Vinasse steaming and distilling process control method and device, storage medium and electronic equipment

Abstract

The invention provides a method and a device for controlling a process of feeding distillers' grains into a retort for distillation, a storage medium and electronic equipment, and is applied to the technical field of automation control. According to the method, by distinguishing different batches of vinasse material property data and steam thermal physical property data and inputting the data into the pre-trained retort feeding temperature field model, the temperature field data in the retort feeding process can be accurately predicted. Temperature field data and vinasse material property data are combined, so that the steaming height, timing, steam flow and pressure can be effectively controlled, and the steaming process is optimized. Thirdly, inputting the steaming end temperature field data and the vinasse material property data into the distillation wine taking model to obtain distillation wine taking data so as to control the steam flow and pressure in the distillation process and realize accurate control on the steaming process and the distillation process of the vinasse, so that the production efficiency and the vinasse quality stability of the solid-state-method white spirit are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of automation control technology, and in particular to a method, device, storage medium and electronic equipment for controlling a lees upper retort distillation process. Background Art

[0002] In baijiu production, the solid-state retorting and distillation process directly impacts yield and quality. As production demands grow, many distilleries are adopting mechanized retorting. While this improves efficiency, it lacks effective control over the height and timing of each retort, as well as steam pressure and flow rate, resulting in less-than-expected results.

[0003] Current research on baijiu retorting and distillation primarily focuses on device design and modification, with limited optimization results. For example, online liquor extraction methods based on near-infrared spectroscopy and steam detection during baijiu retorting using convolutional neural networks have been investigated. However, these studies fail to consider the differences in material properties between batches, often focus simulations on either the retorting or distillation process without comprehensively considering their interplay, and inadequately optimize steam flow and pressure.

[0004] Therefore, how to effectively control the steaming and distillation process of solid-state liquor to improve the production efficiency and quality stability of solid-state liquor has become a technical problem that technical personnel in this field urgently need to solve. Summary of the Invention

[0005] In view of the above problems, the present invention provides a method, device, storage medium and electronic device for controlling the distiller's grains retort distillation process to overcome or at least partially solve the above problems. The technical solution is as follows:

[0006] A method for controlling a distiller's grains retort distillation process, comprising:

[0007] Obtaining property data of a current batch of distiller's grains, wherein the property data of the distiller's grains includes thermophysical property data of the current batch of distiller's grains;

[0008] Obtaining steam thermophysical property data of the current batch;

[0009] Inputting the distiller's grains material property data, the distiller's grains thermophysical property data, and the steam thermophysical property data into a pre-trained upper retort temperature field model to obtain upper retort temperature field data output by the upper retort temperature field model, wherein the upper retort temperature field data includes upper retort process temperature field data and upper retort end temperature field data;

[0010] Using the temperature field data of the steaming process and the data on the properties of the lees material, control the steaming height, steaming timing, steam flow rate and steaming pressure of the steaming process of the current batch;

[0011] Inputting the upper steamer end temperature field data and the lees material property data into a pre-trained distillation wine extraction model to obtain distillation wine extraction data output by the distillation wine extraction model;

[0012] The distillation wine extraction data is used to control the steam flow and pressure of the distillation wine extraction process of the current batch.

[0013] A device for controlling a distiller's lees upper steamer distillation process comprises: a distiller's lees material property data acquisition unit, a steam thermophysical property data acquisition unit, an upper steamer temperature field data acquisition unit, an upper steamer process control unit, a distillation and wine extraction data acquisition unit, and a distillation and wine extraction process control unit.

[0014] The distiller's grains material property data obtaining unit is used to obtain distiller's grains material property data of a current batch, wherein the distiller's grains material property data includes distiller's grains thermophysical property data of the current batch of distiller's grains material;

[0015] The steam thermophysical property data obtaining unit is used to obtain the steam thermophysical property data of the current batch;

[0016] The upper steamer temperature field data acquisition unit is used to input the distiller's grains material property data, the distiller's grains thermophysical property data, and the steam thermophysical property data into a pre-trained upper steamer temperature field model to obtain upper steamer temperature field data output by the upper steamer temperature field model, wherein the upper steamer temperature field data includes upper steamer process temperature field data and upper steamer end temperature field data;

[0017] The steaming process control unit is used to control the steaming height, steaming timing, steam flow rate and steaming pressure of the steaming process of the current batch by using the temperature field data of the steaming process and the data on the properties of the lees material;

[0018] The distillation wine extraction data acquisition unit is used to input the upper steamer end temperature field data and the lees material property data into a pre-trained distillation wine extraction model to obtain the distillation wine extraction data output by the distillation wine extraction model;

[0019] The distillation and wine extraction process control unit is used to use the distillation and wine extraction data to control the steam flow and pressure of the distillation and wine extraction process of the current batch.

[0020] A computer-readable storage medium stores a program, which, when executed by a processor, implements the method for controlling the lees upper retort distillation process.

[0021] An electronic device comprising at least one processor, and at least one memory and bus connected to the processor; wherein the processor and the memory communicate with each other via the bus; and the processor is used to call program instructions in the memory to execute the method for controlling the lees upper steamer distillation process.

[0022] By means of the above technical solution, the method, device, storage medium and electronic device for controlling the distillation process of the lees upper steamer provided by the present invention obtain the lees material property data of the current batch, wherein the lees material property data includes the lees thermophysical property data of the lees material of the current batch; obtain the steam thermophysical property data of the current batch; input the lees material property data, the lees thermophysical property data and the steam thermophysical property data into a pre-trained upper steamer temperature field model, and obtain the upper steamer temperature field data output by the upper steamer temperature field model. , wherein the upper steamer temperature field data includes the upper steamer process temperature field data and the upper steamer end temperature field data; the upper steamer process temperature field data and the lees material property data are used to control the upper steamer height, upper steamer timing, upper steamer steam flow rate and upper steamer pressure of the upper steamer process of the current batch; the upper steamer end temperature field data and the lees material property data are input into a pre-trained distillation wine extraction model to obtain the distillation wine extraction data output by the distillation wine extraction model; the distillation wine extraction data is used to control the steam flow rate and pressure of the distillation wine extraction process of the current batch. The present invention can accurately predict the temperature field data of the upper steamer process by distinguishing the lees material property data and steam thermophysical property data of different batches and inputting them into the pre-trained upper steamer temperature field model. Combining the temperature field data and the lees material property data, the upper steamer height, timing, steam flow rate and pressure can be effectively controlled, thereby optimizing the upper steamer process. Next, the temperature field data at the end of steaming and the material property data of the lees are input into the distillation and wine extraction model to obtain the distillation and wine extraction data, so as to control the steam flow and pressure in the distillation process, and realize the precise control of the steaming process and distillation process of the lees, thereby effectively improving the production efficiency and quality stability of solid-state liquor.

[0023] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0025] Figure 1 A schematic flow chart showing an embodiment of a method for controlling a distiller's grains retort distillation process according to an embodiment of the present invention is shown;

[0026] Figure 2 A schematic flow chart showing a specific implementation of a method for controlling a distiller's grains upper retort distillation process according to an embodiment of the present invention is shown;

[0027] Figure 3 A schematic flow chart of the process of obtaining the upper steamer temperature field model provided by an embodiment of the present invention is shown;

[0028] Figure 4 A schematic flow chart showing a process for obtaining a wine distillation model provided by an embodiment of the present invention is shown;

[0029] Figure 5 A schematic diagram of the upper retort distillation process provided by an embodiment of the present invention is shown;

[0030] Figure 6 A schematic diagram of the structure of a device for controlling a process of distilling lees in a retort provided by an embodiment of the present invention is shown;

[0031] Figure 7 A schematic structural diagram of an electronic device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0032] Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0033] In the production of baijiu (white liquor), the solid-state retorting and distillation process are crucial steps that directly impact both yield and quality. The quality of the retorting process is directly related to the looseness of the lees and the efficiency of steam passage. Traditional retorting requires adherence to the principles of "light, thin, accurate, loose, flat, and uniform" to ensure even heating of the lees, thereby improving alcohol extraction. However, with increasing production demand, many distilleries are beginning to adopt mechanized methods to replace manual retorting to improve production efficiency and consistency.

[0034] Although mechanized steaming has improved efficiency, in practice, there is still a lack of effective guidance on the height and timing of each steaming operation, as well as the control of steam pressure and flow during the distillation process. As a result, the results of mechanized steaming and distillation have not met expectations. This situation has led many distilleries to face the problem of unstable wine quality while increasing production, which has increased production costs.

[0035] Existing research on the steaming and distillation process of liquor mostly focuses on the design and modification of the equipment, with the goal of improving or replacing manual steaming in order to improve the steaming effect and production efficiency. However, there are relatively few studies on the simulation and optimization of the process. The existing liquor extraction method based on online near-infrared spectroscopy and its online simulation extraction device collect alcohol data through spectral technology and conduct modeling analysis to achieve the goal of online wine extraction. In addition, the steam detection method for liquor steaming based on convolutional neural networks mainly uses a thermal infrared camera to obtain infrared-like images of the steamer barrel. After image processing, the DeconvSSD model is used to determine the feeding situation during the steaming process to reduce the phenomena of "steam compression" and "steam leakage". Although there have been some research results, the simulation of the existing solid-state liquor steaming and distillation process still has the following limitations:

[0036] 1. Failure to consider the differences in material properties between different batches: There may be significant differences in the composition and properties of different batches of distiller's grains, and the impact of these differences on the steaming and distillation processes has not been fully considered.

[0037] 2. Single process simulation: Existing studies often simulate the steaming process or the distillation process, but fail to comprehensively consider the impact of the steaming process on the distillation process, resulting in insufficient overall optimization effect.

[0038] 3. Lack of steam flow and pressure optimization: Steam flow and pressure are important factors affecting distillation efficiency. The existing research has insufficient optimization of these key variables, which limits the overall performance of the control process.

[0039] Based on this, in an embodiment of the present invention, a method for controlling the distillation process of distiller's grains in the upper steamer is provided. First, the distiller's grains material property data of the current batch, including the thermophysical properties of the distiller's grains, is obtained, and the steam thermophysical property data of the current batch is collected. Next, these data will be input into a pre-trained upper steamer temperature field model to generate temperature field data of the upper steamer process, including the temperature changes during the upper steamer process and the temperature state at the end. These temperature field data and the distiller's grains material property data are used to accurately control the height, timing, steam flow rate and pressure during the upper steamer process. Subsequently, the temperature field data at the end of the upper steamer and the distiller's grains material property data will be input into the distillation and wine extraction model to obtain the corresponding distillation and wine extraction data. The distillation and wine extraction data will be used to optimize the steam flow rate and pressure of the distillation process. It can be seen that the present invention realizes the effective management of the distiller's grains upper steamer and distillation process through this series of precise control measures, thereby significantly improving the production efficiency and wine quality stability of solid-state liquor.

[0040] like Figure 1 As shown, a flow chart of an embodiment of a method for controlling a distiller's grains retort distillation process according to an embodiment of the present invention is provided. The method may include:

[0041] S100: Obtaining property data of a current batch of distiller's grains material, wherein the property data of the distiller's grains material includes thermophysical property data of the current batch of distiller's grains material.

[0042] Distiller's grains material property data refers to the various physical and chemical properties of different batches of distiller's grains after mixing with bran. This data is crucial for processing and optimizing the baijiu production process. Understandably, in baijiu production, raw materials and production conditions may vary from batch to batch, necessitating detailed material property analysis for each batch to ensure consistent quality.

[0043] Thermophysical properties of distiller's grains refer to the thermal characteristics of the distiller's grains. These properties help determine the thermal conductivity of the distiller's grains during heating and cooling, and are crucial for temperature control during retorting and distillation. These properties can include the density and thermal conductivity of the distiller's grains after bran mixing for the current batch. The density of the distiller's grains after bran mixing refers to the mass per unit volume of the distiller's grains after bran mixing. The thermal conductivity of the distiller's grains after bran mixing refers to the measured thermal conductivity of the distiller's grains after bran mixing.

[0044] The data on the properties of the lees material may also include the acid sludge water test results, the amount of bran mixed, the amount of steaming, and the moisture content of the lees after bran mixing of the current batch of lees material.

[0045] Among them, the acid and starch test results include the acidity, water content and starch content of the current batch of lees materials detected during the fermentation barrel stage.

[0046] The amount of bran mixing refers to the amount of bran mixing material added when processing the lees. The fermented lees need to be mixed with bran to increase the looseness.

[0047] Among them, the amount of mash put into the steamer refers to the amount of fermented mash put into the steamer.

[0048] Among them, the moisture content of the distiller's grains after mixing with bran refers to the moisture content of the distiller's grains after mixing with bran.

[0049] The embodiment of the present invention fully considers the differences in the properties of materials in different batches. By collecting the property data of the lees material of the current batch, it helps to subsequently effectively control the upper steamer distillation of the current batch of lees material, thereby controlling the stability of the wine quality of different batches.

[0050] S110. Obtain steam thermophysical property data of the current batch.

[0051] The steam thermophysical property data is data on various thermal physical properties of the steam provided to the upper retort for distillation in the current batch. The steam thermophysical property data may include the specific heat capacity, thermal conductivity, density, and latent heat of the steam.

[0052] Specifically, embodiments of the present invention can perform online monitoring and sampling of steam using precise instruments and equipment (such as thermal analyzers, densitometers, etc.), collecting real-time data on its thermophysical properties such as specific heat capacity, thermal conductivity, density, and latent heat under specific temperature and pressure conditions, and then organizing and analyzing these data to construct thermophysical property data for the current batch of steam.

[0053] S120. Input the distiller's grains material property data, distiller's grains thermophysical property data, and steam thermophysical property data into a pre-trained upper steamer temperature field model to obtain the upper steamer temperature field data output by the upper steamer temperature field model, wherein the upper steamer temperature field data includes the upper steamer process temperature field data and the upper steamer end temperature field data.

[0054] The upper steamer temperature field model, a mathematical model constructed using machine learning techniques, is used to predict and analyze temperature variations in lees during the liquor production process. Based on historical data and inputs such as lees material properties and steam thermophysical properties, the upper steamer temperature field model uses calculations and simulations to predict the temperature distribution and variations of lees under different conditions, providing a basis for process optimization and temperature control.

[0055] The upper retort temperature field data refers to the data output by the upper retort temperature field model regarding the temperature distribution of the lees during the upper retort process. This includes both the upper retort process and the end of the upper retort process. This upper retort temperature field data can be used to analyze and monitor the temperature changes of the lees at different stages to ensure a stable production process and improve the quality of the wine.

[0056] The temperature field data during the retorting process refers to the temperature change data of the lees monitored throughout the entire retorting process, including the temperature rise data of the lees during the retorting process. This temperature rise data includes the temperature rise of the lees during different stages (such as the cooling stage, the rapid temperature rise stage, the slow temperature rise stage, and the constant temperature matured stage). For example, the temperature rise data of the lees during the retorting process can be shown in Table 1.

[0057] Table 1

[0058] Warming up stage Temperature range Cold mash stage Average temperature 28℃ The rapid temperature rise stage when steam contacts the mash 28-80℃ Slow heating stage 80-98℃ Constant temperature mash stage > 98℃

[0059] The temperature field data at the end of the steaming process refers to the final temperature distribution data of the lees at the end of the steaming process.

[0060] S130. Using the temperature field data of the steaming process and the data on the properties of the lees material, control the steaming height, steaming timing, steam flow rate, and steaming pressure of the steaming process of the current batch.

[0061] Among them, the steaming height refers to the amount of lees loaded during the steaming process, which is used to ensure that the steam contacts the lees evenly, improve heating efficiency, and reduce the risk of local excessive temperature.

[0062] Among them, the timing of steaming refers to the time point in the steaming process when to decide when to put the lees into steam treatment, which is used to ensure that the lees are steam-heated under the optimal temperature conditions to achieve ideal wine quality and production efficiency.

[0063] Among them, the steam flow rate of the upper steamer refers to the steam flow rate entering the lees processing area through the steam pipe during the upper steamer process, which is used to ensure that the lees obtain uniform heat distribution during the heating process.

[0064] Among them, the steaming pressure refers to the pressure in the steam system during the steaming process, which is used to maintain the heat conduction efficiency of the steam, ensure that the steam is evenly distributed in the lees, and maintain the stability of the heating process.

[0065] Specifically, the embodiments of the present invention can provide different types of guidance for different production lines based on the temperature field data of the steaming process and the material property data of the lees, so as to control the steaming height, steaming timing, steam flow rate and steaming pressure of the steaming process of the current batch.

[0066] Optionally, embodiments of the present invention, specifically for robotic production lines, can monitor the temperature distribution in real time during the robotic retorting process, analyze the temperature data, and provide recommendations on the amount of steam to be retorted per session and the optimal timing. Furthermore, for areas of abnormal temperature (such as high-temperature areas with a risk of steam leakage), regional paving can be implemented to mitigate risk and ensure even heat distribution.

[0067] Optionally, embodiments of the present invention, specifically for disc-loading retort production lines, can monitor temperature distribution data in real time during the retort process. This data can guide the amount and timing of retort loading. Furthermore, for high-temperature areas, a full-layer paving process is recommended to ensure uniform steam contact with the lees, thereby improving heating efficiency.

[0068] Optionally, for manual production lines, this embodiment of the present invention can monitor temperature changes during the manual retorting process and provide recommendations on the appropriate retorting quantity and optimal timing. For areas of abnormally high temperature detected, operators will be instructed to implement regional material paving measures to reduce the risk of steam leakage and ensure effective heat transfer.

[0069] Specifically, embodiments of the present invention dynamically adjust steam flow and pressure based on real-time temperature field distribution data to meet heating rate requirements and ensure sufficient preheating of the lees during the retorting process. Furthermore, dynamic steam flow and pressure regulation ensures smooth and even steam distribution, thereby improving overall production efficiency and product quality.

[0070] S140. Input the temperature field data at the end of the upper steamer and the lees material property data into a pre-trained distillation wine extraction model to obtain the distillation wine extraction data output by the distillation wine extraction model.

[0071] The distillation model, built using machine learning, simulates and predicts various parameters and outcomes during the distillation process. It can be trained using historical data and relevant variables (such as the temperature field at the end of the retort and data on the properties of the lees) to predict steam usage, temperature changes, concentration distribution, base liquor composition, and energy consumption under specific conditions.

[0072] Among them, distillation data refers to various parameters about the distillation process output by the distillation model, including steam data, temperature distribution, concentration distribution, base wine data and energy consumption data.

[0073] Steam data refers to information related to steam used in the distillation process, which may include parameters such as steam flow and pressure.

[0074] Among them, temperature distribution refers to the temperature changes at different locations during the distillation process.

[0075] Among them, concentration distribution refers to the concentration distribution of alcohol and other components (such as aroma substances, impurities, etc.) at different positions during the distillation process, which can be used to evaluate distillation efficiency.

[0076] Among them, base wine data refers to the basic information of the base wine used in the distillation process, including the base wine flow rate and base wine alcohol content.

[0077] Among them, energy consumption data refers to the energy consumption of the distillation process calculated based on steam consumption.

[0078] S150: Using the distillation wine extraction data, control the steam flow and pressure of the distillation wine extraction process of the current batch.

[0079] Specifically, the embodiment of the present invention can use the distillation wine extraction data to accurately control the steam flow and pressure during the distillation wine extraction process of the current batch, so as to meet the temperature requirements of different stages of the distillation wine extraction process (first wine, second stage wine, and tail wine), thereby ensuring the distillation efficiency while improving the wine yield of the second stage wine.

[0080] The present invention provides a method for controlling a distiller's grains upper steamer distillation process, the method comprising: obtaining distiller's grains material property data of a current batch, wherein the distiller's grains material property data includes distiller's grains thermophysical property data of the distiller's grains material of the current batch; obtaining steam thermophysical property data of the current batch; inputting the distiller's grains material property data, distiller's grains thermophysical property data, and steam thermophysical property data into a pre-trained upper steamer temperature field model, obtaining upper steamer temperature field data output by the upper steamer temperature field model, wherein the upper steamer temperature The field data includes the temperature field data of the upper steaming process and the temperature field data at the end of the upper steaming; the temperature field data of the upper steaming process and the lees material property data are used to control the upper steaming height, upper steaming timing, upper steaming steam flow rate and upper steaming pressure of the upper steaming process of the current batch; the temperature field data at the end of the upper steaming and the lees material property data are input into a pre-trained distillation wine extraction model to obtain the distillation wine extraction data output by the distillation wine extraction model; the distillation wine extraction data is used to control the steam flow rate and pressure of the distillation wine extraction process of the current batch. The present invention can accurately predict the temperature field data of the upper steaming process by distinguishing the lees material property data and steam thermophysical property data of different batches and inputting them into a pre-trained upper steaming temperature field model. Combining the temperature field data and the lees material property data can effectively control the upper steaming height, timing, steam flow rate and pressure, thereby optimizing the upper steaming process. Next, the temperature field data at the end of steaming and the material property data of the lees are input into the distillation and wine extraction model to obtain the distillation and wine extraction data, so as to control the steam flow and pressure in the distillation process, and realize the precise control of the steaming process and distillation process of the lees, thereby effectively improving the production efficiency and quality stability of solid-state liquor.

[0081] Optional, based on Figure 1 The method shown, such as Figure 2 As shown, a flow chart of a specific implementation of the method for controlling the distillation process of lees provided by an embodiment of the present invention is provided, wherein step S100 may include:

[0082] S200. Obtaining an acid-sediment water test result of a current batch of distiller's grains material, wherein the acid-sediment water test result includes the acidity, water content, and starch content of the current batch of distiller's grains material.

[0083] Specifically, the present invention can obtain the detection results of acidified water by using detection technology during the processing of the current batch of lees. The acidified water detection is mainly performed during the fermentation stage of the fermentation barrel to evaluate the fermentation status of the lees.

[0084] S210: Obtain the amount of bran mixed with and the amount of steaming for the current batch of distiller's grains after fermentation is completed.

[0085] Specifically, after fermentation is completed, in order to improve the looseness of the vinasse, the vinasse needs to be mixed with bran. In this process, the embodiment of the present invention can record the amount of mixed bran and the amount of vinasse added to the steamer after mixing bran.

[0086] S220: inputting the acid precipitate water detection result and the bran mixing amount into a pre-built bran mixing moisture content model to obtain the distiller's grains moisture content after bran mixing output by the bran mixing moisture content model.

[0087] The post-bran mixing moisture content model maps the acid-water test results and the bran mixing amount to the distiller's grains moisture content after bran mixing. The post-bran mixing moisture content model can predict the corresponding distiller's grains moisture content after bran mixing based on the acid-water test results and the bran mixing amount.

[0088] S230: Input the moisture content of the vinasse after mixing with bran and the amount of mixed bran into a pre-built density model after mixing with bran, and obtain the density of the vinasse after mixing with bran output by the density model after mixing with bran.

[0089] The bran-mixed density model is a mapping relationship model established based on the moisture content and bran mixing amount of the distillers' grains after bran mixing and the density of the distillers' grains after bran mixing. The bran-mixed density model can predict the corresponding distillers' grains density after bran mixing based on the input moisture content and bran mixing amount of the distillers' grains after bran mixing.

[0090] S240: Input the acidified water detection result and the bran mixing amount into a pre-built raw material component model to obtain the distiller's grains raw material composition data output by the raw material component model.

[0091] The raw material composition model is a mapping relationship model established based on the acid-water test results and the amount of bran mixed with the distiller's grains raw material composition data. The raw material composition model can predict the corresponding distiller's grains raw material composition data based on the input acid-water test results and the amount of bran mixed with the distiller's grains raw material composition data.

[0092] Among them, the composition data of the lees raw materials refers to the specific proportion and content of each component in the lees obtained through the raw material component model analysis.

[0093] S250: Input the density of the vinasse after mixing with bran into a pre-built porosity model to obtain the porosity of the vinasse after mixing with bran output by the porosity model.

[0094] The porosity model is a mapping relationship model established based on the density of the lees after mixing with bran and the porosity of the lees after mixing with bran. The porosity model can predict the corresponding porosity of the lees after mixing with bran based on the input density of the lees after mixing with bran.

[0095] S260, detecting the temperature of the lees after mixing with bran.

[0096] Among them, the temperature of the lees after mixing with bran refers to the temperature measured of the lees material after mixing with bran.

[0097] S270. Input the density of the vinasse after mixing with bran, the moisture content of the vinasse after mixing with bran, the porosity of the vinasse after mixing with bran, the raw material composition data of the vinasse and the temperature of the vinasse after mixing with bran into a pre-built thermal conductivity model to obtain the thermal conductivity test result of the vinasse after mixing with bran output by the thermal conductivity model.

[0098] The thermal conductivity model is a mapping relationship model established based on the density, moisture content, porosity, raw material composition, and temperature of the bran-mixed lees, and the thermal conductivity test results of the bran-mixed lees. The thermal conductivity model can predict the corresponding thermal conductivity test results of the bran-mixed lees based on the input data of the density, moisture content, porosity, raw material composition, and temperature of the bran-mixed lees.

[0099] The embodiment of the present invention can construct a mapping model including a post-bran mixing moisture content model, a post-bran mixing density model, a raw material component model, a porosity model, and a thermal conductivity model by detecting the moisture content, density, and thermal conductivity of different batches of vinasse samples after mixing with bran.

[0100] Specifically, the embodiment of the present invention can use the atmospheric drying method to detect the moisture content, by heating the sample under atmospheric pressure to evaporate the water, and then determine the moisture content of the lees by measuring the mass change before and after weighing the sample. The embodiment of the present invention can use the immersion method to measure the true density of the lees sample, that is, immersing the lees sample in a liquid that does not react or dissolve with it, calculating the volume of liquid displaced by the lees sample and combining it with the mass of the sample to obtain the true density. At the same time, the bulk density of the lees sample is obtained by the filling method. The embodiment of the present invention can use the transient plane source method, by attaching a small area heat source that is instantaneously heated to the lees sample, recording the change of the surrounding temperature over time, and thus calculating the thermal conductivity of the lees sample.

[0101] Specifically, embodiments of the present invention can perform data preprocessing on historical data from different batches of lees samples after bran mixing. This involves cleaning the detected data, removing outliers and missing values, and performing standardization or normalization for cases where the data range varies significantly. Next, feature variables strongly correlated with the target variable (such as moisture content, density, and thermal conductivity) are screened for each mapping model, and feature construction is performed as necessary to enhance the model's predictive capabilities. Next, the application scope of the mapping model is clarified, specifically the relationship between the input variables (such as bran mixing amount, moisture content, etc.) and the output variables (such as density and thermal conductivity). Based on the requirements, an appropriate mapping model, such as linear regression or polynomial regression, is selected to ensure that a single or multiple inputs correspond to a single output. Finally, the dataset is divided into a training set and a test set. Model parameters are continuously optimized during training, and the model is validated using the test set after training. The model's predictive performance is evaluated using metrics such as mean squared error to ensure its effectiveness and accuracy in practical applications. Through the above steps, an accurate mapping model can be constructed to effectively predict the moisture content, density and thermal conductivity of the lees after mixing with bran.

[0102] The embodiment of the present invention can obtain accurate data on the properties of the lees material through a pre-built mapping model, thereby providing reliable basic data for subsequent predictions of the steaming temperature field and distillation wine extraction, and thus helping to accurately control the steaming process and distillation process of the lees.

[0103] Optional, such as Figure 3 As shown, a schematic diagram of a process for obtaining a temperature field model of an upper retort provided by an embodiment of the present invention is provided. The process for obtaining a temperature field model of an upper retort may include:

[0104] S300. Obtain temperature field sample data, wherein the temperature field sample data includes historical data of initial temperature of lees after data cleaning and standardization of lees samples from different batches, sample data of lees material properties, sample data of lees thermophysical properties, and sample data of steam thermophysical properties.

[0105] The historical data of initial temperature of lees include the initial temperature data of lees samples from different batches, which serve as the starting parameters for studying heat and mass transfer.

[0106] It can be understood that for the sample data of distiller's grains material properties, the sample data of distiller's grains thermophysical properties and the sample data of steam thermophysical properties, please refer to the corresponding descriptions of distiller's grains material properties data, distiller's grains thermophysical properties data and steam thermophysical properties data, which will not be repeated here.

[0107] S310. Input the temperature field sample data into a pre-built upper steamer temperature field model to obtain the upper steamer temperature field prediction data output by the upper steamer temperature field model, wherein the upper steamer temperature field model is a heat and mass transfer coupling model formed by combining the heat conduction equation in the solid lees, the convection heat transfer equation between steam and lees, the radiation heat transfer equation in the lees, and the mass transfer equation for water evaporation and ester volatilization in the lees. The boundary conditions and initial conditions of the upper steamer temperature field model are defined based on the energy conservation and mass conservation equations.

[0108] The upper steamer temperature field prediction data refers to the temperature distribution data predicted by the pre-built upper steamer temperature field model based on the temperature field sample data.

[0109] Among them, the heat conduction equation inside the lees solid is a mathematical equation that describes the heat conduction process inside the lees solid.

[0110] The steam and lees convection heat transfer equation refers to a mathematical equation that describes the heat exchange between steam and lees through the convection process.

[0111] Among them, the lees radiation heat transfer equation refers to the mathematical equation that describes the heat exchange on the lees surface through radiation.

[0112] Among them, the mass transfer equation for water evaporation and ester volatilization in the lees refers to a mathematical equation that describes how the water and volatile components (such as esters) in the lees migrate and transform during the heating process.

[0113] S320. Detecting the actual temperature of the wine lees sample during the steaming process in real time through a thermocouple to obtain actual data of the temperature field of the steamer.

[0114] The actual upper steamer temperature field data refers to the temperature information monitored in real time by sensors such as thermocouples during the steaming process of the lees. This data reflects the actual temperature distribution of the lees at different locations and time points, and is typically recorded digitally and visualized as a temperature field.

[0115] S330: Compare the predicted data of the upper steamer temperature field with the actual data of the upper steamer temperature field to obtain a first model output error.

[0116] The first model output error refers to the difference between the predicted data of the upper steamer temperature field and the actual data of the upper steamer temperature field.

[0117] S340 , determining whether the output error of the first model is greater than a preset temperature field error threshold; if yes, executing step S350 ; if no, executing step S360 .

[0118] The preset temperature field error threshold is used to determine the acceptable range of the output error of the upper steamer temperature field model. If the output error of the first model exceeds this threshold, the model performance of the upper steamer temperature field model is considered to be substandard and needs to be adjusted.

[0119] S350, iteratively adjust the model parameters of the upper steamer temperature field model, and return to step S310.

[0120] Among them, the model parameters of the upper steamer temperature field model refer to the numerical values ​​used to describe the system characteristics in the upper steamer temperature field model. These parameters affect the output results of the model, such as: thermal conductivity coefficient, convective heat transfer coefficient and radiation emissivity.

[0121] S360: Obtain a trained upper steamer temperature field model.

[0122] The embodiment of the present invention lays the foundation for model establishment by collecting temperature history data, material properties and thermophysical properties of different batches of distiller's grains samples, and cleaning and standardizing them. Subsequently, the sorted temperature field sample data is input into the pre-built upper steamer temperature field model, and the upper steamer temperature field prediction data is generated using complex heat and mass transfer coupling equations. At the same time, the actual temperature of the distiller's grains sample is monitored in real time and compared with the predicted data to calculate the output error of the first model. By judging whether the error exceeds the preset threshold, if it exceeds, the model parameters are iteratively adjusted to optimize the prediction to ensure continuous improvement and accuracy of the model. Finally, a trained upper steamer temperature field model is obtained, which helps to obtain more accurate upper steamer temperature field data in practical applications, thereby improving the control accuracy of the upper steamer process and ensuring the stability of the liquor quality.

[0123] Optional, such as Figure 4 As shown, a schematic diagram of a process for obtaining a distillation wine extraction model provided by an embodiment of the present invention is provided. The process for obtaining the distillation wine extraction model may include:

[0124] S400: Obtaining distilled wine sample data, wherein the distilled wine sample data includes lees material property sample data and steaming end temperature field sample data of lees samples from different batches.

[0125] It is understandable that, regarding the wine lees material property sample data and the upper steaming end temperature field sample data of the wine lees sample, please refer to the corresponding description of the wine lees material property data and the upper steaming end temperature field data, which will not be repeated here.

[0126] S410. Input the distillation wine sample data into a pre-built distillation wine model to obtain distillation wine prediction data output by the distillation wine model, wherein the distillation wine model is built based on a non-standard packed tower structure.

[0127] Among them, the distillation wine prediction data refers to various parameters of the distillation wine process predicted by a pre-built distillation wine model based on the distillation wine sample data, including steam data, temperature distribution, concentration distribution, base wine data and energy consumption data.

[0128] Among them, the non-standard packed tower structure refers to the packed tower design used in the distillation process. Its packing configuration and structural characteristics are different from those of conventional standard packed towers. Its function is to optimize the contact between steam and liquid and improve separation efficiency.

[0129] Specifically, embodiments of the present invention utilize process modeling software to simulate the solid-state liquor distillation process using a non-standard packed tower based on specific assumptions during the construction of a distillation liquor extraction model. First, after the retort is completed, sample data on the properties of the lees material is used as the initial input for the model, while sample data on the temperature field at the end of the retort is used as the initial temperature input.

[0130] Among them, the assumptions used in constructing the distillation wine model include: equilibrium level assumption, evaporation efficiency assumption, ignoring the condensation effect of the retort cover, ignoring the gas storage volume in the equilibrium level, ignoring the temperature rise of the retort barrel, and ignoring trace chemical reaction processes.

[0131] Among them, the equilibrium stage assumption is to assume that each equilibrium stage is in a state of heat and mass transfer equilibrium between the gas phase and the liquid phase, ignoring the heat transfer calculation at the microscale, and transforming the distillation tower from a distributed parameter model to a lumped parameter model based on the equilibrium stage.

[0132] Among them, the evaporation efficiency assumption means that the liquid to be separated in the packed tower is mixed with the reflux liquid after the liquid distributor to form a liquid film, and there is almost no evaporation resistance. However, the liquid phase evaporation resistance inside the lees needs to be considered and corrected by the evaporation efficiency coefficient.

[0133] Among them, ignoring the condensation effect of the steamer cover means that since the steamer cover operates at high temperature and has a limited area, the condensation effect is not obvious and can therefore be ignored.

[0134] Among them, ignoring the gas storage capacity in the equilibrium stage means that due to the high flow rate and short residence time of the rising air flow, there are fewer pores in the grains of the wine lees, and the gas storage capacity can be ignored compared with the liquid holding capacity.

[0135] Ignoring the temperature rise of the steamer barrel means that the steamer barrel has been fully preheated during the steaming process, and the influence of the temperature rise of the steamer barrel can be ignored during the distillation process.

[0136] Ignoring trace chemical reaction processes means that some trace chemical reactions may occur during the distillation process, such as the Maillard reaction between sugars and amino acids, but the amounts of these reactions are relatively small and can therefore be ignored in the simulation.

[0137] Among them, the modeling process of non-standard packed tower includes the steps of physical property configuration, model building, model configuration, and operation solution.

[0138] Among them, physical property configuration includes defining the main components in the liquor distillation process, selecting appropriate thermodynamic methods, setting the property parameters and binary interaction parameters of pure substances, and creating virtual components for missing components to facilitate simulation.

[0139] Among them, model building includes using the unit operation module and flow stream of the process modeling software to build a distillation and wine extraction model.

[0140] The model configuration includes configuring the unit modules and stream parameters of the distillation model, including the number of stages of the packed tower, the efficiency of the tower, and the temperature, flow rate and component parameters of the stream.

[0141] Among them, running the solution includes performing a simulation on the distillation model to check whether it converges.

[0142] In the modeling process of the distillation wine extraction model, the mathematical models involved include the equilibrium-level material equation, the component normalization equation and the equilibrium-level enthalpy balance equation.

[0143] Among them, the equilibrium level material equation is:

[0144]

[0145] Among them, M j is the liquid holdup of the jth equilibrium stage, V j-1 、V j are the gas volumes entering and flowing out of the jth equilibrium stage, L j+1 , L j are the amount of liquid entering and flowing out of the jth equilibrium stage; y j,i 、x j,i are the mole fractions of gas and liquid component i in the jth equilibrium stage, respectively.

[0146] Among them, the component normalization equation is:

[0147]

[0148] Among them, the equilibrium-level enthalpy balance equation is:

[0149]

[0150] Among them, H j g is the molar enthalpy of the gas phase mixture in equilibrium level j, H j l is the molar enthalpy of the liquid mixture in equilibrium level j, Q j lossis the heat loss in the equilibrium stage j.

[0151] S420. Obtain actual data of distillation of the wine lees sample through an online alcohol content detection device.

[0152] Among them, the online alcohol detection device is an instrument for real-time monitoring and measurement of the alcohol concentration in liquid samples.

[0153] Among them, the actual data of distillation and wine extraction refers to the parameter information obtained by the online alcohol content detection device during the distillation and wine extraction process of the lees sample, including steam data, temperature distribution, concentration distribution, base wine data and energy consumption data.

[0154] S430: Compare the predicted data of wine distillation with the actual data of wine distillation to obtain a second model output error.

[0155] Among them, the output error of the second model refers to the difference between the predicted data of distilled wine and the actual data of distilled wine.

[0156] S440. Determine whether the output error of the second model is greater than the preset distillation error threshold. If yes, execute step S450; if not, execute step S460.

[0157] The preset distillation error threshold is used to determine the acceptable range of error in the distillation model output. If the output error of the second model exceeds this threshold, the distillation model is considered to be substandard and needs to be adjusted.

[0158] S450. Iteratively adjust the model parameters of the distillation wine extraction model and return to execute step S410.

[0159] The model parameters of the distillation wine extraction model refer to the various numerical values ​​required when establishing and running the distillation wine extraction simulation model. These parameters affect the output results of the model, such as: operating condition parameters, tower geometric parameters, operating strategy parameters and thermodynamic model parameters.

[0160] S460: Obtain a trained distillation wine extraction model.

[0161] The embodiment of the present invention establishes a rich sample library by acquiring sample data of different batches of lees, including the material properties of the lees and the temperature field data at the end of the upper steamer. These sample data are input into a pre-built distillation and wine extraction model to generate distillation and wine extraction prediction data. The model is constructed based on a non-standard packed tower structure and can more effectively simulate the material separation and heat transfer in the distillation process. At the same time, the actual distillation and wine extraction data obtained by the online alcohol content detection device is compared with the predicted data output by the model to accurately evaluate the prediction accuracy of the model. Then, by calculating the output error between the predicted data and the actual data and judging whether it exceeds the preset error threshold, the model can be iteratively optimized. If the error exceeds the threshold, the model parameters are adjusted and the data input step is returned to improve the accuracy and reliability of the model. Finally, through continuous iteration and optimization, a trained distillation and wine extraction model can be obtained, thereby providing a more accurate control basis for each batch of distillation processes, ensuring the improvement of product quality and production efficiency.

[0162] Optional, in the above Figure 1 On the basis of one or more corresponding embodiments, in another optional embodiment provided by the embodiment of the present invention, the method may further include:

[0163] The production guidance interface displays the data on the properties of the lees materials, the temperature field data of the upper steamer, and the data on the distillation and wine extraction. The production guidance interface also dynamically demonstrates the upper steamer process, the distillation and wine extraction process, and the unsteaming process.

[0164] The dynamic demonstration of the steaming process includes: 1. A dynamic demonstration of the conveyor belt transporting the lees mixed with bran from the hopper, and when the lees are placed on the steamer, a dynamic demonstration of the conveyor belt operation is provided. 2. Different types of steaming demonstrations are provided based on different steaming methods. The manual steaming method provides a dynamic demonstration of the process of spreading the lees with a dustpan, the robotic steaming method provides a dynamic demonstration of the machine hopper spreading the lees, and the disc steaming machine method provides a dynamic demonstration of the disc scraping the lees. 3. A dynamic demonstration of the steamer lidding process is provided.

[0165] The dynamic demonstration of the distillation process includes: 1. A visual representation of the vapor flow and temperature distribution of the solid lees within the retort during the distillation process. 2. A dynamic rendering of the alcohol vapor condensing through the condenser and its outflow. 3. Real-time base liquor mass flow rate and alcohol content are provided, demonstrating the process of separating the first, second, and last liquors based on alcohol content.

[0166] The dynamic demonstration of the steamer unloading process includes: 1. The dynamic demonstration of the crane lifting the steamer after the distillation is completed. 2. The dynamic demonstration of the process of pouring the lees from the steamer. 3. The dynamic demonstration of the crane lifting the steamer back to the loading steamer after the lees are unloaded.

[0167] This embodiment of the present invention displays distiller's grains material property data, steaming temperature field data, and distillation data on a three-dimensional production guidance interface. It also dynamically demonstrates the steaming, distillation, and unsteaming processes. This allows operators to intuitively understand the current production status, monitor changes in each link in a timely manner, and improve production transparency and efficiency. Furthermore, the visualization of real-time data helps operators make accurate decisions and optimize operating parameters, thereby improving product quality, reducing resource waste, and ensuring a safe and stable production process.

[0168] In order to facilitate the understanding of the overall process of the upper steamer distillation process provided by this scheme, Figure 5 To explain: Figure 5 The figure shows a schematic diagram of the upper steamer distillation process provided by an embodiment of the present invention. In the process of material property detection and modeling, the material properties of the lees are obtained through detection technology. In the fermentation barrel stage, acid precipitate detection is used to evaluate the acidity, moisture and starch content of the lees to judge the fermentation situation. After the fermentation is completed, bran mixing needs to be added to increase the looseness of the lees, and the amount of bran mixing and its effect on the upper steamer amount are recorded. For different batches of bran mixing lees, models such as water content, density, raw material components and porosity are established, and a mapping relationship is established between the detection results and the bran mixing amount. At the same time, the thermal conductivity model is associated with the density, water content, porosity and temperature of the lees through regression analysis. The temperature field modeling combines the thermophysical properties of the material and steam, calculates the temperature distribution through the heat and mass transfer equation, and verifies the accuracy of the model through actual temperature detection. In the distillation and wine extraction modeling process, the process modeling software is used to simulate the distillation of liquor, and the material properties and temperature field data are used as the initial input of the model. The model performance is verified by an online alcohol content detection device. Finally, the production guidance interface provides users with interactive functions, displays material properties, temperature field and distillation data, and provides operational guidance for steaming and distillation processes.

[0169] Although the operations are depicted in a particular order, this should not be understood as requiring that the operations be performed in the particular order shown or in a sequential order.Multitasking and parallel processing may be advantageous under certain circumstances.

[0170] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0171] Corresponding to the above method embodiment, the embodiment of the present invention also provides a device for controlling the distillation process of lees, the structure of which is as follows: Figure 6As shown, it includes: a wine lees material property data acquisition unit 10, a steam thermophysical property data acquisition unit 20, an upper steamer temperature field data acquisition unit 30, an upper steamer process control unit 40, a distillation wine extraction data acquisition unit 50 and a distillation wine extraction process control unit 60.

[0172] The lees material property data obtaining unit 10 is used to obtain the lees material property data of the current batch, wherein the lees material property data includes the lees thermophysical property data of the current batch of lees material.

[0173] The steam thermophysical property data obtaining unit 20 is used to obtain the steam thermophysical property data of the current batch.

[0174] The upper steamer temperature field data acquisition unit 30 is used to input the lees material property data, lees thermophysical property data and steam thermophysical property data into a pre-trained upper steamer temperature field model to obtain the upper steamer temperature field data output by the upper steamer temperature field model, wherein the upper steamer temperature field data includes the upper steamer process temperature field data and the upper steamer end temperature field data.

[0175] The steaming process control unit 40 is used to control the steaming height, steaming timing, steam flow rate and steaming pressure of the steaming process of the current batch using the steaming process temperature field data and the lees material property data.

[0176] The distillation wine data acquisition unit 50 is used to input the temperature field data at the end of the upper steamer and the lees material property data into a pre-trained distillation wine model to obtain the distillation wine data output by the distillation wine model.

[0177] The distillation process control unit 60 is used to control the steam flow and pressure of the distillation process of the current batch of wine using the distillation data.

[0178] Optionally, the lees material property data also includes the acid sludge water test results, bran mixing amount, steaming amount and lees moisture content after bran mixing of the current batch of lees material, and the lees thermophysical property data includes the lees density after bran mixing and the lees thermal conductivity test results after bran mixing of the current batch of lees material.

[0179] Optionally, the lees material property data acquisition unit 10 can be specifically used to obtain the acid precipitate water detection result of the current batch of lees material, wherein the acid precipitate water detection result includes the acidity, water content and starch content of the current batch of lees material; obtain the bran mixing amount and the upper steaming amount of the current batch of lees material after fermentation is completed; input the acid precipitate water detection result and the bran mixing amount into a pre-constructed bran mixing water content model to obtain the lees water content after bran mixing output by the bran mixing water content model; input the lees water content after bran mixing and the bran mixing amount into a pre-constructed bran mixing density model to obtain the bran mixing density model The density of the lees after mixing with bran is output by the model; the acid slurry water detection result and the amount of mixed bran are input into a pre-built raw material component model to obtain the lees raw material composition data output by the raw material component model; the density of the lees after mixing with bran is input into a pre-built porosity model to obtain the porosity of the lees after mixing with bran output by the porosity model; the temperature of the lees after mixing with bran is detected; the density of the lees after mixing with bran, the water content of the lees after mixing with bran, the porosity of the lees after mixing with bran, the lees raw material composition data and the temperature of the lees after mixing with bran are input into a pre-built thermal conductivity model to obtain the thermal conductivity detection result of the lees after mixing with bran output by the thermal conductivity model.

[0180] Optionally, the device for controlling the process of distiller's grains upper steamer distillation may further include: an upper steamer temperature field model obtaining unit.

[0181] The upper steamer temperature field model acquisition unit is used to obtain temperature field sample data, wherein the temperature field sample data includes the initial temperature history data of the lees after data cleaning and standardization of the lees samples of different batches, the lees material property sample data, the lees thermophysical property sample data and the steam thermophysical property sample data; the temperature field sample data is input into the pre-built upper steamer temperature field model to obtain the upper steamer temperature field prediction data output by the upper steamer temperature field model, wherein the upper steamer temperature field model is a heat and mass transfer coupling model formed by combining the heat conduction equation of the lees solid, the convection heat transfer equation of steam and lees, the radiation heat transfer equation of the lees and the mass transfer equation of water evaporation and ester volatilization in the lees. The boundary conditions and initial conditions of the steamer temperature field model are defined based on the energy conservation and mass conservation equations; the actual temperature of the lees sample during the steaming process is detected in real time by thermocouples to obtain the actual data of the upper steamer temperature field; the upper steamer temperature field prediction data is compared with the actual data of the upper steamer temperature field to obtain the first model output error; it is determined whether the first model output error is greater than a preset temperature field error threshold; if so, the model parameters of the upper steamer temperature field model are iteratively adjusted, and the step of inputting the temperature field sample data into the pre-built upper steamer temperature field model to obtain the upper steamer temperature field prediction data output by the upper steamer temperature field model is returned to execute; if not, the trained upper steamer temperature field model is obtained.

[0182] Optionally, the device for controlling the process of distiller's grains distillation in the upper steamer may further include: a unit for obtaining a distillation wine model.

[0183] A distillation wine extraction model acquisition unit is used to obtain distillation wine extraction sample data, wherein the distillation wine extraction sample data includes wine lees material property sample data and upper steaming end temperature field sample data of different batches of wine lees samples; the distillation wine extraction sample data is input into a pre-built distillation wine extraction model to obtain distillation wine extraction prediction data output by the distillation wine extraction model, wherein the distillation wine extraction model is constructed based on a non-standard packed tower structure; the actual distillation wine extraction data of the wine lees sample is obtained through an online alcohol content detection device; the distillation wine extraction prediction data is compared with the actual distillation wine extraction data to obtain a second model output error; it is determined whether the second model output error is greater than a preset distillation wine extraction error threshold; if so, the model parameters of the distillation wine extraction model are iteratively adjusted, and the step of inputting the wine lees material property sample data and the upper steaming end temperature field sample data into the pre-built distillation wine extraction model to obtain the distillation wine extraction prediction data output by the distillation wine extraction model is returned; if not, a trained distillation wine extraction model is obtained.

[0184] Optionally, the temperature field data of the steaming process includes the temperature rise data of the wine lees during the steaming process, and / or the distillation wine data includes steam data, temperature distribution, concentration distribution, base wine data and energy consumption data.

[0185] Optionally, the device for controlling the process of distiller's grains upper retort distillation may further include: a production guidance unit.

[0186] The production guidance unit is used to display the lees material property data, steaming temperature field data and distillation and wine extraction data on the production guidance interface, and dynamically demonstrate the steaming process, distillation and wine extraction process and steaming process on the production guidance interface.

[0187] The present invention provides a device for controlling the distillation process of a lees upper steamer, which is used to: obtain the lees material property data of the current batch, wherein the lees material property data includes the lees thermophysical property data of the lees material of the current batch; obtain the steam thermophysical property data of the current batch; input the lees material property data, the lees thermophysical property data and the steam thermophysical property data into a pre-trained upper steamer temperature field model, and obtain the upper steamer temperature field data output by the upper steamer temperature field model, wherein the upper steamer temperature The field data includes the temperature field data of the upper steaming process and the temperature field data at the end of the upper steaming; the temperature field data of the upper steaming process and the lees material property data are used to control the upper steaming height, upper steaming timing, upper steaming steam flow rate and upper steaming pressure of the upper steaming process of the current batch; the temperature field data at the end of the upper steaming and the lees material property data are input into a pre-trained distillation wine extraction model to obtain the distillation wine extraction data output by the distillation wine extraction model; the distillation wine extraction data is used to control the steam flow rate and pressure of the distillation wine extraction process of the current batch. The present invention can accurately predict the temperature field data of the upper steaming process by distinguishing the lees material property data and steam thermophysical property data of different batches and inputting them into a pre-trained upper steaming temperature field model. Combining the temperature field data and the lees material property data can effectively control the upper steaming height, timing, steam flow rate and pressure, thereby optimizing the upper steaming process. Next, the temperature field data at the end of steaming and the material property data of the lees are input into the distillation and wine extraction model to obtain the distillation and wine extraction data, so as to control the steam flow and pressure in the distillation process, and realize the precise control of the steaming process and distillation process of the lees, thereby effectively improving the production efficiency and quality stability of solid-state liquor.

[0188] Regarding the apparatus in the above embodiment, the specific manner in which each unit performs operations has been described in detail in the embodiment of the method, and will not be elaborated on here.

[0189] The wine lees upper steamer distillation process control device includes a processor and a memory. The above-mentioned wine lees material property data acquisition unit 10, steam thermophysical property data acquisition unit 20, upper steamer temperature field data acquisition unit 30, upper steamer process control unit 40, distillation wine extraction data acquisition unit 50 and distillation wine extraction process control unit 60 are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0190] The processor includes a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be set. By adjusting the kernel parameters to distinguish the material property data and steam thermophysical property data of different batches, and inputting them into a pre-trained upper steaming temperature field model, the temperature field data of the upper steaming process can be accurately predicted. Combining the temperature field data and the material property data of the lees, the upper steaming height, timing, steam flow rate and pressure can be effectively controlled, thereby optimizing the upper steaming process. Next, the temperature field data at the end of the upper steaming and the material property data of the lees are input into the distillation and wine extraction model to obtain distillation and wine extraction data to control the steam flow rate and pressure during the distillation process, thereby achieving precise control of the lees upper steaming process and the distillation process, thereby effectively improving the production efficiency and wine quality stability of solid-state liquor.

[0191] An embodiment of the present invention provides a computer-readable storage medium having a program stored thereon, which implements the method for controlling the lees upper steamer distillation process when executed by a processor.

[0192] An embodiment of the present invention provides a processor, which is used to run a program, wherein the program executes the wine lees upper steamer distillation process control method when running.

[0193] like Figure 7 As shown, an embodiment of the present invention provides an electronic device 1000, comprising at least one processor 1001, at least one memory 1002 connected to the processor 1001, and a bus 1003. The processor 1001 and the memory 1002 communicate with each other via the bus 1003. The processor 1001 is configured to invoke program instructions stored in the memory 1002 to execute the aforementioned method for controlling the distillation process of distiller's grains. The electronic device herein may be a server, a PC, a PAD, a mobile phone, or the like.

[0194] The present invention also provides a computer program product which, when executed on an electronic device, is suitable for executing the program steps of initializing the method for controlling the process of distillation of lees on a retort.

[0195] The present invention is described with reference to flowcharts and / or block diagrams of methods, apparatuses, electronic devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable device to produce a machine, so that the instructions executed by the processor of the computer or other programmable device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0196] In a typical configuration, an electronic device includes one or more processors (CPUs), a memory, and a bus. The electronic device may also include an input / output interface, a network interface, and the like.

[0197] Memory may include non-permanent memory in a computer-readable medium, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory includes at least one memory chip. Memory is an example of a computer-readable medium.

[0198] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0199] In the description of the present invention, it should be understood that if the terms "up", "down", "front", "back", "left" and "right" are used to indicate directions or positional relationships, they are based on the directions or positional relationships shown in the accompanying drawings. They are only used to facilitate the description of the present invention and simplify the description, and do not indicate or imply that the positions or elements referred to must have a specific direction, be constructed and operate in a specific direction. Therefore, they should not be understood as limitations of the present invention.

[0200] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. It should also be noted that the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, commodity, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, commodity, or device comprising the element.

[0201] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0202] The above are merely embodiments of the present invention and are not intended to limit the present invention. It will be apparent to those skilled in the art that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are intended to be within the scope of the present invention.

Claims

1. A method for controlling a distiller's grains retort distillation process, characterized in that: include: Obtaining property data of a current batch of distiller's grains, wherein the property data of the distiller's grains includes thermophysical property data of the current batch of distiller's grains; Obtaining steam thermophysical property data of the current batch; Inputting the distiller's grains material property data, the distiller's grains thermophysical property data, and the steam thermophysical property data into a pre-trained upper retort temperature field model to obtain upper retort temperature field data output by the upper retort temperature field model, wherein the upper retort temperature field data includes upper retort process temperature field data and upper retort end temperature field data; Using the temperature field data of the steaming process and the data on the properties of the lees material, control the steaming height, steaming timing, steam flow rate and steaming pressure of the steaming process of the current batch; Inputting the upper steamer end temperature field data and the lees material property data into a pre-trained distillation wine extraction model to obtain distillation wine extraction data output by the distillation wine extraction model; The distillation wine extraction data is used to control the steam flow and pressure of the distillation wine extraction process of the current batch.

2. The method according to claim 1, characterized in that The lees material property data also includes the acid precipitate water detection results, bran mixing amount, steaming amount and lees water content after bran mixing of the current batch of lees materials, and the lees thermophysical property data includes the lees density after bran mixing and the lees thermal conductivity detection results after bran mixing of the current batch of lees materials.

3. The method according to claim 2, characterized in that The method of obtaining the material property data of the current batch of distiller's grains includes: Obtaining the acid precipitate water test result of the current batch of distiller's grains material, wherein the acid precipitate water test result includes the acidity, water content, and starch content of the current batch of distiller's grains material; Obtaining the mixed bran amount and the upper steamer amount of the current batch of distiller's grains material after fermentation is completed; Inputting the acid precipitate water detection result and the bran mixing amount into a pre-built bran mixing water content model to obtain the water content of the distiller's grains after bran mixing output by the bran mixing water content model; Inputting the water content of the distiller's grains after mixing with bran and the amount of bran mixed into a pre-built density model after mixing with bran, and obtaining the density of the distiller's grains after mixing with bran output by the density model after mixing with bran; Inputting the acidified water detection result and the bran mixing amount into a pre-built raw material component model to obtain distiller's grains raw material composition data output by the raw material component model; Inputting the density of the vinasse mixed with bran into a pre-built porosity model to obtain the porosity of the vinasse mixed with bran output by the porosity model; Detect the temperature of the lees after mixing with bran; The density of the vinasse after mixing with bran, the moisture content of the vinasse after mixing with bran, the porosity of the vinasse after mixing with bran, the vinasse raw material composition data and the temperature of the vinasse after mixing with bran are input into a pre-built thermal conductivity model to obtain the thermal conductivity detection result of the vinasse after mixing with bran output by the thermal conductivity model.

4. The method according to claim 1, wherein The process of obtaining the upper steamer temperature field model includes: Obtaining temperature field sample data, wherein the temperature field sample data includes historical data of initial temperature of lees after data cleaning and standardization of lees samples from different batches, sample data of lees material properties, sample data of lees thermophysical properties, and sample data of steam thermophysical properties; Inputting the temperature field sample data into a pre-constructed upper steamer temperature field model to obtain upper steamer temperature field prediction data output by the upper steamer temperature field model, wherein the upper steamer temperature field model is a heat and mass transfer coupling model formed by combining the heat conduction equation within the lees solid, the convection heat transfer equation between steam and lees, the radiation heat transfer equation for the lees, and the mass transfer equation for water evaporation and ester volatilization within the lees, and the boundary conditions and initial conditions of the upper steamer temperature field model are defined based on the energy conservation and mass conservation equations; The actual temperature of the lees sample during the steaming process is detected in real time by a thermocouple to obtain actual data of the temperature field of the steamer; Comparing the predicted data of the upper steamer temperature field with the actual data of the upper steamer temperature field to obtain a first model output error; Determine whether the output error of the first model is greater than the preset temperature field error threshold. If so, iteratively adjust the model parameters of the upper steamer temperature field model, and return to execute the step of inputting the temperature field sample data into the pre-built upper steamer temperature field model to obtain the upper steamer temperature field prediction data output by the upper steamer temperature field model. If not, obtain the trained upper steamer temperature field model.

5. The method according to claim 1, characterized in that The process of obtaining the distillation liquor model includes: Obtaining distilled wine sample data, wherein the distilled wine sample data includes lees material property sample data and retort end temperature field sample data of lees samples from different batches; Inputting the distillation liquor sample data into the pre-built distillation liquor model to obtain distillation liquor prediction data output by the distillation liquor model, wherein the distillation liquor model is built based on a non-standard packed tower structure; Obtaining actual data of distillation and wine extraction of the lees sample through an online alcohol content detection device; Comparing the predicted data of distilled liquor extraction with the actual data of distilled liquor extraction to obtain a second model output error; Determine whether the output error of the second model is greater than the preset distillation wine extraction error threshold. If so, iteratively adjust the model parameters of the distillation wine extraction model, return to execute the step of inputting the wine lees material property sample data and the upper steamer end temperature field sample data into the pre-built distillation wine extraction model to obtain the distillation wine extraction prediction data output by the distillation wine extraction model. If not, obtain the trained distillation wine extraction model.

6. The method according to claim 1, characterized in that The temperature field data of the upper steaming process includes the temperature rise data of the wine lees during the upper steaming process, and / or the distillation wine extraction data includes steam data, temperature distribution, concentration distribution, base wine data and energy consumption data.

7. The method according to claim 1, characterized in that Also includes: The wine lees material property data, the upper steamer temperature field data and the distillation wine extraction data are displayed on the production guidance interface, and the upper steamer process, the distillation wine extraction process and the steamer discharge process are dynamically demonstrated on the production guidance interface.

8. A device for controlling the process of distiller's grains retort distillation, characterized in that: include: Wine lees material property data acquisition unit, steam thermophysical property data acquisition unit, upper steamer temperature field data acquisition unit, upper steamer process control unit, distillation wine data acquisition unit and distillation wine process control unit, The distiller's grains material property data obtaining unit is used to obtain distiller's grains material property data of a current batch, wherein the distiller's grains material property data includes distiller's grains thermophysical property data of the current batch of distiller's grains material; The steam thermophysical property data obtaining unit is used to obtain the steam thermophysical property data of the current batch; The upper steamer temperature field data acquisition unit is used to input the distiller's grains material property data, the distiller's grains thermophysical property data, and the steam thermophysical property data into a pre-trained upper steamer temperature field model to obtain upper steamer temperature field data output by the upper steamer temperature field model, wherein the upper steamer temperature field data includes upper steamer process temperature field data and upper steamer end temperature field data; The steaming process control unit is used to control the steaming height, steaming timing, steam flow rate and steaming pressure of the steaming process of the current batch by using the temperature field data of the steaming process and the data on the properties of the lees material; The distillation wine extraction data acquisition unit is used to input the upper steamer end temperature field data and the lees material property data into a pre-trained distillation wine extraction model to obtain the distillation wine extraction data output by the distillation wine extraction model; The distillation and wine extraction process control unit is used to use the distillation and wine extraction data to control the steam flow and pressure of the distillation and wine extraction process of the current batch.

9. A computer-readable storage medium having a program stored thereon, characterized in that: When the program is executed by a processor, the method for controlling the lees retort distillation process according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: The electronic device includes at least one processor, and at least one memory and bus connected to the processor; wherein the processor and the memory communicate with each other through the bus; the processor is used to call the program instructions in the memory to execute the lees upper steamer distillation process control method as described in any one of claims 1 to 7.

Images