milk with lactic acid bacteria according to a preset inoculation amount and type of lactic acid bacteria, and the raw milk after inoculation uploads the inoculation data to the cloud platform part through the yogurt data acquisition module and the yogurt data transmission module, and is transmitted to the yogurt fermentation module; the yogurt fermentation module ferments the raw milk according to the preset fermentation temperature, humidity and time, and the fermented yogurt is detected by the yogurt detection module, including the yogurt temperature, pH value, lactic acid bacteria content, coagulation time and coagulation degree before and after fermentation, and the fermentation data is uploaded to the cloud platform part through the yogurt data acquisition module and the yogurt data transmission module; the yogurt sorting module controls the flow direction of the yogurt according to the detection result, and transmits the qualified yogurt to the yogurt filling monitoring module, and transmits the unqualified yogurt to the waste treatment equipment; the yogurt filling module fills and caps the yogurt according to the preset filling amount and filling container, and the yogurt after filling uploads the filling data to the cloud platform part through the filling data acquisition module and the filling data transmission module, and is transmitted to the packaging equipment.

[0056] Specifically, the cloud platform data storage module receives and stores the transmission data of the raw milk data storage module, the yogurt data storage module, and the filling data storage module; the data analysis module analyzes and processes the data; the data application module feeds back the results of the data analysis to the yogurt fermentation module in the form of a control signal; the data display module displays the results of the data analysis and the results after feedback control to the customer in the form of a chart.

[0057] Specifically, the production model represents Y=β0+β1X1+β2X2+...+β n X n +ò Among them, β0 is the intercept term, β1 to β n is the regression coefficient, ò is the error term, Y is the yogurt production, X1, X2,,, X n is a factor affecting yogurt production; in this embodiment, three factors affecting yogurt production are selected, namely, the quality of raw milk, the selection of fermentation bacteria, and the control of fermentation conditions. The observed values ​​of yogurt production and the above factors are collected to form a data set. Let β0~β3 be 2, 2, 3, 1 respectively, that is, the regression equation is Y=2+2X1+3X2+X3; calculate the residual sum of squares SSE, Among them, Y i is the actual value of the ith data, is the predicted value of the ith data, in this embodiment SSE=200. Calculate the regression square sum SSR to calculate using the following formula: in, is the predicted value of the i-th data, is the mean of the dependent variable, in this embodiment, SSR = 40. Calculate the F statistic and substitute it into the formula to obtain: The significance level is selected as 0.05, and the F statistic of the regression model is 0.426. The regression model is significant, and this regression equation can be used to estimate the yogurt production under these three influencing factors. Therefore, the production model is Y = 2 + 2X1 + 3X2 + X3, where X1 ~ X3 are the quality of raw milk, the selection of fermentation strains, and the control of fermentation conditions, and Y is the predicted yield.

[0058] The quality index of the yogurt is expressed as: Q=w1P+w2F+w3A+w4V+w5N, wherein P is protein content, F is fat content, A is acidity, V is viscosity, N is total colony count, and w1, w2, w3, w4, and w5 are weight coefficients; assuming that protein content and total colony count are most important to the quality of yogurt, while fat content and acidity are second to the quality of yogurt, and viscosity is the least important to the quality of yogurt, the following weight coefficients are taken: w1=0.3, w2=0.2, w3=0.2, w4=0.1, w5=0.2, protein content P=3.5g / 100g, fat content F=3.0g / 100g, acidity A=4.0pH, viscosity V=200mPa·s, total colony count N=10 6 CFU / mL, the quality index of yogurt is Q = 0.3 × 3.5 + 0.2 × 3.0 + 0.2 × 4.0 + 0.1 × 200 + 0.2 × 10 6 =200053.5.

[0059] Embodiment 2:

[0060] Figure 2 The flowchart of the present invention is shown in the figure. The present invention is a yogurt product assembly line processing monitoring method based on artificial intelligence, characterized in that the method comprises the following steps:

[0061] S1 Raw milk monitoring: sampling and testing of raw milk, including density, fat content, protein content, lactic acid bacteria content, antibiotic residues, and harmful microorganisms content. According to the national food safety standard: fermented milk is judged to be qualified. Qualified raw milk is transported to the next step, and unqualified raw milk is transported to the waste treatment facility and the collected data is transmitted to the cloud platform; S2 Raw milk processing: sterilize and blend qualified raw milk. The data collection module collects raw milk temperature, pressure, flow, total colony count before and after sterilization, raw milk density, fat content, protein content, and lactic acid bacteria content before and after blending. The processed raw milk is transported to the next step and the collected data is transmitted to the cloud platform;

[0062] S3 Fermentation: Inoculate and ferment the processed raw milk, and test the fermented yogurt, including the yogurt temperature before and after inoculation, pH value, type and amount of additives, density, fat content, protein content, lactic acid bacteria content, organic acid content, water content, and harmful microorganism content. The collected data is transmitted to the cloud platform, and the yogurt is judged to be qualified according to the national food safety standard: fermented milk. Qualified yogurt is sent to the next step;

[0063] S4 Yogurt filling: Fill and cap qualified yogurt and transmit filling data to the cloud platform;

[0064] S5 Result Display The cloud platform performs data analysis based on the received data. The analysis results are fed back to the yogurt fermentation module in the form of control signals through the data application module to adjust the parameters, establish a yogurt production model, and calculate the yogurt quality index. The analysis results and feedback results are displayed to the user in the form of charts.

[0065] Specifically, S3 fermentation includes the following steps:

[0066] S31 inoculation: according to the requirements of different yogurt specifications, the inoculation amount and lactic acid bacteria type are set, the raw milk is inoculated, the inoculation data is uploaded to the cloud platform, and the inoculated raw materials are transported to the yogurt fermentation module;

[0067] S32 fermentation, according to the set fermentation temperature, humidity and time, ferment the inoculated raw milk, collect yogurt temperature, pH value, lactic acid bacteria content, density, fat content, protein content, lactic acid bacteria content, organic acid content, water content, harmful microorganism content in real time, upload the fermentation data to the cloud platform, after data analysis, the cloud platform feeds back the control signal to the yogurt fermentation module, adjusts the fermentation temperature, humidity and time in real time, and tests the fermented yogurt, including pH value, additive type and amount, density, fat content, protein content, lactic acid bacteria content, organic acid content, water content, harmful microorganism content, to determine whether it meets the national food safety standard: fermented milk;

[0068] S33 Yogurt diversion: Control the flow direction of yogurt according to the test results, convey qualified yogurt to the yogurt filling monitoring module, and convey unqualified yogurt to the waste treatment equipment.

[0069] Embodiment 3:

[0070] This embodiment provides the specific calculation of the sterilization temperature and time, fermentation temperature, humidity and time, and decision model. The sterilization temperature and time of the raw milk sterilization module are determined by the following formula: Among them, T k is the sterilization time, N0 is the initial number of microorganisms in the raw milk, N kis the number of microorganisms remaining after sterilization, k is the sterilization rate constant, C p is the specific heat capacity of raw milk, ΔT is the sterilization temperature difference, Q h is the heating power; suppose the initial number of microorganisms in raw milk is N0=10 6 / mL, specific heat capacity is C p =3.9J / (g℃), the initial temperature is T0=4℃, and the target temperature for sterilization is T s =72℃, the residual quantity is N k =10 2 / mL, heating power is Q h =1000W, then the calculation can be done according to the following steps:

[0071] Calculate the sterilization temperature difference ΔT = T s -T0=72-4=68℃.

[0072] Calculate the sterilization rate constant k,

[0073] Calculate the sterilization time T k , substituting into the first formula we get:

[0074] Verify whether the sterilization time conforms to the second formula and substitute: The second result is inconsistent with the result obtained by the first formula. This is because the second formula ignores factors such as the mass and flow rate of raw milk, as well as heat loss during the heating process. Therefore, it can only be used as a rough estimate and cannot be used as a basis for accurate calculations.

[0075] To sum up, 11.7>3.7, so according to the first formula, the sterilization time should be 11.7s.

[0076] The fermentation temperature, humidity and time of the yogurt fermentation module are determined by the following formula: f =h(L k ), H f =i(L k ), Among them, T f is the fermentation temperature, H f is the fermentation humidity, t f is the fermentation time, N f is the number of lactic acid bacteria after fermentation, N i is the number of lactic acid bacteria inoculated, r is the growth rate of lactic acid bacteria, L k is the type of lactic acid bacteria, h and i are the functions of fermentation temperature and humidity, respectively, given by the following formula: h(L k )=a k T0+b k , i(Lk )=c k H0+d k Among them, a k ,b k is the temperature coefficient of the kth bacterial species, c k ,b k is the humidity coefficient of the kth bacterial species, T0 is the ambient temperature, and H0 is the ambient humidity; assuming that the lactic acid bacteria species in yogurt are thermophilic Streptococcus and Bulgarian Lactobacillus, and the number of lactic acid bacteria inoculated is N i =10 5 CFU / mL, the number of lactic acid bacteria after fermentation is N f =10 8 CFU / mL, the temperature coefficient of thermophilic Streptococcus is a1=0.1 and b1=35, the humidity coefficient is c1=0.05 and d1=80, the temperature coefficient of Lactobacillus bulgaricus is a2=0.08 and b2=37, the humidity coefficient is c2=0.04 and d2=85, the ambient temperature is T0=25°C, and the ambient humidity is H0=70%, then the calculation can be performed according to the following steps:

[0077] Calculate the fermentation temperature T f , respectively, into the first formula to get: T f =h(L1)=a1T0+b1=0.1×25+35=37.5℃, T f =h(L2)=a2T0+b2=0.08×25+37=39°C. The optimal fermentation temperature of the two lactic acid bacteria is different, so we take the average of the two, that is,

[0078] Calculate fermentation humidity H f , respectively, into the second formula to obtain: H f =i(L1)=c1H0+d1=0.05×70+80=83.5%, H f =i(L2)=c2H0+d2=0.04×70+85=87.8%. The optimal fermentation humidity of the two lactic acid bacteria is different, so we take the average of the two, that is,

[0079] Calculate the fermentation time t f , the growth rate of lactic acid bacteria r: r = 10 5.62-0.12Tf =10 5.62-0.12×38.25 =0.0121 / h. Substituting into the formula, we get:

[0080] Verify whether the fermentation temperature, humidity and time meet the quality requirements of yogurt. The fermentation temperature of yogurt is generally 40-45°C, the fermentation humidity is generally 80-90%, and the fermentation time is generally 6-10h, so the calculated fermentation parameters are all within a reasonable range.

[0081] In summary, according to these formulas, the fermentation temperature should be 38.25°C, the fermentation humidity should be 85.65%, and the fermentation time should be 8.1h.

[0082] The decision model is expressed as: Among them, w0, w1, w2, w3, w4 are decision parameters, T, pH, L and D are the temperature, pH value, lactic acid bacteria content and density of yogurt respectively, and y indicates whether the fermentation parameters need to be adjusted.

[0083] In the first step, the dataset is prepared by collecting historical data of yogurt fermentation, including the values ​​of T, pH, L, D, and y, obtained from instruments or records in the laboratory or factory.

[0084] The second step is to process the data. The collected data needs to be preprocessed using the data analysis module, such as cleaning, missing value processing, outlier processing, normalization, dimensionality reduction, etc., to improve the availability and effectiveness of the data, reduce noise and redundancy, and facilitate subsequent modeling and analysis. In this embodiment, T, pH, L and D have been normalized to the range of 0 to 1 to avoid the influence of different scales.

[0085] The third step is to select an algorithm. You need to select an appropriate machine learning algorithm based on the characteristics of the data and the goal of the problem. In this example, logistic regression is selected.

[0086] The fourth step is to train the model. The data needs to be divided into a training set and a test set. The training set is used to train the machine learning model to adjust the parameters of the model so that the model can fit the training data as closely as possible, that is, to minimize the difference between y and f(T, pH, L, D). In this embodiment, the gradient descent algorithm is used to optimize the model parameters and update the parameters iteratively. The update formula of the gradient descent algorithm is: Among them, w i is the i-th parameter, α is the learning rate, and J is the loss function, expressed as:

[0087]

[0088] Where n is the number of training data, y i is the true value of the i-th data, f(T i ,pH i ,L i ,D i ) is the predicted value of the i-th data. is the partial derivative of the loss function with respect to the i-th parameter, that is Among them, x i is the ith characteristic value of the ith data, that is, T, pH, L or D. In this embodiment, α=0.01, and the number of iterations is 100.

[0089] The fifth step is to evaluate the model. The test set is needed to evaluate the machine learning model, and the performance of the model on unknown data is measured by accuracy, recall, precision, and F1 value.

[0090] Step 6: Apply the model. After the model training and evaluation are completed, the model can be applied to the actual yogurt fermentation process, that is, according to the real-time collected T, pH, L and D values, the model is used to predict the value of y. If y = 1, it means that the fermentation parameters need to be adjusted. If y = 0, it means that the fermentation parameters do not need to be adjusted. Then, according to the prediction results, take corresponding control measures, such as changing temperature, humidity, time, etc., to optimize the quality and yield of yogurt.

[0091] The specific working principle of the present invention is as follows: the system and method regularly samples and detects raw milk through a raw milk sampling module and a raw milk detection module, diverts and stores raw milk through a raw milk diversion module, and uploads raw milk data to a cloud platform through a raw milk data acquisition module and a raw milk data transmission module; receives and distributes raw milk through a raw milk receiving module, sterilizes raw milk at high temperature through a raw milk sterilization module, mixes raw milk in proportion and adds additives through a raw milk blending module, and uploads raw milk processing data to a cloud platform through a raw milk processing data acquisition module and a raw milk processing data transmission module; inoculates raw milk with lactic acid bacteria through a yogurt inoculation module, and ferments the inoculated raw milk through a yogurt fermentation module. Fermentation is carried out at a constant temperature and humidity, the quality of the fermented yogurt is inspected by a yogurt detection module, qualified and unqualified yogurt are sorted by a yogurt sorting module, and relevant data of the yogurt are uploaded to the cloud platform part through a yogurt data acquisition module and a yogurt data transmission module; the yogurt is filled and capped by a yogurt filling module, and relevant filling data is uploaded to the cloud platform part by a filling data acquisition module and a filling data storage module; the cloud platform part stores and backs up the system data through a data storage module, analyzes and mines the system data through a data analysis module, visualizes and generates reports for the system data through a data display module, and calculates the system data through a data application module to obtain a yield model and a yogurt quality index.

[0092] It should be noted that, in this article, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. Specific examples are used in this article to illustrate the principles and implementation methods of the technical solution of the present application. The above examples are only used to help understand the method of the present application and its core idea. The above is only a preferred implementation method of the present application. It should be pointed out that due to the limitations of textual expression and the objective existence of infinite specific structures, for ordinary technicians in this technical field, without departing from the principles of the present application, several improvements, modifications or changes can be made, and the above technical features can be combined in an appropriate manner; these improvements, modifications, changes or combinations, or the direct application of the patent concept and technical solution to other occasions without improvement, should be regarded as the scope of protection of the present application.

Claims

1. A yogurt product production line processing monitoring method based on artificial intelligence, characterized in that: The method is implemented by an artificial intelligence-based yogurt product assembly line processing monitoring system, which includes: The raw milk collection and monitoring module includes a raw milk sampling module, a raw milk detection module, a raw milk diversion module, a raw milk data acquisition module and a raw milk data transmission module. This part regularly samples and detects the raw milk through the raw milk sampling module and the raw milk detection module, diverts and stores the raw milk through the raw milk diversion module, and uploads the raw milk data to the cloud platform through the raw milk data acquisition module and the raw milk data transmission module; The raw milk processing monitoring module includes a raw milk receiving module, a raw milk sterilization module, a raw milk blending module, a raw milk processing data acquisition module and a raw milk processing data transmission module. This part receives and distributes the raw milk through the raw milk receiving module, sterilizes the raw milk at high temperature through the raw milk sterilization module, blends and adds additives to the raw milk in proportion through the raw milk blending module, and uploads the raw milk processing data to the cloud platform through the raw milk processing data acquisition module and the raw milk processing data transmission module; Yogurt fermentation monitoring module, which includes a yogurt inoculation module, a yogurt fermentation module, a yogurt detection module, a yogurt sorting module, a yogurt data acquisition module and a yogurt data transmission module. This part inoculates lactic acid bacteria into raw milk through the yogurt inoculation module, ferments the inoculated raw milk at a constant temperature and humidity through the yogurt fermentation module, performs quality inspection on the fermented yogurt through the yogurt detection module, sorts qualified and unqualified yogurt through the yogurt sorting module, and uploads relevant data of yogurt to the cloud platform through the yogurt data acquisition module and the yogurt data and transmission module; Yogurt filling monitoring module, which includes a yogurt filling module, a filling data acquisition module and a filling data transmission module. This part fills and caps the yogurt through the yogurt filling module, and uploads the relevant filling data to the cloud platform part through the filling data acquisition module and the filling data transmission module; The cloud platform part includes a data storage module, a data analysis module, a data display module, and a data application module. This part stores and backs up the system data through the data storage module, analyzes the system data through the data analysis module, generates visual reports for the system data through the data display module, and optimizes the system data and provides decision support through the data application module; The raw milk collection monitoring module, the raw milk processing monitoring module, the yogurt fermentation monitoring module, and the yogurt filling monitoring module are connected in sequence, and the cloud platform part transmits data with the raw milk collection monitoring module, the raw milk processing monitoring module, the yogurt fermentation monitoring module, and the yogurt filling monitoring module respectively. The above data transmission is transmitted through the Internet of Things, and the PLC control system is used between the modules to realize automatic parameter adjustment, process control, and result feedback; The raw milk sampling module includes a sampling robot, a sampler and a raw milk storage tank. The sampling robot extracts a set amount of raw milk from the raw milk storage tank according to the set sampling time and frequency. The sampler packs the raw milk sample into a sampling bottle and sends the sampling bottle to the raw milk detection module. The raw milk detection module takes out a preset amount of raw milk sample from the sampling bottle according to the preset detection items and standards, and performs physical, chemical and microbiological tests on the raw milk sample, including density, fat content, protein content, lactic acid bacteria content, antibiotic residue, and harmful microorganism content. The test results are uploaded to the cloud platform part through the raw milk data acquisition module and the raw milk data transmission module. The raw milk diversion module includes a diversion robot and a diversion valve. The diversion robot sends qualified raw milk samples back to the raw milk storage tank according to the test results, and sends unqualified raw milk samples to the waste treatment equipment. The diversion valve controls the flow direction of the raw milk according to the test results, and sends qualified raw milk to the raw milk processing monitoring module, and sends unqualified raw milk to the waste treatment equipment. The raw milk receiving module includes a receiving robot and a receiving valve. The receiving robot receives a fixed amount of raw milk from the raw milk storage tank according to a preset receiving time and quantity. The receiving valve controls the flow of the raw milk and delivers the raw milk to the raw milk sterilization module. The raw milk sterilization module controls the sterilization equipment to sterilize the raw milk according to a preset sterilization temperature and time. The sterilized raw milk uploads sterilization data to the cloud platform part through the raw milk processing data acquisition module and the raw milk processing data transmission module, and is delivered to the raw milk blending module. The sterilization time of the raw milk sterilization module is determined by the following formula: ,in, For sterilization time, is the initial number of microorganisms in raw milk, is the number of microorganisms remaining after sterilization. is the sterilization rate constant; The raw milk blending module blends and adds additives to the raw milk in proportion according to the preset blending ratio and types of additives. The blended raw milk is uploaded to the cloud platform through the raw milk processing data acquisition module and the raw milk processing data transmission module, and then transmitted to the yogurt fermentation monitoring module. The yogurt inoculation module inoculates the raw milk with lactic acid bacteria according to the preset inoculation amount and lactic acid bacteria type, and the raw milk after inoculation uploads the inoculation data to the cloud platform part through the yogurt data acquisition module and the yogurt data transmission module, and transmits it to the yogurt fermentation module; the yogurt fermentation module ferments the raw milk according to the preset fermentation temperature, humidity and time, and the fermented yogurt is detected by the yogurt detection module to obtain the detection result, which includes the yogurt temperature, pH value, lactic acid bacteria content, coagulation time and coagulation degree before and after fermentation, and the fermentation data is uploaded to the cloud platform part through the yogurt data acquisition module and the yogurt data transmission module; The fermentation temperature, humidity and time of the yogurt fermentation module are determined by the following formula: in, is the fermentation temperature, For fermentation humidity, is the fermentation time, is the number of lactic acid bacteria after fermentation, is the number of lactic acid bacteria inoculated, is the growth rate of lactic acid bacteria, is the type of k-th lactic acid bacteria, and is a function of fermentation temperature and humidity, respectively, given by the following formulas: in, is the temperature coefficient of the kth bacterial species, is the humidity coefficient of the kth bacterial species, is the ambient temperature, is the ambient humidity; The yogurt sorting module controls the flow direction of the yogurt according to the detection results, and conveys the qualified yogurt to the yogurt filling monitoring module, and conveys the unqualified yogurt to the waste treatment equipment; the yogurt filling module fills and caps the yogurt according to the preset filling volume and filling container, and the yogurt after filling uploads the filling data to the cloud platform part through the filling data acquisition module and the filling data transmission module, and conveys it to the packaging equipment; The method comprises the following steps: S1 Raw milk monitoring: Raw milk is sampled and tested, including density, fat content, protein content, lactic acid bacteria content, antibiotic residues, and harmful microorganisms. According to the national food safety standard: fermented milk is judged to be qualified. Qualified raw milk is transported to the next step, and unqualified raw milk is transported to waste treatment facilities and the collected data is transmitted to the cloud platform; S2 Raw milk processing: sterilize and blend qualified raw milk. The data collection module collects data including raw milk temperature, pressure, flow, total colony count before and after sterilization, raw milk density, fat content, protein content, and lactic acid bacteria content before and after blending. The processed raw milk is transported to the next step and the collected data is transmitted to the cloud platform. S3 Fermentation: Inoculate and ferment the processed raw milk, and test the fermented yogurt, including the yogurt temperature before and after inoculation, pH value, type and amount of additives, density, fat content, protein content, lactic acid bacteria content, organic acid content, water content, and harmful microorganism content. The collected data is transmitted to the cloud platform, and the yogurt is judged to be qualified according to the national food safety standard: fermented milk. Qualified yogurt is sent to the next step; S4 Yogurt filling: Fill and cap qualified yogurt and transmit filling data to the cloud platform; S5 Result display The cloud platform performs data analysis based on the received data, and the analysis results are fed back to the yogurt fermentation module in the form of control signals through the data application module to adjust parameters, establish a yogurt production model, and calculate the quality index of yogurt, and the analysis results and feedback results are displayed to users in the form of charts; S3 fermentation includes the following steps: S31 inoculation: according to the requirements of different yogurt specifications, the inoculation amount and lactic acid bacteria type are set, the raw milk is inoculated, the inoculation data is uploaded to the cloud platform, and the inoculated raw materials are transported to the yogurt fermentation module; S32 fermentation, according to the set fermentation temperature, humidity and time, the inoculated raw milk is fermented, and the yogurt temperature, pH value, lactic acid bacteria content, density, fat content, protein content, lactic acid bacteria content, organic acid content, water content, harmful microorganism content are collected in real time, and the fermentation data is uploaded to the cloud platform. After the cloud platform analyzes the data, the data application module adjusts the fermentation temperature, humidity and fermentation time through the decision-making model to control the signal feedback to the yogurt fermentation module, and the fermentation temperature, humidity and time are adjusted in real time. The fermented yogurt is tested, including pH value, additive type and amount, density, fat content, protein content, lactic acid bacteria content, organic acid content, water content, harmful microorganism content, to determine whether it meets the national food safety standard: fermented milk; S33 Yogurt diversion: Control the flow direction of yogurt according to the test results, transport qualified yogurt to the yogurt filling monitoring module, and transport unqualified yogurt to the waste treatment equipment; The decision model is expressed as: in, is the decision parameter, T, pH, L and D are the temperature, pH value, lactic acid bacteria content and density of yogurt respectively, and y indicates whether the fermentation parameters need to be adjusted.

2. The artificial intelligence-based yogurt product production line processing monitoring method according to claim 1, characterized in that: The cloud platform data storage module receives and stores the transmission data of the raw milk data transmission module, the yogurt data transmission module, and the filling data transmission module; the data analysis module analyzes and processes the data; the data application module feeds back the results of the data analysis to the yogurt fermentation module in the form of a control signal, establishes a production model, and calculates the quality index of the yogurt; the data display module displays the results of the data analysis, the production model, the quality index, and the results after feedback control to the customer in the form of charts.

3. The artificial intelligence-based yogurt product production line processing monitoring method according to claim 2 is characterized in that: The production model is expressed as: in, is the intercept term, arrive is the regression coefficient, is the error term, is the yogurt production, It is a factor that affects the yield of yogurt; the quality index of the yogurt is expressed as: Where P is protein content, F is fat content, A is acidity, V is viscosity, and N is the total number of colonies. is the weight coefficient.

Citation Information

Patent Citations

  • SYSTEM FOR LOCAL OR REMOTE MONITORING OF MILK STORED ON FARMS AND RELATED OPERATIONS

    BR102019012348A2

  • Method for quantitatively evaluating quality of dairy products

    CN101718772A

  • Sensory evaluation method for predicting fermented yogurt based on BP neural network

    CN101793886A

  • Filled milk production monitoring method and management system

    CN116700183A

  • Device for dosing and filling of liquid or pastry products expecially for filling sorted products, for e.g. fruit yoghurt or similar, preferably on multi-way aseptic machines

    EP0582955A1