Intelligent control method and system for monosodium glutamate production equipment

Abstract

The present invention relates to an intelligent control method and system for monosodium glutamate production equipment, belonging to the technical field of food production and processing equipment, obtaining the occupied area of ​​the monosodium glutamate production site, determining multiple sensors connected to each distributed IO device in the two-dimensional grid coordinate system, obtaining the point cloud data of the monosodium glutamate production equipment and multiple sensors, constructing a digital simulation model of the monosodium glutamate production equipment, obtaining multiple key parameters of monosodium glutamate crystallization based on the digital simulation model and calculating the supersaturation, obtaining the supersaturation of the current crystallization process, and calculating and cascading the supersaturation of the current crystallization process by setting a PID controller and a fuzzy controller in the digital simulation model to generate a final control scheme for the monosodium glutamate production equipment. The present invention can perform online detection and automatic control of key process parameters of the monosodium glutamate production crystallization process, realize intelligent control of the monosodium glutamate production crystallization process, and improve product quality.

Description

Technical Field

[0001] The present invention relates to the technical field of food production and processing equipment, and in particular to an intelligent control method and system for monosodium glutamate production equipment. Background Art

[0002] MSG, also known as sodium monosodium glutamate, is a commonly used condiment. It is a sodium salt compound of the natural amino acid glutamic acid. It is usually in the form of colorless to white crystals. Its main component is sodium glutamate. Glutamic acid is a common amino acid in artificial and natural foods. It can enhance the umami taste of food and improve the taste performance. In the production process of MSG, decolorization, concentration and crystallization are the key links to determine the quality of MSG. However, the existing MSG production equipment lacks accurate and efficient automatic control of the decolorization and crystallization process of MSG production resin through key process parameters such as concentration, flow rate and material hammer. It is impossible to accurately achieve the coordinated control effect of supersaturation and liquid level in the crystallization process, resulting in large errors in supersaturation and liquid level in the crystallization process of MSG production, which makes it difficult for the produced MSG to meet the expected requirements and poor production quality. It requires re-production, which is time-consuming and labor-intensive, and increases labor cost output. In addition, due to the error, the energy consumption of equipment operation is increased, which is not conducive to environmental protection, sustainable development and production concepts. Therefore, it is urgent to study and develop an online intelligent control method and system for the crystallization process of MSG production to solve the above problems. Summary of the invention

[0003] The present invention overcomes the deficiencies of the prior art and provides an intelligent control method and system for monosodium glutamate production equipment.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] The first aspect of the present invention provides an intelligent control method for monosodium glutamate production equipment, comprising the following steps:

[0006] Acquire the occupied area of ​​the monosodium glutamate production site, construct a two-dimensional grid coordinate system based on the occupied area, and determine a plurality of sensors connected to each distributed IO device in the two-dimensional grid coordinate system;

[0007] Acquire point cloud data of the monosodium glutamate production equipment and the plurality of sensors, construct a digital simulation model of the point cloud data using digital simulation software, and obtain a digital simulation model of the monosodium glutamate production equipment;

[0008] Acquire multiple key process parameters of MSG crystallization based on the digital simulation model, and calculate supersaturation according to the multiple key process parameters of MSG crystallization to obtain current crystallization supersaturation;

[0009] By setting a PID controller and a fuzzy controller in the digital simulation model to calculate the current crystallization supersaturation, an optimal supersaturation control scheme and an optimal liquid level control scheme are obtained, and the optimal supersaturation control scheme and the optimal liquid level control scheme are cascade-controlled to generate a final control scheme for the monosodium glutamate production equipment.

[0010] Furthermore, in a preferred embodiment of the present invention, the method of obtaining the occupied area of ​​the MSG production site, constructing a two-dimensional grid coordinate system based on the occupied area, and determining a plurality of sensors connected to each distributed IO device in the two-dimensional grid coordinate system specifically includes the following steps:

[0011] Acquire the occupied area of ​​the monosodium glutamate production site, divide the occupied area into a plurality of sub-areas, construct a two-dimensional grid coordinate system, import the plurality of sub-areas into the two-dimensional grid coordinate system, and obtain coordinate information of each sub-area;

[0012] Acquire the actual occupied area of ​​the monosodium glutamate production equipment, define the actual occupied area as an overlapping range, import the overlapping range into the two-dimensional grid coordinate system for fitting, and obtain coordinate information of the sub-area within the overlapping range;

[0013] Obtaining installation points of a plurality of distributed IO devices in the occupied area, and obtaining signal transmission ranges of the plurality of distributed IO devices, extracting corresponding sub-areas in the two-dimensional grid coordinate system based on the plurality of installation points, obtaining corresponding sub-areas of the plurality of distributed IO devices, and obtaining coordinate information of the plurality of distributed IO devices according to the coordinate information of each sub-area;

[0014] Taking the coordinate information of each of the distributed IO devices as the center point, and calculating the Euclidean distance between each of the center points and the coordinate information of the sub-area within the overlapping range in a two-dimensional grid coordinate system based on the signal transmission range, to obtain multiple Euclidean distances;

[0015] A Euclidean distance threshold is preset, and if a plurality of the Euclidean distances are greater than the Euclidean distance threshold, the corresponding Euclidean distances are marked to determine a plurality of sensors connected to each distributed IO device.

[0016] Furthermore, in a preferred embodiment of the present invention, the step of obtaining the point cloud data of the MSG production equipment and the plurality of sensors, constructing a digital simulation model of the point cloud data using digital simulation software, and obtaining a digital simulation model of the MSG production equipment specifically includes the following steps:

[0017] Scanning the MSG production equipment with structured light and projecting structured light patterns of multiple sensors to detect changes in surface patterns, generate different surface measurement points and calculate depth data of each measurement point, and obtain point cloud data of multiple patterns;

[0018] Based on the point cloud data, a plurality of corresponding texture information is extracted, a spatial three-dimensional model is constructed, the point cloud data of the plurality of textures are mapped to the model vertices of the spatial three-dimensional model, and the plurality of texture information is interpolated and fitted in the mapped spatial three-dimensional model to obtain a three-dimensional model of a monosodium glutamate production equipment and a plurality of three-dimensional models of sensors;

[0019] The three-dimensional model of the monosodium glutamate production equipment is fitted with a plurality of three-dimensional models of the sensors through digital simulation software to obtain a digital simulation model of the monosodium glutamate production equipment.

[0020] Furthermore, in a preferred embodiment of the present invention, the method of obtaining a plurality of key process parameters of MSG crystallization based on the digital simulation model, and calculating supersaturation according to the plurality of key process parameters of MSG crystallization to obtain the current crystallization supersaturation specifically includes the following steps:

[0021] Inputting relevant parameters of MSG production and crystal boiling into the digital simulation model to simulate the MSG crystallization process, collecting simulation data of the MSG production and crystal boiling process through multiple sensors, and transmitting the data to the data center of the distributed IO device for conversion, thereby obtaining multiple key process parameters of MSG crystal boiling;

[0022] Acquire the concentration parameter in the crystallization tank in the current digital simulation model, introduce a multivariate regression analysis algorithm to calculate and analyze the influence of multiple key process parameters on the concentration parameter, define multiple key process parameters as independent variables, define the concentration parameter as a dependent variable, and construct a linear regression model based on the independent variable and the dependent variable;

[0023] Introducing the least square method to estimate the regression coefficient of the linear regression model, setting the multiple independent variables as observed values, calculating the residuals between the observed values ​​and the predicted values, and obtaining multiple regression coefficients;

[0024] Determine whether each of the regression coefficients is greater than a preset regression coefficient. If so, the key parameter corresponding to the regression coefficient has a greater influence on the concentration parameter. One or more key process parameters corresponding to the regression coefficients are extracted and integrated to obtain a key process parameter set.

[0025] A method for calculating the supersaturation of MSG crystallization is obtained based on a big data network, the supersaturation calculation method is analyzed to obtain necessary calculation conditions, key process parameters that meet the necessary calculation conditions are screened out from the key process parameter set to obtain multiple key calculation parameters, and the multiple key calculation parameters are substituted into the supersaturation calculation method for calculation to obtain the current crystallization supersaturation.

[0026] Furthermore, in a preferred embodiment of the present invention, the current crystallization supersaturation is calculated by setting a PID controller and a fuzzy controller in the digital simulation model to obtain an optimal supersaturation control scheme and an optimal liquid level control scheme, and the optimal supersaturation control scheme and the optimal liquid level control scheme are cascade-controlled to generate a final control scheme for the monosodium glutamate production equipment, which specifically includes the following steps:

[0027] In the digital simulation model, a PID controller is added to simulate the supersaturation control of the MSG crystallization process, and the initial parameters of the PID controller are obtained. The Ziegler-Nichols method is introduced to adjust the initial parameters of the PID controller, and the integral time and differential time of the initial parameters are set to 0 to obtain the initial proportional time.

[0028] Based on the starting proportional time, gradually increase the proportional gain until the PID controller system has continuous oscillation and record the critical value and the period, obtain the current critical gain and the current oscillation period, calculate the preliminary data of the proportional gain, the integral time and the differential time according to the current critical gain and the current oscillation period, and obtain the PID control data set;

[0029] Fine-tune and optimize the PID control data set according to the current crystallization supersaturation to obtain an optimal supersaturation control solution;

[0030] A fuzzy controller is added to the digital simulation model to control the liquid level in the crystallization tank, and multiple liquid level error parameters and multiple liquid level change rates are extracted from the simulation data of the digital simulation model, and the membership degrees of the multiple liquid level error parameters and the multiple liquid level change rates are calculated and transformed by a Gaussian membership function to generate multiple liquid level fuzzy sets;

[0031] Based on the fuzzy logic reasoning method, multiple liquid level fuzzy sets are inferred to obtain multiple fuzzy output quantities, and the weighted average method is simultaneously introduced to perform defuzzification operations on the multiple fuzzy output quantities and integrate them to obtain the optimal liquid level control solution;

[0032] The optimal supersaturation control scheme and the optimal liquid level control scheme are combined into a cascade control structure through cascade control to obtain a final control scheme for the monosodium glutamate production equipment.

[0033] Furthermore, in a preferred embodiment of the present invention, the optimal supersaturation control scheme and the optimal liquid level control scheme are combined into a cascade control structure through cascade control to obtain a final control scheme for the monosodium glutamate production equipment, which specifically includes the following steps:

[0034] A cascade controller is set up based on a digital simulation model to coordinate the supersaturation and liquid level in the MSG crystallization process;

[0035] Preset a supersaturation threshold, calculate the difference between the supersaturation of crystallization at a preset time node and the supersaturation threshold based on the optimal supersaturation control scheme, obtain a supersaturation deviation value, and analyze and calculate the supersaturation deviation value through the PID controller to obtain an expected liquid level value;

[0036] Based on the optimal liquid level control scheme, the actual liquid level value of the crystallization tank at a preset time node is obtained, and the difference between the actual liquid level value and the expected liquid level value is calculated to obtain a liquid level deviation value;

[0037] Based on the fuzzy controller, the liquid level deviation value is mapped to the output control quantity to obtain one or more fuzzy output control quantities. According to the fuzzy rule base, the one or more fuzzy output control quantities are calculated and combined to form a cascade structure, and finally the final control plan for the monosodium glutamate production equipment is obtained.

[0038] A second aspect of the present invention provides an intelligent control system for monosodium glutamate production equipment, the intelligent control system for monosodium glutamate production equipment comprising a memory and a processor, the memory storing an intelligent control method program for monosodium glutamate production equipment, and when the intelligent control method program for monosodium glutamate production equipment is executed by the processor, the following steps are implemented:

[0039] Acquire the occupied area of ​​the monosodium glutamate production site, construct a two-dimensional grid coordinate system based on the occupied area, and determine a plurality of sensors connected to each distributed IO device in the two-dimensional grid coordinate system;

[0040] Acquire point cloud data of the monosodium glutamate production equipment and the plurality of sensors, construct a digital simulation model of the point cloud data using digital simulation software, and obtain a digital simulation model of the monosodium glutamate production equipment;

[0041] Acquire multiple key process parameters of MSG crystallization based on the digital simulation model, and calculate supersaturation according to the multiple key process parameters of MSG crystallization to obtain current crystallization supersaturation;

[0042] By setting a PID controller and a fuzzy controller in the digital simulation model to calculate the current crystallization supersaturation, an optimal supersaturation control scheme and an optimal liquid level control scheme are obtained, and the optimal supersaturation control scheme and the optimal liquid level control scheme are cascade-controlled to generate a final control scheme for the monosodium glutamate production equipment.

[0043] Furthermore, in a preferred embodiment of the present invention, the current crystallization supersaturation is calculated by setting a PID controller and a fuzzy controller in the digital simulation model to obtain an optimal supersaturation control scheme and an optimal liquid level control scheme, and the optimal supersaturation control scheme and the optimal liquid level control scheme are cascade-controlled to generate a final control scheme for the monosodium glutamate production equipment, which specifically includes the following steps:

[0044] In the digital simulation model, a PID controller is added to simulate the supersaturation control of the MSG crystallization process, and the initial parameters of the PID controller are obtained. The Ziegler-Nichols method is introduced to adjust the initial parameters of the PID controller, and the integral time and differential time of the initial parameters are set to 0 to obtain the initial proportional time.

[0045] Based on the starting proportional time, gradually increase the proportional gain until the PID controller system has continuous oscillation and record the critical value and the period, obtain the current critical gain and the current oscillation period, calculate the preliminary data of the proportional gain, the integral time and the differential time according to the current critical gain and the current oscillation period, and obtain the PID control data set;

[0046] Fine-tune and optimize the PID control data set according to the current crystallization supersaturation to obtain an optimal supersaturation control solution;

[0047] A fuzzy controller is added to the digital simulation model to control the liquid level in the crystallization tank, and multiple liquid level error parameters and multiple liquid level change rates are extracted from the simulation data of the digital simulation model, and the membership degrees of the multiple liquid level error parameters and the multiple liquid level change rates are calculated and transformed by a Gaussian membership function to generate multiple liquid level fuzzy sets;

[0048] Based on the fuzzy logic reasoning method, multiple liquid level fuzzy sets are inferred to obtain multiple fuzzy output quantities, and the weighted average method is simultaneously introduced to perform defuzzification operations on the multiple fuzzy output quantities and integrate them to obtain the optimal liquid level control solution;

[0049] The optimal supersaturation control scheme and the optimal liquid level control scheme are combined into a cascade control structure through cascade control to obtain a final control scheme for the monosodium glutamate production equipment.

[0050] The present invention solves the technical defects existing in the background technology, and the beneficial technical effects of the present invention are:

[0051] The occupied area of ​​the monosodium glutamate production site is obtained, multiple sensors connected to each distributed IO device are determined in the two-dimensional grid coordinate system, the point cloud data of the monosodium glutamate production equipment and the multiple sensors are obtained, and a digital simulation model of the monosodium glutamate production equipment is constructed. Based on the digital simulation model, multiple key parameters of monosodium glutamate crystallization are obtained and supersaturation is calculated to obtain the supersaturation of the current crystallization process. The supersaturation of the current crystallization process is calculated by setting a PID controller and a fuzzy controller in the digital simulation model to obtain the optimal supersaturation control scheme and the optimal liquid level control amount, and the optimal supersaturation control scheme and the optimal liquid level control amount are cascade-controlled to generate the final control scheme of the monosodium glutamate production equipment. The present invention can perform online detection and automatic control of the key process parameters of the monosodium glutamate production crystallization process, realize intelligent control of the monosodium glutamate production crystallization process, and improve production efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0053] Figure 1 A first method flow chart of an intelligent control method for monosodium glutamate production equipment is shown;

[0054] Figure 2 A second method flow chart of an intelligent control method for monosodium glutamate production equipment is shown;

[0055] Figure 3 A third method flow chart of an intelligent control method for monosodium glutamate production equipment is shown;

[0056] Figure 4 The system framework diagram of an intelligent control system for monosodium glutamate production equipment is shown. DETAILED DESCRIPTION

[0057] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0058] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0059] The first aspect of the present invention provides an intelligent control method for a monosodium glutamate production equipment. Figure 1 As shown, the following steps are included:

[0060] S102: Acquire the occupied area of ​​the MSG production site, construct a two-dimensional grid coordinate system based on the occupied area, and determine a plurality of sensors connected to each distributed IO device in the two-dimensional grid coordinate system;

[0061] S104: acquiring point cloud data of the MSG production equipment and the plurality of sensors, and constructing a digital simulation model of the point cloud data using digital simulation software to obtain a digital simulation model of the MSG production equipment;

[0062] S106: acquiring a plurality of key process parameters for crystallization of monosodium glutamate based on the digital simulation model, and calculating supersaturation according to the plurality of key process parameters for crystallization of monosodium glutamate to obtain current crystallization supersaturation;

[0063] S108: By setting a PID controller and a fuzzy controller in the digital simulation model to calculate the current crystallization supersaturation, an optimal supersaturation control scheme and an optimal liquid level control scheme are obtained, and the optimal supersaturation control scheme and the optimal liquid level control scheme are cascade-controlled to generate a final control scheme for the monosodium glutamate production equipment.

[0064] Furthermore, in a preferred embodiment of the present invention, the method of obtaining the occupied area of ​​the MSG production site, constructing a two-dimensional grid coordinate system based on the occupied area, and determining a plurality of sensors connected to each distributed IO device in the two-dimensional grid coordinate system specifically includes the following steps:

[0065] Acquire the occupied area of ​​the monosodium glutamate production site, divide the occupied area into a plurality of sub-areas, construct a two-dimensional grid coordinate system, import the plurality of sub-areas into the two-dimensional grid coordinate system, and obtain coordinate information of each sub-area;

[0066] Acquire the actual occupied area of ​​the monosodium glutamate production equipment, define the actual occupied area as an overlapping range, import the overlapping range into the two-dimensional grid coordinate system for fitting, and obtain coordinate information of the sub-area within the overlapping range;

[0067] Obtaining installation points of a plurality of distributed IO devices in the occupied area, and obtaining signal transmission ranges of the plurality of distributed IO devices, extracting corresponding sub-areas in the two-dimensional grid coordinate system based on the plurality of installation points, obtaining corresponding sub-areas of the plurality of distributed IO devices, and obtaining coordinate information of the plurality of distributed IO devices according to the coordinate information of each sub-area;

[0068] Taking the coordinate information of each of the distributed IO devices as the center point, and calculating the Euclidean distance between each of the center points and the coordinate information of the sub-area within the overlapping range in a two-dimensional grid coordinate system based on the signal transmission range, to obtain multiple Euclidean distances;

[0069] A Euclidean distance threshold is preset, and if a plurality of the Euclidean distances are greater than the Euclidean distance threshold, the corresponding Euclidean distances are marked to determine a plurality of sensors connected to each distributed IO device.

[0070] It should be noted that by adopting distributed IO technology, data acquisition and control signal output can be distributed, the reliability and flexibility of the MSG production equipment system can be improved, the efficiency and stability of data transmission in the key crystallization process can be ensured, and the wiring and maintenance costs can be reduced. Since the distributed IO devices are distributed at different positions of the MSG production equipment to connect the corresponding sensors, a number of coordinates are first generated in the occupied area of ​​the MSG production site through a two-dimensional coordinate system grid, and then the MSG production equipment is overlapped and fitted in the two-dimensional coordinate system grid. Since the overlapping area is the concentrated location of the sensors, the distributed IO devices should be set outside the overlapping area, so the coordinate search for this overlapping area is not performed. Then, according to the location of the distributed IO devices installed at the current production site and their signal transmission range, the corresponding connected sensors are found within the overlapping range. The Euclidean distance from the distributed IO device position coordinates to the several coordinates in the overlapping area of ​​its signal transmission range can be calculated. Finally, it is determined whether it meets the preset Euclidean distance threshold for one-to-one correspondence, so that the sensor connected to each distributed IO device can be determined. The present invention can accurately determine the sensor corresponding to each distributed IO device on the monosodium glutamate production equipment, thereby realizing data collection and control signal output of the monosodium glutamate production process, providing a data acquisition channel and support for intelligent control of the equipment, and having high reliability.

[0071] Furthermore, in a preferred embodiment of the present invention, the step of obtaining the point cloud data of the MSG production equipment and the plurality of sensors, constructing a digital simulation model of the point cloud data using digital simulation software, and obtaining a digital simulation model of the MSG production equipment specifically includes the following steps:

[0072] Scanning the MSG production equipment with structured light and projecting structured light patterns of multiple sensors to detect changes in surface patterns, generate different surface measurement points and calculate depth data of each measurement point, and obtain point cloud data of multiple patterns;

[0073] Based on the point cloud data, a plurality of corresponding texture information is extracted, a spatial three-dimensional model is constructed, the point cloud data of the plurality of textures are mapped to the model vertices of the spatial three-dimensional model, and the plurality of texture information is interpolated and fitted in the mapped spatial three-dimensional model to obtain a three-dimensional model of a monosodium glutamate production equipment and a plurality of three-dimensional models of sensors;

[0074] The three-dimensional model of the monosodium glutamate production equipment is fitted with a plurality of three-dimensional models of the sensors through digital simulation software to obtain a digital simulation model of the monosodium glutamate production equipment.

[0075] It should be noted that the texture information includes RGB color, texture trend, texture depth, etc. The three-dimensional model constructed by traditional three-dimensional software has poor details and needs to be manually drawn and calibrated. The modeling takes a long time, which is time-consuming and laborious. The constructed three-dimensional model is prone to errors, which affects the accuracy of the simulation. Therefore, the structured light scanning technology can be used to scan the MSG production equipment and sensors to obtain the point cloud data of the corresponding texture, and the texture mapping technology is used to fit the texture information contained in the point cloud data to the reconstructed three-dimensional model, so that the three-dimensional model is more realistic and detailed. Then, the three-dimensional model of the MSG production equipment and multiple sensor three-dimensional models are fitted by digital simulation software, and finally a digital simulation model of the MSG production resin decolorization is generated, which is used to provide a test basis for the acquisition of subsequent key process parameters. The present invention can construct a digital simulation model of the MSG production resin decolorization by structured light scanning counting, thereby realizing the simulation test operation of the MSG crystal boiling process, which is convenient for the staff to record and adjust the parameters, thereby improving the efficiency and accuracy of the intelligent regulation of the equipment.

[0076] Furthermore, in a preferred embodiment of the present invention, a plurality of key process parameters of MSG crystallization are obtained based on the digital simulation model, and supersaturation is calculated according to the plurality of key process parameters of MSG crystallization to obtain the current crystallization supersaturation, such as Figure 2 As shown, the specific steps include:

[0077] S202: Inputting relevant parameters of MSG production and crystal boiling into the digital simulation model to simulate the MSG crystallization process, collecting simulation data of the MSG production and crystal boiling process through multiple sensors, and transmitting the data to the data center of the distributed IO device for conversion, so as to obtain multiple key process parameters of MSG crystal boiling;

[0078] S204: obtaining the concentration parameter in the crystallization tank in the current digital simulation model, introducing a multivariate regression analysis algorithm to calculate and analyze the influence of multiple key process parameters on the concentration parameter, defining multiple key process parameters as independent variables, defining the concentration parameter as a dependent variable, and constructing a linear regression model based on the independent variables and the dependent variable;

[0079] S206: Introducing the least square method to estimate the regression coefficient of the linear regression model, setting the multiple independent variables as observed values, calculating the residuals between the observed values ​​and the predicted values, and obtaining multiple regression coefficients;

[0080] S208: Determine whether each regression coefficient is greater than a preset regression coefficient. If so, the key parameter corresponding to the regression coefficient has a greater impact on the concentration parameter. One or more key process parameters corresponding to the regression coefficients are extracted and integrated to obtain a key process parameter set.

[0081] S210: Obtain a method for calculating the supersaturation of MSG crystallization based on a big data network, analyze the supersaturation calculation method to obtain necessary calculation conditions, screen out key process parameters that meet the necessary calculation conditions from the key process parameter set, obtain multiple key calculation parameters, and substitute the multiple key calculation parameters into the supersaturation calculation method for calculation to obtain the current crystallization supersaturation.

[0082] It should be noted that the digital simulation model of monosodium glutamate production resin decolorization is used to simulate the monosodium glutamate production crystal boiling process. During the simulation process, many relevant process parameters will be generated, but there may be only one or several key process parameters that affect the crystallization supersaturation, and not all process parameters will affect the crystallization supersaturation. Therefore, it is necessary to calculate and infer the corresponding key process parameters that affect the crystallization supersaturation, so as to calculate the supersaturation of the crystallization process; multiple key parameters are obtained during the simulation process, and the key parameters include mother liquor concentration, paste hammer degree, material temperature, vacuum degree, etc. The influence of multiple key parameters on the concentration parameters in the current crystallization tank is calculated based on the multivariate regression analysis algorithm, and a linear regression model is constructed. At the same time, the regression coefficient of the linear regression model is estimated by combining the least squares method. The regression coefficient can evaluate the correlation between the supersaturation of the crystallization process and a certain key parameter, so as to determine the target key process parameters, and finally the corresponding key process parameters obtained are substituted into the supersaturation calculation method found in the big data network for calculation, and the supersaturation of the current crystallization process can be obtained. This method can determine the correlation between key process parameters that affect the supersaturation of the crystallization process and calculate the supersaturation of the current crystallization process, so as to determine the gap between the quality of the current monosodium glutamate production and the expected quality, improve the decision-making ability of the intelligent control of the monosodium glutamate production equipment, reduce the control error, and have high reliability.

[0083] Furthermore, in a preferred embodiment of the present invention, the current crystallization supersaturation is calculated by setting a PID controller and a fuzzy controller in the digital simulation model to obtain an optimal supersaturation control scheme and an optimal liquid level control scheme, and the optimal supersaturation control scheme and the optimal liquid level control scheme are cascade-controlled to generate a final control scheme for the monosodium glutamate production equipment, which specifically includes the following steps:

[0084] In the digital simulation model, a PID controller is added to simulate the supersaturation control of the MSG crystallization process, and the initial parameters of the PID controller are obtained. The Ziegler-Nichols method is introduced to adjust the initial parameters of the PID controller, and the integral time and differential time of the initial parameters are set to 0 to obtain the initial proportional time.

[0085] Based on the starting proportional time, gradually increase the proportional gain until the PID controller system has continuous oscillation and record the critical value and the period, obtain the current critical gain and the current oscillation period, calculate the preliminary data of the proportional gain, the integral time and the differential time according to the current critical gain and the current oscillation period, and obtain the PID control data set;

[0086] Fine-tune and optimize the PID control data set according to the current crystallization supersaturation to obtain an optimal supersaturation control solution;

[0087] A fuzzy controller is added to the digital simulation model to control the liquid level in the crystallization tank, and multiple liquid level error parameters and multiple liquid level change rates are extracted from the simulation data of the digital simulation model, and the membership degrees of the multiple liquid level error parameters and the multiple liquid level change rates are calculated and transformed by a Gaussian membership function to generate multiple liquid level fuzzy sets;

[0088] Based on the fuzzy logic reasoning method, multiple liquid level fuzzy sets are inferred to obtain multiple fuzzy output quantities, and the weighted average method is simultaneously introduced to perform defuzzification operations on the multiple fuzzy output quantities and integrate them to obtain the optimal liquid level control solution;

[0089] The optimal supersaturation control scheme and the optimal liquid level control scheme are combined into a cascade control structure through cascade control to obtain a final control scheme for the monosodium glutamate production equipment.

[0090] It should be noted that in the crystallization process, supersaturation and liquid level are key control parameters, which can directly determine whether the quality of MSG production meets the standards. The input and output control of crystallization supersaturation and liquid level can be accurately calculated and regulated by comprehensively using PID control, fuzzy control digital equipment and algorithms, thereby developing an automated program for intelligent control of the MSG crystallization process; supersaturation control is performed using a PID controller, and the initial parameters of the PID controller are adjusted by introducing the Ziegler-Nichols method. The Ziegler-Nichols method is a PID controller tuning method that is widely used in industrial control systems and can be used based on According to the current critical gain and the current oscillation period, the preliminary data of proportional gain, integral time and differential time are calculated to obtain a PID control data set, which can optimize and correct the supersaturation of the current crystallization process, so as to reach a suitable range and finally generate an optimal supersaturation control scheme; while the liquid level control is completed by using a fuzzy controller, and the output signal of the fuzzy controller is determined according to the error and change rate of the liquid level, and the fuzzy logic reasoning method is introduced to reason the liquid level fuzzy set to obtain the optimal liquid level control amount, and finally the cascade control algorithm is used to combine the optimal supersaturation control scheme and the optimal liquid level control amount to generate the final control scheme of the monosodium glutamate production equipment. The present invention can take supersaturation as the core control parameter, and comprehensively use PID, fuzzy control, cascade control and other control algorithms to realize the automatic coordinated control of supersaturation and liquid level in the crystallization process, effectively improve the quality of monosodium glutamate crystal production, and greatly reduce the occurrence of errors.

[0091] Furthermore, in a preferred embodiment of the present invention, the optimal supersaturation control scheme and the optimal liquid level control scheme are combined into a cascade control structure through cascade control to obtain the final control scheme of the monosodium glutamate production equipment, such as Figure 3 As shown, the specific steps include:

[0092] S302: Setting a cascade controller based on a digital simulation model to coordinately control the supersaturation and liquid level of the MSG crystallization process;

[0093] S304: preset a supersaturation threshold, calculate the difference between the supersaturation of crystallization at a preset time node and the supersaturation threshold based on the optimal supersaturation control scheme, obtain a supersaturation deviation value, and analyze and calculate the supersaturation deviation value through the PID controller to obtain an expected liquid level value;

[0094] S306: Based on the optimal liquid level control solution, the actual liquid level value of the crystallization tank at a preset time node is obtained, and the difference between the actual liquid level value and the expected liquid level value is calculated to obtain a liquid level deviation value;

[0095] S308: Based on the fuzzy controller, the liquid level deviation value is mapped to the output control quantity to obtain multiple fuzzy output control quantities, and the multiple fuzzy output control quantities are calculated and merged according to the fuzzy rule base to form a cascade structure, and finally the final control plan for the monosodium glutamate production equipment is obtained.

[0096] It should be noted that the PID controller and the fuzzy controller are usually two independent controllers. If a specific controller is not used to connect the two in series, the coordinated control of supersaturation and liquid level cannot be achieved, resulting in a significant reduction in the quality of monosodium glutamate production; the cascade controller is a control system structure that can connect the controllers in series in a specific order to achieve a more complex control target, so that the PID controller receives an input signal and provides an output signal as an input of the fuzzy controller, thereby achieving the coordination of supersaturation and liquid level; the cascade controller enables the PID controller to calculate the expected liquid level value of the optimal supersaturation control scheme, and then calculates the liquid level deviation value based on the optimal liquid level control scheme at a preset time node according to the obtained expected liquid level value, controls the fuzzy controller to perform fuzzy conversion of the liquid level deviation to a specific output control amount, and finally the cascade controller outputs multiple fuzzy output control amounts in series to obtain the final control scheme. The present invention can connect the obtained optimal supersaturation control scheme and the optimal liquid level control scheme in series in a specific order through the cascade controller, so that it can achieve the coordinated control between supersaturation and liquid level, thereby improving the precise control of the monosodium glutamate crystallization process, ensuring the production quality and efficiency of monosodium glutamate, and having high reliability.

[0097] In addition, the intelligent control method for monosodium glutamate production equipment further comprises the following steps:

[0098] Obtaining a process flow for the production and preparation of monosodium glutamate, and separately extracting a process flow for concentrating and crystallizing a monosodium glutamate mother liquor according to the process flow for the production and preparation of monosodium glutamate;

[0099] The process flow of the monosodium glutamate mother liquor concentration and crystallization is searched in the big data network to obtain several process requirements corresponding to the process flow of the monosodium glutamate mother liquor concentration and crystallization;

[0100] Analyze the several production requirements, search the big data network for monitoring configuration software that meets the several production requirements, and design the operator station interface through the graphic editing tool provided by the monitoring configuration software to obtain the operator human-machine interface;

[0101] Obtaining the underlying data source of the current monosodium glutamate production equipment, connecting the underlying data source to the operator workbench, and obtaining an interactive operator human-machine interface;

[0102] According to the optimal control scheme, the current monosodium glutamate production equipment is controlled and optimized to obtain the optimized monosodium glutamate production equipment, and the monosodium glutamate is actually produced based on the optimized monosodium glutamate production equipment, and the actual crystallization supersaturation is obtained;

[0103] Calculate the difference between the actual crystallization supersaturation and the actual crystallization supersaturation recorded by the monosodium glutamate production equipment before optimization to obtain a supersaturation deviation value, and determine whether the supersaturation deviation value is greater than a preset deviation value;

[0104] If it is greater than, the supersaturation deviation value is set as the alarm threshold value and uploaded to the interactive operator human-machine interface; if it is less than, the actual crystallization supersaturation is written into the production qualification log in the interactive operator human-machine interface and marked as green, and set as the comparison data of the next actual crystallization supersaturation.

[0105] It should be noted that, under normal circumstances, when the monosodium glutamate production equipment is in operation, a professional operator is required to monitor and adjust the data in real time so that the monosodium glutamate production can keep moving in the expected direction. However, at present, there is still a lack of a human-machine platform that is convenient for operators to manage the equipment on the monosodium glutamate production equipment, which makes the regulation rate slow, the operation is not ideal, and the production quality does not meet the requirements. The process requirements are the requirements required to be implemented and monitored in the monosodium glutamate production process. The present invention can construct an interactive operator human-machine interface through monitoring configuration software, and manage and alarm the actual crystallization supersaturation in the interactive human-machine interface, improve operating efficiency, convenience and safety, better help operators understand and manage equipment, achieve more optimized production and operation effects, and make accurate decisions.

[0106] In addition, the intelligent control method for monosodium glutamate production equipment further comprises the following steps:

[0107] Acquire multiple working mechanisms of the monosodium glutamate production equipment, and construct a prediction model based on the historical operation data corresponding to the multiple working mechanisms under different production environment combination conditions, and import the historical operation data corresponding to the multiple working mechanisms under different production environment combination conditions into the prediction model for training and optimization, so as to obtain a trained prediction model;

[0108] Acquire the real-time production environment of the monosodium glutamate production equipment, import the real-time production environment into the trained prediction model, and obtain the prediction operation data of the plurality of working mechanisms under the combination conditions of the real-time production environment;

[0109] Acquire actual operation data of each of the working mechanisms within a preset time period, calculate the Mahalanobis distance between each of the actual operation parameters and the predicted operation parameters, and obtain a plurality of Mahalanobis distances;

[0110] It is determined whether each Mahalanobis distance is greater than a preset Mahalanobis distance. If so, the working mechanism corresponding to the distance greater than the preset Mahalanobis distance is marked as a fault point.

[0111] It should be noted that during the actual operation of the monosodium glutamate production equipment, the equipment may fail due to wear and aging, so the equipment operation data can be predicted and compared with the actual data to determine whether the equipment fails. The present invention can accurately determine the equipment operation failure, thereby avoiding failures that affect the quality of monosodium glutamate production during equipment operation, and facilitates maintenance personnel to perform fault tracing, reduce the occurrence of failures, and improve the efficiency of monosodium glutamate production.

[0112] The second aspect of the present invention provides an intelligent control system for monosodium glutamate production equipment, the intelligent control system for monosodium glutamate production equipment comprising a memory 41 and a processor 42, the memory 41 stores an intelligent control method program for monosodium glutamate production equipment, and when the intelligent control method program for monosodium glutamate production equipment is executed by the processor 42, Figure 4 As shown, implement the following steps:

[0113] Acquire the occupied area of ​​the monosodium glutamate production site, construct a two-dimensional grid coordinate system based on the occupied area, and determine a plurality of sensors connected to each distributed IO device in the two-dimensional grid coordinate system;

[0114] Acquire point cloud data of the monosodium glutamate production equipment and the plurality of sensors, construct a digital simulation model of the point cloud data using digital simulation software, and obtain a digital simulation model of the monosodium glutamate production equipment;

[0115] Acquire multiple key process parameters of MSG crystallization based on the digital simulation model, and calculate supersaturation according to the multiple key process parameters of MSG crystallization to obtain current crystallization supersaturation;

[0116] By setting a PID controller and a fuzzy controller in the digital simulation model to calculate the current crystallization supersaturation, an optimal supersaturation control scheme and an optimal liquid level control scheme are obtained, and the optimal supersaturation control scheme and the optimal liquid level control scheme are cascade-controlled to generate a final control scheme for the monosodium glutamate production equipment.

[0117] Furthermore, in a preferred embodiment of the present invention, the current crystallization supersaturation is calculated by setting a PID controller and a fuzzy controller in the digital simulation model to obtain an optimal supersaturation control scheme and an optimal liquid level control scheme, and the optimal supersaturation control scheme and the optimal liquid level control scheme are cascade-controlled to generate a final control scheme for the monosodium glutamate production equipment, which specifically includes the following steps:

[0118] In the digital simulation model, a PID controller is added to simulate the supersaturation control of the MSG crystallization process, and the initial parameters of the PID controller are obtained. The Ziegler-Nichols method is introduced to adjust the initial parameters of the PID controller, and the integral time and differential time of the initial parameters are set to 0 to obtain the initial proportional time.

[0119] Based on the starting proportional time, gradually increase the proportional gain until the PID controller system has continuous oscillation and record the critical value and the period, obtain the current critical gain and the current oscillation period, calculate the preliminary data of the proportional gain, the integral time and the differential time according to the current critical gain and the current oscillation period, and obtain the PID control data set;

[0120] Fine-tune and optimize the PID control data set according to the current crystallization supersaturation to obtain an optimal supersaturation control solution;

[0121] A fuzzy controller is added to the digital simulation model to control the liquid level in the crystallization tank, and multiple liquid level error parameters and multiple liquid level change rates are extracted from the simulation data of the digital simulation model, and the membership degrees of the multiple liquid level error parameters and the multiple liquid level change rates are calculated and transformed by a Gaussian membership function to generate multiple liquid level fuzzy sets;

[0122] Based on the fuzzy logic reasoning method, multiple liquid level fuzzy sets are inferred to obtain multiple fuzzy output quantities, and the weighted average method is simultaneously introduced to perform defuzzification operations on the multiple fuzzy output quantities and integrate them to obtain the optimal liquid level control solution;

[0123] The optimal supersaturation control scheme and the optimal liquid level control scheme are combined into a cascade control structure through cascade control to obtain a final control scheme for the monosodium glutamate production equipment.

[0124] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An intelligent control method for monosodium glutamate production equipment, characterized in that: The following steps are involved: Acquire the occupied area of ​​the monosodium glutamate production site, construct a two-dimensional grid coordinate system based on the occupied area, and determine a plurality of sensors connected to each distributed IO device in the two-dimensional grid coordinate system; Acquire point cloud data of the monosodium glutamate production equipment and the plurality of sensors, construct a digital simulation model of the point cloud data using digital simulation software, and obtain a digital simulation model of the monosodium glutamate production equipment; Acquire multiple key process parameters of MSG crystallization based on the digital simulation model, and calculate supersaturation according to the multiple key process parameters of MSG crystallization to obtain current crystallization supersaturation; By setting a PID controller and a fuzzy controller in the digital simulation model to calculate the current crystallization supersaturation, an optimal supersaturation control scheme and an optimal liquid level control scheme are obtained, and the optimal supersaturation control scheme and the optimal liquid level control scheme are cascade-controlled to generate a final control scheme for the monosodium glutamate production equipment; The method comprises the following steps: calculating the current crystallization supersaturation by setting a PID controller and a fuzzy controller in the digital simulation model, obtaining an optimal supersaturation control scheme and an optimal liquid level control scheme, and cascadingly controlling the optimal supersaturation control scheme and the optimal liquid level control scheme to generate a final control scheme for the monosodium glutamate production equipment. In the digital simulation model, a PID controller is added to simulate the supersaturation control of the MSG crystallization process, and the initial parameters of the PID controller are obtained. The Ziegler-Nichols method is introduced to adjust the initial parameters of the PID controller, and the integral time and differential time of the initial parameters are set to 0 to obtain the initial proportional time. Based on the initial proportional time, gradually increase the proportional gain until the PID controller system has continuous oscillation and record the critical value and the period, obtain the current critical gain and the current oscillation period, calculate the preliminary data of the proportional gain, the integral time and the differential time according to the current critical gain and the current oscillation period, and obtain the PID control data set; Fine-tune and optimize the PID control data set according to the current crystallization supersaturation to obtain an optimal supersaturation control solution; A fuzzy controller is added to the digital simulation model to control the liquid level in the crystallization tank, and multiple liquid level error parameters and multiple liquid level change rates are extracted from the simulation data of the digital simulation model, and the membership degrees of the multiple liquid level error parameters and the multiple liquid level change rates are calculated and transformed by a Gaussian membership function to generate multiple liquid level fuzzy sets; Based on the fuzzy logic reasoning method, multiple liquid level fuzzy sets are inferred to obtain multiple fuzzy output quantities, and the weighted average method is simultaneously introduced to perform defuzzification operations on the multiple fuzzy output quantities and integrate them to obtain the optimal liquid level control solution; The optimal supersaturation control scheme and the optimal liquid level control scheme are combined into a cascade control structure through cascade control to obtain a final control scheme for the monosodium glutamate production equipment; The optimal supersaturation control scheme and the optimal liquid level control scheme are combined into a cascade control structure through cascade control to obtain the final control scheme of the monosodium glutamate production equipment, which specifically includes the following steps: A cascade controller is set up based on a digital simulation model to coordinate the supersaturation and liquid level in the MSG crystallization process; Preset a supersaturation threshold, calculate the difference between the supersaturation of crystallization at a preset time node and the supersaturation threshold based on the optimal supersaturation control scheme, obtain a supersaturation deviation value, and analyze and calculate the supersaturation deviation value through the PID controller to obtain an expected liquid level value; Based on the optimal liquid level control scheme, the actual liquid level value of the crystallization tank at a preset time node is obtained, and the difference between the actual liquid level value and the expected liquid level value is calculated to obtain a liquid level deviation value; Based on the fuzzy controller, the liquid level deviation value is mapped to the output control quantity to obtain one or more fuzzy output control quantities. According to the fuzzy rule base, the one or more fuzzy output control quantities are calculated and combined to form a cascade structure, and finally the final control plan for the monosodium glutamate production equipment is obtained.

2. The intelligent control method for monosodium glutamate production equipment according to claim 1, characterized in that: The method of obtaining the occupied area of ​​the MSG production site, constructing a two-dimensional grid coordinate system based on the occupied area, and determining a plurality of sensors connected to each distributed IO device in the two-dimensional grid coordinate system specifically includes the following steps: Acquire the occupied area of ​​the monosodium glutamate production site, divide the occupied area into a plurality of sub-areas, construct a two-dimensional grid coordinate system, import the plurality of sub-areas into the two-dimensional grid coordinate system, and obtain coordinate information of each sub-area; Acquire the actual occupied area of ​​the monosodium glutamate production equipment, define the actual occupied area as an overlapping range, import the overlapping range into the two-dimensional grid coordinate system for fitting, and obtain coordinate information of the sub-area within the overlapping range; Obtaining installation points of a plurality of distributed IO devices in the occupied area, and obtaining signal transmission ranges of the plurality of distributed IO devices, extracting corresponding sub-areas in the two-dimensional grid coordinate system based on the plurality of installation points, obtaining corresponding sub-areas of the plurality of distributed IO devices, and obtaining coordinate information of the plurality of distributed IO devices according to the coordinate information of each sub-area; Taking the coordinate information of each of the distributed IO devices as the center point, and calculating the Euclidean distance between each of the center points and the coordinate information of the sub-area within the overlapping range in a two-dimensional grid coordinate system based on the signal transmission range, to obtain multiple Euclidean distances; A Euclidean distance threshold is preset, and if a plurality of the Euclidean distances are greater than the Euclidean distance threshold, the corresponding Euclidean distances are marked to determine a plurality of sensors connected to each distributed IO device.

3. The intelligent control method for monosodium glutamate production equipment according to claim 1, characterized in that: The step of obtaining the point cloud data of the MSG production equipment and the plurality of sensors, and constructing a digital simulation model of the point cloud data using digital simulation software to obtain a digital simulation model of the MSG production equipment specifically includes the following steps: Scanning the MSG production equipment with structured light and projecting structured light patterns of multiple sensors to detect changes in surface patterns, generate different surface measurement points and calculate depth data of each measurement point, and obtain point cloud data of multiple patterns; Based on the point cloud data, a plurality of corresponding texture information is extracted, a spatial three-dimensional model is constructed, the point cloud data of the plurality of textures are mapped to the model vertices of the spatial three-dimensional model, and the plurality of texture information is interpolated and fitted in the mapped spatial three-dimensional model to obtain a three-dimensional model of a monosodium glutamate production equipment and a plurality of three-dimensional models of sensors; The three-dimensional model of the monosodium glutamate production equipment is fitted with a plurality of three-dimensional models of the sensors through digital simulation software to obtain a digital simulation model of the monosodium glutamate production equipment.

4. The intelligent control method for monosodium glutamate production equipment according to claim 1, characterized in that: The method of acquiring a plurality of key process parameters for monosodium glutamate crystallization based on the digital simulation model, and calculating supersaturation according to the plurality of key process parameters for monosodium glutamate crystallization to obtain current crystallization supersaturation specifically includes the following steps: Inputting relevant parameters of MSG production and crystal boiling into the digital simulation model to simulate the MSG crystallization process, collecting simulation data of the MSG production and crystal boiling process through multiple sensors, and transmitting the data to the data center of the distributed IO device for conversion, thereby obtaining multiple key process parameters of MSG crystal boiling; Acquire the concentration parameter in the crystallization tank in the current digital simulation model, introduce a multivariate regression analysis algorithm to calculate and analyze the influence of multiple key process parameters on the concentration parameter, define multiple key process parameters as independent variables, define the concentration parameter as a dependent variable, and construct a linear regression model based on the independent variable and the dependent variable; Introducing the least square method to estimate the regression coefficient of the linear regression model, setting the multiple independent variables as observed values, calculating the residuals between the observed values ​​and the predicted values, and obtaining multiple regression coefficients; Determine whether each of the regression coefficients is greater than a preset regression coefficient. If so, the key parameter corresponding to the regression coefficient has a greater influence on the concentration parameter. One or more key process parameters corresponding to the regression coefficients are extracted and integrated to obtain a key process parameter set. A method for calculating the supersaturation of MSG crystallization is obtained based on a big data network, the supersaturation calculation method is analyzed to obtain necessary calculation conditions, key process parameters that meet the necessary calculation conditions are screened out from the key process parameter set to obtain multiple key calculation parameters, and the multiple key calculation parameters are substituted into the supersaturation calculation method for calculation to obtain the current crystallization supersaturation.

5. An intelligent control system for monosodium glutamate production equipment, characterized in that: The intelligent control system of the monosodium glutamate production equipment comprises a memory and a processor, wherein the memory stores an intelligent control program of the monosodium glutamate production equipment, and when the intelligent control program of the monosodium glutamate production equipment is executed by the processor, the following steps are implemented: Acquire the occupied area of ​​the monosodium glutamate production site, construct a two-dimensional grid coordinate system based on the occupied area, and determine a plurality of sensors connected to each distributed IO device in the two-dimensional grid coordinate system; Acquire point cloud data of the monosodium glutamate production equipment and the plurality of sensors, construct a digital simulation model of the point cloud data using digital simulation software, and obtain a digital simulation model of the monosodium glutamate production equipment; Acquire multiple key process parameters of MSG crystallization based on the digital simulation model, and calculate supersaturation according to the multiple key process parameters of MSG crystallization to obtain current crystallization supersaturation; By setting a PID controller and a fuzzy controller in the digital simulation model to calculate the current crystallization supersaturation, an optimal supersaturation control scheme and an optimal liquid level control scheme are obtained, and the optimal supersaturation control scheme and the optimal liquid level control scheme are cascade-controlled to generate a final control scheme for the monosodium glutamate production equipment; The method comprises the following steps: calculating the current crystallization supersaturation by setting a PID controller and a fuzzy controller in the digital simulation model, obtaining an optimal supersaturation control scheme and an optimal liquid level control scheme, and cascadingly controlling the optimal supersaturation control scheme and the optimal liquid level control scheme to generate a final control scheme for the monosodium glutamate production equipment. In the digital simulation model, a PID controller is added to simulate the supersaturation control of the MSG crystallization process, and the initial parameters of the PID controller are obtained. The Ziegler-Nichols method is introduced to adjust the initial parameters of the PID controller, and the integral time and differential time of the initial parameters are set to 0 to obtain the initial proportional time. Based on the initial proportional time, gradually increase the proportional gain until the PID controller system has continuous oscillation and record the critical value and the period, obtain the current critical gain and the current oscillation period, calculate the preliminary data of the proportional gain, the integral time and the differential time according to the current critical gain and the current oscillation period, and obtain the PID control data set; Fine-tune and optimize the PID control data set according to the current crystallization supersaturation to obtain an optimal supersaturation control solution; A fuzzy controller is added to the digital simulation model to control the liquid level in the crystallization tank, and multiple liquid level error parameters and multiple liquid level change rates are extracted from the simulation data of the digital simulation model, and the membership degrees of the multiple liquid level error parameters and the multiple liquid level change rates are calculated and transformed by a Gaussian membership function to generate multiple liquid level fuzzy sets; Based on the fuzzy logic reasoning method, multiple liquid level fuzzy sets are inferred to obtain multiple fuzzy output quantities, and the weighted average method is simultaneously introduced to perform defuzzification operations on the multiple fuzzy output quantities and integrate them to obtain the optimal liquid level control solution; The optimal supersaturation control scheme and the optimal liquid level control scheme are combined into a cascade control structure through cascade control to obtain a final control scheme for the monosodium glutamate production equipment.

Images