Blade charging process outlet temperature automatic prediction system

Abstract

The application discloses a blade feeding process outlet temperature automatic prediction system, comprising a data acquisition module, a prediction model module, a temperature prediction module and a temperature control and early warning module; the system respectively establishes a material balance analysis model for outlet blade moisture content prediction and an energy balance analysis model for outlet blade temperature prediction based on the material mass conservation equation and the energy conservation equation of the blade feeding process, and the outlet temperature is predicted in real time through real-time data acquisition and displayed through a dynamic curve diagram, so that automatic prediction and real-time checking of the outlet temperature are realized, the accuracy of the process outlet temperature is improved, and the response speed of temperature automatic regulation is improved, and the problems of large labor, low efficiency and feedback lag in traditional manual monitoring and checking of the outlet temperature are fundamentally overcome.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of tobacco processing, in particular to an automatic prediction system for the outlet temperature of a tobacco leaf feeding process. BACKGROUND

[0002] Different processing temperatures have a great influence on the sensory evaluation of tobacco leaves, that is, processing temperatures can significantly affect the gloss, aroma, harmony, offensive odor, irritation and aftertaste of finished cigarettes. In the production process of cigarette products, by optimizing the best processing conditions, the moisture content of tobacco leaves can be considered while the aroma of tobacco can be retained to the greatest extent, and the offensive odor and irritating odor in tobacco leaves can be volatilized to different degrees.

[0003] In actual production, with the changes of tobacco leaf color, brand and other factors, the zero of the moisture meter for measuring temperature changes, causing measurement errors, which requires manual correction. The specific correction method is to take samples 150mm behind the outlet temperature detector after the process is stable, and quickly put them into a plastic bucket. The mercury bulb of the mercury thermometer is placed in the middle of the sample, the bucket cover is closed, and the value displayed by the temperature detector at the time of sampling is recorded. After three minutes of sample temperature detection, the measured temperature value of the mercury thermometer is read and recorded. Do not take the thermometer out of the sample during reading.

[0004] The above steps are performed three times to obtain three sets of temperature detection data. The average value displayed by the outlet temperature detector is compared with the actual average value detected by the mercury thermometer to verify the temperature detector. This verification method requires manual verification, which is labor-intensive, low-efficiency and has a lagging feedback.

[0005] Therefore, it is necessary to study an automatic prediction and verification system for the outlet temperature of a tobacco leaf feeding process. SUMMARY

[0006] To solve the above problems, the present application provides an automatic prediction system for the outlet temperature of a tobacco leaf feeding process. The present application is applicable to the tobacco processing process and is used for the automatic prediction and real-time verification of the outlet temperature of a tobacco leaf feeding process, which can effectively improve the accuracy, verification efficiency and automatic control response speed of the outlet temperature of the process.

[0007] The technical solution adopted by the present application to solve its technical problems is:

[0008] The automatic prediction system for the outlet temperature of a tobacco leaf feeding process comprises

[0009] The data acquisition module is used for automatically acquiring model parameter data. The data acquisition range includes moisture, circulating air temperature, temperature and equipment detection item parameters related to mass conservation and energy conservation of the tobacco leaf feeding process. The data acquisition range is shown in the following table:

[0010]

[0011]

[0012] a prediction model module, which respectively establishes a material balance analysis model for outlet blade moisture content prediction and an energy balance analysis model for outlet blade temperature prediction based on material mass conservation equation and energy conservation equation of the blade feeding process;

[0013] The material balance analysis model comprises

[0014] ① Steam system balance model

[0015] Main steam: W C = W Ca + W Cb + W Cc ;

[0016] W Cb + W Cc = W C - W Ca ;

[0017] Condensate water:

[0018] V D × ρw= W Cb + W Cc ;

[0019] ② Exhaust system balance model

[0020] The moisture at the exhaust port mainly comes from the compensation steam and hot air system;

[0021]

[0022] Wherein is the conversion coefficient of the injection steam into the blade;

[0023] W = W + W

[0024] ;

[0025] W B = W Ca + ΔV E × AH(T E ) × RH E - V F × AH(T F ) × RH F + W G + W A ;

[0026] Moisture balance:

[0027]

[0028] Dry substance balance:

[0029] W B ×(1-H B )=W G ×(1-β)+W A ×(1-H A );

[0030] Where β is the water content in the feed liquid;

[0031] ④ Outlet water content prediction model

[0032] Based on model ①, model ② and model ③, further obtained:

[0033] Outlet water content prediction model:

[0034]

[0035] The energy balance analysis model includes

[0036] ① Total energy balance model

[0037] Q2+Q3=Q1+Q4+Q5;

[0038] Where Q1 is the heat released by hot air and cylinder heating system (main steam):

[0039]

[0040] Obtained

[0041] Blade temperature rise heat absorption Q2:

[0042]

[0043] Circulating hot air system heat absorption Q3:

[0044]

[0045] Compensation steam heat release Q4:

[0046]

[0047] Feed liquid system heat release Q5:

[0048]

[0049] Where C p,s is the specific heat capacity of the feed liquid excluding water content;

[0050] ② Outlet temperature prediction model

[0051] Based on the total energy balance model, the following is obtained

[0052]

[0053] Substitute the data to establish the equation group to solve the unknown parameters:

[0054] The heat exchange efficiency COP of the heat system, the specific heat capacity C of the tobacco leaf blade dry matter, the specific heat capacity C of the feed liquid excluding water, and the specific heat capacity C of the feed liquid excluding water p,t p,s ;

[0055] Substitute the obtained parameters into the heat exchange efficiency COP calculation formula of the heat system to obtain the outlet temperature prediction model T B :

[0056]

[0057] The temperature prediction module is based on the prediction model module and real-time data, and the outlet temperature is predicted in real time, and is displayed through a dynamic curve chart.

[0058] The temperature control and early warning module automatically adjusts and compensates the steam opening degree when the outlet temperature prediction value shows a temperature deviation, and automatically adjusts and compensates the steam opening degree when the difference between the outlet temperature prediction value and the measured value is greater than or equal to ±5℃. When the difference between the outlet temperature prediction value and the measured value after automatic adjustment still does not meet the threshold requirement, the equipment is shut down and repaired.

[0059] As an improvement of the above technical solution, after the data acquisition module completes real-time acquisition of all parameters, necessary data processing is performed on the collected data: the collected data is excluded from the normal data, and the normal data is input into the prediction model module.

[0060] As an improvement of the above technical solution, the automatic prediction system further comprises a model verification module, which compares and analyzes the outlet temperature prediction value and the measured value in real time / periodically to verify the prediction model accuracy.

[0061] The beneficial effects brought by the present application are:

[0062] The present application can realize automatic prediction and real-time verification of the outlet temperature of the tobacco leaf blade feeding process, effectively improve the accuracy of the process outlet temperature, and the response speed of the temperature automatic regulation, and fundamentally overcome the problems of large labor force, low efficiency and feedback lag in traditional manual monitoring and verification of the outlet temperature.

[0063] ​The prediction model module respectively establishes a material balance analysis model and an energy balance analysis model based on a material mass conservation equation and an energy conservation equation of the blade feeding process, realizes real-time prediction of production parameters by means of a data flow relationship, the model has high precision and is kept synchronous with feedback control; the prediction model is provided with multiple models based on different production brands, so as to meet the difference between different production brands and improve the universality of the temperature automatic prediction system.

[0064] The system is provided with a model verification module, which can compare and analyze the predicted value and the measured value of the outlet temperature in real time / periodically, so as to verify the precision of the prediction model, and can also call historical production parameters, compensate / modify the prediction model based on seasons, environment and the like by means of a big data system, and improve the error prevention ability of the system. BRIEF DESCRIPTION OF DRAWINGS

[0065] The application will be further described below in combination with the drawings and specific embodiments:

[0066] Figure 1 It is a structural block diagram of the blade feeding process outlet temperature automatic prediction system.

[0067] Figure 2 It is a material mass and energy conservation data parameter relationship diagram of the blade feeding process. DETAILED DESCRIPTION

[0068] The technical solutions in the embodiments of the application will be clearly and completely described below in combination with the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the application.

[0069] Embodiment 1

[0070] Reference Figure 1 , the blade feeding process outlet temperature automatic prediction system comprises

[0071] A data acquisition module is used for automatically acquiring model parameter data; the data acquisition range includes moisture, circulating air temperature, temperature and equipment detection item parameters related to material mass conservation and energy conservation of the blade feeding process, and Table 1 is referred to for details:

[0072] Table 1 Range and mode of automatically acquired parameter data of the data acquisition module

[0073]

[0074]

[0075] When the real-time collection of all parameters is completed based on the parameter items in Table 1, the corresponding parameter collection positions and the collection instruments, the data collection module performs necessary data processing on the collected data: abnormal data such as broken flow and 3σ are removed, and normal data is input into the prediction model module;

[0076] The prediction model module respectively establishes a material balance analysis model for outlet blade moisture content prediction and an energy balance analysis model for outlet blade temperature prediction based on the material mass conservation equation and the energy conservation equation of the blade feeding process, Figure 2 An illustration of the relationship between the material mass and energy conservation data parameters of the blade feeding process is shown.

[0077] The material balance analysis model includes

[0078] ① Steam system balance model

[0079] Main steam: W C = W Ca + W Cb + W Cc ;

[0080] W Cb + W Cc = W C - W Ca ;

[0081] Condensate:

[0082] V D × ρw = W Cb + W Cc ;

[0083] ② Exhaust system balance model

[0084] The moisture at the exhaust port mainly comes from the compensation steam and hot air system.

[0085]

[0086] Wherein is the conversion coefficient of the injection steam into the blade;

[0087] W

[0088] ③ Blade feeding system balance model

[0089] Total mass:

[0090] W B = W Ca + ΔV E × AH(T E ) × RHE -V F ×AH(T F )×RH F +W G +W A ;

[0091] Water balance:

[0092]

[0093] Dry matter balance:

[0094] W B ×(1-H B )=W G ×(1-β)+W A ×(1-H A );

[0095] Where β is the water content in the feed liquid;

[0096] ④ Outlet moisture content prediction model

[0097] Based on model ①, model ② and model ③, further obtained:

[0098] Outlet moisture content prediction model:

[0099]

[0100] The energy balance analysis model includes

[0101] ① Total energy balance model

[0102] Q2+Q3=Q1+Q4+Q5;

[0103] Where - heat release Q1 of hot air and cylinder heating system (main steam):

[0104]

[0105] Obtained Blade temperature rise heat absorption Q2:

[0106]

[0107] Circulating hot air system heat absorption Q3:

[0108]

[0109] Compensation steam heat release Q4:

[0110]

[0111] Feed liquid system heat release Q5:

[0112]

[0113] wherein C p,s is the specific heat capacity of the material liquid excluding water content;

[0114] ② Outlet temperature prediction model

[0115] Based on the total energy balance model in ①, the following is obtained:

[0116]

[0117] Substitute the three sets of data to establish an equation group to solve the unknown parameters:

[0118] The heat exchange efficiency COP of the heat system, the specific heat capacity C of the tobacco leaf dry matter, the specific heat capacity C of the material liquid excluding water content, and the specific heat capacity C of the material liquid excluding water content p,t p,s ; Re-substitute the obtained parameters into the heat exchange efficiency COP calculation formula of the heat system to obtain the outlet temperature prediction model T B :

[0119]

[0120] The temperature prediction module is based on the prediction model module and real-time data to real-time predict the outlet temperature of the leaf material adding process, and displays through a dynamic curve chart.

[0121] The temperature control and early warning module automatically adjusts and compensates the steam opening degree when the outlet temperature prediction value shows a temperature deviation. When the difference between the outlet temperature prediction value and the measured value is ≥±5℃, it automatically alarms and automatically adjusts and compensates the steam opening degree. When the difference between the outlet temperature prediction value and the measured value after automatic adjustment still does not meet the threshold requirement, the equipment is shut down and repaired.

[0122] The model verification module compares and analyzes the outlet temperature prediction value and the measured value in real time / periodically to verify the prediction model accuracy.

[0123] The control process of the outlet temperature automatic prediction system of the tobacco leaf material adding process is as follows:

[0124] ​After the device receives the production instruction, the system starts running, calls the model corresponding to the plate number, collects data in real time through the collection instrument arranged at each position of the device, eliminates abnormal data, automatically enters the normal data into the model prediction module for real-time prediction of the outlet moisture and outlet temperature of the blade feeding process, and displays the prediction results through a dynamic curve chart; the curve chart is tracked and analyzed in real time, and when the outlet temperature prediction value shows a temperature deviation, the control system automatically adjusts the steam opening degree to compensate for the deviation; when the difference between the outlet temperature prediction value and the measured value is ≥±5℃ (the threshold value is adjustable), the system automatically alarms and automatically adjusts the steam opening degree; when the difference meets the threshold requirement, the production continues; if the difference between the outlet temperature prediction value and the measured value still does not meet the threshold requirement after automatic adjustment, the device stops and is repaired.

[0125] Embodiment 2

[0126] The blade feeding process outlet temperature automatic prediction method comprises

[0127] Step 1: Data collection

[0128] Automatic collection of model parameter data;

[0129] The data collection range refers to Table 1, including moisture, circulating air temperature, temperature, and device detection items related to material mass conservation and energy conservation in the blade feeding process;

[0130] Step 2: Model construction

[0131] Based on the material mass conservation equation and the energy conservation equation of the blade feeding process, a material balance analysis model for outlet blade moisture prediction and an energy balance analysis model for outlet blade temperature prediction are established respectively;

[0132] Among them: the material balance analysis model includes ① steam system balance model, ② moisture removal system balance model, ③ blade feeding system balance model and ④ outlet moisture prediction model; the energy balance analysis model includes ① total energy balance model and ② outlet temperature prediction model;

[0133] Step 3: Temperature prediction

[0134] Based on the prediction model established in Step 2 and the real-time data collected in Step 1, the outlet temperature of the blade feeding process is predicted in real time, and the prediction results are displayed through a dynamic curve chart;

[0135] Step 4: Temperature control and early warning

[0136] When the outlet temperature prediction value shows a temperature deviation, the steam opening degree is automatically adjusted to compensate for the deviation;

[0137] When the difference between the outlet temperature prediction value and the measured value is ≥ ± 5℃, an alarm is automatically triggered, and the steam opening degree is automatically adjusted and compensated;

[0138] When the difference between the outlet temperature prediction value and the measured value still fails to meet the threshold requirement after automatic adjustment, the equipment is shut down and maintained;

[0139] Step 5: Model verification

[0140] The outlet temperature prediction value is compared with the measured value in real time / periodically to verify the prediction model accuracy.

[0141] When an abnormal alarm is triggered, the steam opening degree is automatically adjusted and compensated by the control system, and then the data is manually checked and entered into the system, and compared with the prediction data. This operation is equivalent to adding an error prevention function to avoid prediction or adjustment errors.

[0142] It should be noted that the above only describes the preferred embodiments of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent replacements to some technical features, and any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. An automatic temperature prediction system for the outlet of the blade feeding process, characterized in that: include The data acquisition module is used to automatically collect model parameter data. The data acquisition scope includes moisture, circulating air temperature, temperature, and equipment detection parameters related to the blade feeding process and material mass conservation and energy conservation. The data acquisition scope is shown in the table below: The prediction model module establishes a material balance analysis model for predicting the moisture content of the outlet blade and an energy balance analysis model for predicting the temperature of the outlet blade, based on the material mass conservation equation and energy conservation equation of the blade feeding process. The material balance analysis model includes ① Steam system balance model Main steam: ; have to ; Condensate: ； ② Tidal discharge system balance model The moisture at the outlet of the vent mainly comes from the compensating steam and hot air system; ； in The conversion coefficient for ejected steam entering the blades; have to ; ③Balance model of blade feeding system Total mass: ; have to ; Moisture balance: ； Dry matter balance: ； in This refers to the water content in the liquid. ④ Export moisture content prediction model Based on models ①, ②, and ③, we further obtain: Export moisture content prediction model: ； The energy balance analysis model includes ① Total Energy Balance Model ； in-- Heat release from hot air and cylinder heating system : ； Seeking ; Leaves absorb heat as they heat up : ； The circulating hot air system absorbs heat. : ； Compensation for heat released by steam : ； Heat released by the liquid feed system : ； in The specific heat capacity of the liquid excluding water; ②Exit temperature prediction model Based on the total energy balance model ①, we get ； Substitute the data to establish a system of equations and solve for the unknown parameters: Heat exchange efficiency of thermal system Specific heat capacity of dry matter in tobacco leaves Specific heat capacity of the liquid excluding water ; Substitute the obtained parameters back into the heat exchange efficiency of the heat system. The calculation formula yields the outlet temperature prediction model. ; The temperature prediction module, based on the prediction model module and real-time data, predicts the outlet temperature in real time and displays it through a dynamic curve. The temperature control and early warning module automatically adjusts the compensating steam opening when the predicted outlet temperature shows a temperature deviation; it automatically alarms and adjusts the compensating steam opening when the difference between the predicted and measured outlet temperature is ≥ ±5℃; and it shuts down the equipment for maintenance when the difference between the predicted and measured outlet temperature still does not meet the threshold requirement after automatic adjustment.

2. The automatic temperature prediction system for the blade feeding process outlet as described in claim 1, characterized in that: After the data acquisition module completes the real-time acquisition of all parameters, it processes the acquired data: it removes abnormal data and inputs normal data into the prediction model module.

3. The automatic temperature prediction system for the blade feeding process outlet as described in claim 1, characterized in that: The automatic prediction system also includes a model verification module, which compares and analyzes the predicted and measured values ​​of the outlet temperature in real time or periodically to verify the accuracy of the prediction model.

Images