A method and system for controlling tea beverage processing distillation temperature

Abstract

The invention discloses a method and system for controlling the distillation temperature of tea beverage processing, which belongs to the technical field of processing control. The invention determines the current optimal extraction component and the current required distillation negative pressure and distillation temperature according to the non-destructive temperature corresponding to each main component required to be extracted from the current tea liquid and the corresponding boiling point-negative pressure relationship curve, and controls and adjusts them to ensure that the required components are effectively extracted during distillation while avoiding the components being destroyed by high temperature and affecting the distillation quality. During the distillation process, the estimated distillation time using the currently required distillation temperature and distillation negative pressure is estimated to determine the timing of analyzing and adjusting the required temperature in the next stage, thereby improving the distillation efficiency. The distillation temperature is monitored and adjusted in real time through a temperature sensor during the process to further ensure the distillation quality.

Description

Technical Field

[0001] The present invention relates to the technical field of processing control, and in particular to a method and system for controlling the distillation temperature of tea beverage processing. Background Art

[0002] Some major ingredients in tea, such as volatile terpenes, water-soluble plant crude polysaccharides, water-soluble plant trace elements, tea polyphenols, and some aromatic compounds, are sensitive to high temperatures and may denature or degrade, leading to a decline in the quality of the final tea product, such as poor taste or nutritional value. Therefore, how to regulate and control the distillation temperature during tea processing and distillation is an urgent problem that needs to be solved. Summary of the invention

[0003] The present invention is to solve the technical problems existing in the prior art. The present invention provides a method for controlling the distillation temperature of tea beverage processing, comprising the following steps: S1, boiling tea raw materials into tea liquid and then cooling it to a preset temperature; S2. Acquire tea liquid data of the tea liquid, including the name of the tea liquid, the name of the main component to be extracted, the non-destructive temperature, and the corresponding boiling point-negative pressure relationship curve; S3, according to the non-destructive temperature corresponding to each main component to be extracted from the current tea liquid and the corresponding boiling point-negative pressure relationship curve, determine the current optimal extraction component and the current required distillation negative pressure and distillation temperature and control and adjust them; S4, estimating the estimated distillation time for distillation using the currently required distillation temperature and distillation negative pressure, and after reaching the current estimated distillation time, extracting the current optimal extraction component from the main components required to be extracted from the current tea liquid, and repeating steps S3 and S4 until the tea liquid in the negative pressure distillation furnace is completely evaporated; In the process of executing step S3 to step S4, the following steps are also executed simultaneously: T1. During the distillation process, the real-time distillation temperature of the negative pressure distillation furnace is monitored by a temperature sensor; T2. If the error between the monitored real-time distillation temperature and the currently required distillation temperature is greater than the preset threshold, the power of the heating device of the negative pressure distillation furnace is adjusted through the PID controller to adjust the real-time distillation temperature so that the error between the real-time distillation temperature and the currently required distillation temperature is less than the preset threshold.

[0004] Furthermore, the determination of the currently required distillation negative pressure and distillation temperature and the control and adjustment thereof specifically include the following steps: S31, selecting the minimum non-destructive temperature from the non-destructive temperatures of the main component currently to be extracted, and taking the main component corresponding to the minimum non-destructive temperature as the optimal extraction component; S32. Calculate the current required distillation temperature T using the minimum non-destructive temperature, , where, represents the minimum non-destructive temperature, and A1 represents the first preset adjustment parameter, A1 > 0; S33. According to the boiling point - negative pressure relationship curve corresponding to the optimal extraction component, obtain the first adjustment negative pressure P1 and the second adjustment negative pressure P2 corresponding to the optimal extraction component, P1 < P2. The first adjustment negative pressure makes the boiling point FD of the optimal extraction component satisfy, and the second adjustment negative pressure makes the boiling point FD of the optimal extraction component satisfy. Finally, calculate the distillation negative pressure P, where P = (P1 + P2) / 2, A2 > 0, and A2 represents the second preset parameter; S34. After adjusting the negative pressure value of the negative pressure distillation furnace to P, adjust the distillation temperature to T.

[0005] Further, estimate the predicted distillation duration of distillation using the current required distillation temperature and distillation negative pressure, specifically: According to the current required distillation temperature and distillation negative pressure, the tea liquid data of the current tea liquid, the real-time remaining tea liquid volume, and the name of the current optimal extraction component, estimate and obtain the predicted distillation duration through a pre-trained prediction model or by staff combining experience.

[0006] Further, the real-time remaining tea liquid volume is obtained by monitoring the tea liquid in the negative pressure distillation furnace using a liquid level sensor.

[0007] Further, the temperature sensor is temperature compensated through a pre-trained deep belief network model.

[0008] Further, the deep belief network model is hyperparameter optimized through the beluga optimization algorithm.

[0009] Further, the hyperparameter optimization through the beluga optimization algorithm is specifically: A1. Initialize the hyperparameter space. According to the hyperparameter space, randomly generate a preset number of belugas to form an initial population. The hyperparameter space represents the types of hyperparameters to be optimized and the corresponding numerical optimization intervals. Each beluga represents a set of hyperparameter combinations; A2. For each beluga, train the deep belief network model for the temperature compensation task, and calculate the fitness according to their respective training output results. Mean square error or mean absolute error, etc., can be selected as the fitness; A3. Select the individual with the highest fitness in the current population and use it as the leading beluga; A4. Determine the position update step of the current iteration according to the balance factor B of the current iteration. If B>0.5, the current iteration updates the position of the white whale through the exploration step of the algorithm. If B≤0.5, the current iteration updates the position of the white whale through the development step of the algorithm. A5. Determine whether the balance factor B of the current iteration is less than the falling probability W of the current iteration: If not, iterate with the white whale position updated in step A4, and repeat steps A2 to A5 until the number of iterations reaches the preset maximum iteration value, and then stop, and take the value of the hyperparameter represented by the real-time leading white whale as the optimal solution; If so, the whale fall step of the algorithm is used to update the white whale position obtained in step 4 of the current iteration, further update the white whale position and iterate, and repeat steps A2 to A5 until the number of iterations reaches the preset maximum iteration value and then stops. The value of the hyperparameter represented by the real-time leading white whale is used as the optimal solution.

[0010] Furthermore, the step of developing the algorithm to update the position of the white whale is specifically: Adjust the random jump intensity C1 in the development step through the Funh chaos map: , , Where r1 represents a random number of (0,1), t represents the number of completed iterations, Tmax represents the preset maximum number of iterations, H represents the chaotic value obtained by Funh chaotic mapping, and when t=0, H is a non-zero random number of (-1,1); According to the adjusted random jump intensity, the first pre-updated position X1 of the beluga whale is calculated by the Levy flight strategy: , Among them, i represents the i-th beluga whale, Indicates the current position of the leading white whale, represents the Levy walk function, represents the position of the random white whale k after completing t iterations, represents the position of the ith beluga whale after completing t iterations, and r2 represents a random number (0,1); Through the dynamic reverse learning strategy, the reverse solution Q of the corresponding hyperparameter is calculated according to the current solution q of each hyperparameter corresponding to the first pre-update position of the White Whale, and the reverse solution set of each hyperparameter at the pre-update position is used as the second pre-update position corresponding to the White Whale: , Among them, u and l represent the upper and lower limits of the numerical optimization interval of the corresponding hyperparameter type, r3 and r4 represent random numbers (0,1); The beluga whales before this position update are taken as the first population, the beluga whales at the first pre-update position are taken as the second population, the old population and the beluga whales at the second pre-update position are obtained as the third population, the fitness of all beluga whales in the first population, the second population and the third population are obtained, and the beluga whales with the same preset number are selected from large to small according to the fitness as the population after this development step.

[0011] Furthermore, step T1 further includes: monitoring the real-time distillation negative pressure of the negative pressure distillation furnace by a vacuum pressure sensor during the distillation process; Step T2 also includes: if the error between the monitored real-time distillation negative pressure and the currently required distillation negative pressure is greater than a preset threshold, the power of the negative pressure device is adjusted by the second PID controller to thereby adjust the real-time distillation negative pressure.

[0012] The present invention also provides a tea beverage processing and distillation temperature control system, comprising: A tea liquid data acquisition module, used to acquire tea liquid data of the tea liquid, including the name of the tea liquid, the name of the main component to be extracted and the non-destructive temperature of each main component and the corresponding boiling point-negative pressure relationship curve; The adjustment and analysis module is used to determine the current optimal extraction component and the current required distillation negative pressure and distillation temperature and perform control and adjustment according to the non-destructive temperature corresponding to each main component required to be extracted from the current tea liquid and the corresponding boiling point-negative pressure relationship curve; A duration estimation module, used to estimate the estimated distillation duration for distillation using the currently required distillation temperature and distillation negative pressure; Monitoring module, used to monitor the real-time distillation temperature; The control module is used to adjust the power of the heating device and thus adjust the real-time distillation temperature according to the monitored real-time distillation temperature and the currently required distillation temperature.

[0013] Compared with the prior art, the present invention has the following beneficial effects: The present invention determines the current optimal extraction component and the current required distillation negative pressure and distillation temperature and performs control and adjustment according to the non-destructive temperature corresponding to each main component required to be extracted from the current tea liquid and the corresponding boiling point-negative pressure relationship curve, thereby ensuring that the required components are effectively extracted during distillation while avoiding the components being destroyed by high temperature and affecting the distillation quality. During the distillation process, the estimated distillation time for distillation using the current required distillation temperature and distillation negative pressure is estimated to determine the timing of analyzing and adjusting the required temperature in the next stage, thereby improving the distillation efficiency. During the process, the distillation temperature is monitored and adjusted in real time by a temperature sensor, thereby further ensuring the distillation quality. The present invention uses the value obtained by subtracting the preset adjustment parameter from the minimum non-destructive temperature as the distillation temperature, so that there is room for temperature jumps during the distillation process, ensuring that the minimum non-destructive temperature is not exceeded, thereby preventing the corresponding main components from being destroyed and thus reducing the distillation quality; The present invention uses a deep belief network model to perform temperature compensation on a temperature sensor, thereby improving the accuracy of temperature monitoring and ensuring the timeliness of adjusting the distillation temperature. It also improves the steps of the White Whale optimization algorithm to improve the accuracy of hyperparameter optimization of the deep belief network model, improve the compensation accuracy of the deep belief network model, further improve the temperature monitoring accuracy, and ensure the timeliness of adjusting the distillation temperature. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention. In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0015] Figure 1 It is a flow chart of a tea beverage processing distillation temperature control method of the present invention; Figure 2 It is a flow chart of step S3 of a method for controlling the temperature of tea beverage processing and distillation of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0018] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0019] Embodiment 1 See also Figure 1 As shown, the present invention provides a method for controlling the temperature of tea beverage processing and distillation, which specifically comprises the following steps: S1, boiling tea raw materials into tea liquid and then cooling it to a preset temperature; S2. Acquire tea liquid data of the tea liquid, including the name of the tea liquid, the name of the main component to be extracted and the non-destructive temperature of each main component and the corresponding boiling point-negative pressure relationship curve; S3, according to the non-destructive temperature corresponding to each main component to be extracted from the current tea liquid and the corresponding boiling point-negative pressure relationship curve, determine the current optimal extraction component and the current required distillation negative pressure and distillation temperature and control and adjust them; S4, estimating the estimated distillation time for distillation using the currently required distillation temperature and distillation negative pressure, and after reaching the current estimated distillation time, extracting the current optimal extraction component from the main components required to be extracted from the current tea liquid, and repeating steps S3 and S4 until the tea liquid in the negative pressure distillation furnace is completely evaporated; In the process of executing step S3 to step S4, the following steps are also executed simultaneously: T1. During the distillation process, the real-time distillation temperature of the negative pressure distillation furnace is monitored by a temperature sensor; T2. If the error between the monitored real-time distillation temperature and the currently required distillation temperature is greater than the preset threshold, the power of the heating device of the negative pressure distillation furnace is adjusted through the PID controller to adjust the real-time distillation temperature so that the error between the real-time distillation temperature and the currently required distillation temperature is less than the preset threshold.

[0020] In step S1, the tea raw materials are boiled into tea liquid and then cooled to a preset temperature. Specifically, the tea raw materials are poured into a high-temperature and high-pressure furnace, a barrel is arranged in the middle of the high-temperature and high-pressure furnace, and the tea raw materials are specifically placed in the barrel. The furnace door and the liquid outlet valve are closed, the specified temperature is set, and the pressure in the furnace is adjusted by increasing the air pressure or vacuuming for boiling. After boiling is completed, the boiled tea liquid is cooled to a preset temperature, the liquid outlet valve is opened, and the tea liquid is pumped into a negative pressure distillation furnace connected to the high-temperature and high-pressure furnace by a liquid pumping motor for subsequent distillation.

[0021] In some implementations, the brewed tea liquid is cooled to 90 degrees Celsius.

[0022] In this scheme, the brewed tea liquid is cooled to a preset temperature (such as 90 degrees Celsius) before distillation, which can reduce the thermal damage in the initial high-temperature stage. After the brewing is completed in the high-temperature and high-pressure furnace, the temperature of the tea liquid is often high. If distillation is performed directly, this high-temperature stage may cause damage to the heat-sensitive components in the tea liquid; and at this time the tea liquid is at a certain temperature, and can quickly reach the required boiling point during distillation, which can save the energy required for heating, thereby improving the distillation efficiency.

[0023] In step S2, the name of the main component to be extracted from the tea liquid, the non-destructive temperature of each main component and the corresponding boiling point-negative pressure relationship curve are obtained. Specifically, according to the tea raw materials used, the main components corresponding to the extraction are identified in the database. The database records the name of the tea liquid, the corresponding tea raw materials, the main components corresponding to the extraction, the non-destructive temperature of each main component and the corresponding boiling point-negative pressure relationship curve.

[0024] The non-destructive temperature corresponding to the main component refers to the highest temperature that the main component can withstand without being destroyed (such as denaturation, decomposition, etc.). Some main components in tea drinks, such as volatile terpenes, water-soluble plant crude polysaccharides, water-soluble plant trace elements, tea polyphenols, some aromatic compounds, etc., are sensitive to high temperatures and may be denatured or degraded, which will lead to a decrease in the quality of the final tea product, such as poor taste or nutritional value. Therefore, in the processing and distillation of tea liquid, the distillation temperature should be adjusted from low to high to ensure that it does not exceed the corresponding non-destructive temperature. By setting negative pressure to reduce the boiling point of the required main components, the corresponding main components can be distilled and extracted while the distillation temperature does not exceed the corresponding non-destructive temperature.

[0025] The boiling point-negative pressure relationship curve reflects the boiling points of the corresponding main components at various negative pressure values. A negative pressure value of 0 represents the boiling point under standard atmospheric pressure.

[0026] The non-destruction temperature of each main component and the corresponding boiling point-negative pressure relationship curve are specifically obtained from historical distillation data, experimental data, relevant literature data, etc., and stored in the database.

[0027] Refer to Figure 2 As shown, in step S3, according to the non-destruction temperature corresponding to each main component to be extracted from the current tea liquid, the distillation temperature and distillation negative pressure of the negative pressure distillation furnace are adjusted, specifically including the following steps: S31. Screen out the minimum non-destruction temperature among the non-destruction temperatures of each main component to be extracted currently, and use the main component corresponding to the minimum non-destruction temperature as the optimal extraction component; S32. Calculate the current required distillation temperature T based on the minimum non-destruction temperature, , where, represents the minimum non-destruction temperature, and A1 represents the first preset adjustment parameter, A1>0; S33. According to the boiling point-negative pressure relationship curve corresponding to the optimal extraction component, obtain the first adjustment negative pressure P1 and the second adjustment negative pressure P2 corresponding to the optimal extraction component, P1<P2, and the first adjustment negative pressure makes the boiling point FD of the optimal extraction component satisfy , and the second adjustment negative pressure makes the boiling point FD of the optimal extraction component satisfy , and finally calculate the distillation negative pressure P, where P=(P1+P2) / 2, A2>0, and A2 represents the second preset parameter; S34. After adjusting the negative pressure value of the negative pressure distillation furnace to P, adjust the distillation temperature to T.

[0028] In step S32, the value obtained by subtracting the preset adjustment parameter from the minimum non-destruction temperature is used as the distillation temperature. At this distillation temperature, it can more ensure that the main component corresponding to the minimum non-destruction temperature is not damaged, because the non-destruction temperature is the highest temperature that the main component can withstand without being damaged. However, in the actual distillation process, the temperature will jump due to various factors. Therefore, in this solution, the value obtained by subtracting the preset adjustment parameter from the minimum non-destruction temperature is used as the distillation temperature, so that there is room for temperature jump during the distillation process, ensuring that the minimum non-destruction temperature is not exceeded, so that the corresponding main component is not damaged and the distillation quality is reduced.

[0029] In step S33, because the first adjustment negative pressure makes the optimal extraction component satisfy , and the second adjustment negative pressure makes the optimal extraction component satisfy , and A2 > 0, P1 < P2. Since the boiling point is lower at higher negative pressure, the negative pressure from the first regulated negative pressure to the second regulated negative pressure can make the boiling point of the optimal extraction component equal to or less than the corresponding non-destruction temperature to avoid being damaged by high temperature. Also, the second regulated negative pressure is set to avoid controlling the distillation negative pressure too high, which may cause problems such as explosive boiling of the tea drink, unstable distillation, significant loss of the required extraction components, damage to the distillation equipment, and increased risk. Therefore, the distillation negative pressure is controlled at the intermediate value between the first regulated negative pressure and the second regulated negative pressure corresponding to the optimal extraction component, which can not only make the boiling point of the corresponding component less than the corresponding non-destruction temperature to avoid the corresponding component being damaged by high temperature, but also avoid controlling the distillation negative pressure too high, thus preventing problems such as explosive boiling of the tea drink, unstable distillation, significant loss of the required extraction components, damage to the distillation equipment, and increased risk.

[0030] It should be noted that if there is more than one main component corresponding to the selected minimum non-destruction temperature, one of the main components is randomly selected as the current optimal extraction component.

[0031] In step S4, according to the current required distillation temperature and distillation negative pressure, the tea liquid data of the current tea liquid and the real-time remaining tea liquid volume, and the name of the current optimal extraction component, the estimated distillation duration is obtained through a pre-trained prediction model or by staff combining historical distillation experience.

[0032] In step S4, the real-time remaining tea liquid volume can be obtained by monitoring the tea liquid in the negative pressure distillation furnace with a liquid level sensor.

[0033] During the execution of steps S3 to S4, the following steps are also simultaneously executed: T1. During the distillation process, the real-time distillation temperature of the negative pressure distillation furnace is monitored by a temperature sensor; T2. If the error between the monitored real-time distillation temperature and the current required distillation temperature is greater than the preset threshold, the power of the heating device is adjusted through a PID controller to further adjust the real-time distillation temperature.

[0034] In step T1, the temperature sensor is temperature-compensated through a pre-trained deep belief network model.

[0035] Temperature compensation refers to the process of correcting the sensor reading error caused by environmental temperature changes. Temperature changes may affect the output signal of the sensor, resulting in the measured value deviating from the actual value. Through temperature compensation, this deviation can be reduced, and the accuracy of sensor measurement can be improved.

[0036] The Deep Belief Network (DBN) model is a deep learning model. First, DBN can capture nonlinear relationships in input data. The output of temperature sensors is usually not linearly related to the actual temperature. Especially when working in a wide temperature range, DBN can approximate complex function mappings through multiple layers of nonlinear transformations, thereby better fitting the relationship between sensor output and true temperature. Second, a key feature of DBN is that it can automatically learn high-level features in input data. For temperature compensation, this means that DBN can identify which factors (such as sensor output, ambient temperature, humidity, etc.) have a significant impact on the final temperature measurement results and extract useful features from them for compensation calculations. Third, if temperature compensation involves multiple variables (such as multiple sensor readings, readings under different environmental conditions, etc.), DBN can effectively process high-dimensional input spaces, which is particularly useful for multivariate or multi-sensor systems because it can integrate information from different sources to improve compensation accuracy. Finally, DBN can overcome the overfitting problem to a certain extent and improve the robustness and generalization ability of the model through greedy layer-by-layer training and subsequent fine-tuning steps. This means that even under temperature conditions that have not appeared in the training set, the model can give relatively accurate compensation results.

[0037] In some embodiments, the hyperparameters of the deep belief network model in step T1 are optimized by the Beluga optimization algorithm.

[0038] The hyperparameters of the deep belief network model refer to the parameters that need to be manually set before training the model, such as the number of layers, which determines the depth of the network. More layers may help capture more complex features, but may also lead to overfitting or increase the difficulty of training; the number of nodes per layer defines how many hidden units or nodes there are in each layer. This affects the capacity of the model, that is, the complexity of the function it can learn; the learning rate controls the speed of updating the weights. Too high a learning rate may cause the training process to be unstable, and too low a learning rate may make the training process very slow, etc. Therefore, hyperparameters have an important impact on model performance. Optimizing the hyperparameters of the deep belief network model can enable the model to learn the relationship between temperature readings and true temperatures more accurately, thereby improving compensation accuracy.

[0039] Beluga Whale Optimization (BWO) is a swarm intelligence optimization algorithm that imitates the behavior of beluga whale populations. It can not only converge at a faster speed, but also has stronger global capabilities and can optimize the hyperparameters of the model well. In the Beluga Whale Optimization algorithm, the position of the beluga whale represents the solution of each hyperparameter that needs to be optimized. In this solution, the steps for hyperparameter optimization of the deep belief network model are as follows: A1. Initialize the hyperparameter space. According to the hyperparameter space, randomly generate a preset number of beluga whales to form an initial population. The hyperparameter space represents the type of hyperparameters to be optimized and the corresponding numerical optimization range. Each beluga whale represents a set of hyperparameter combinations. A2. For each beluga whale, train the DBN model to perform the temperature compensation task and calculate the fitness based on the training output results. The mean square error or mean absolute error can be selected as the fitness. A3. Select the individual with the highest fitness in the current population and use it as the leader beluga whale; A4. Determine the position update step of the current iteration according to the balance factor B of the current iteration. If B>0.5, the current iteration updates the position of the white whale through the exploration step of the algorithm. If B≤0.5, the current iteration updates the position of the white whale through the development step of the algorithm. A5. Determine whether the balance factor B of the current iteration is less than the falling probability W of the current iteration: If not, iterate with the white whale position updated in step A4, and repeat steps A2 to A5 until the number of iterations reaches the preset maximum iteration value, and then stop, and take the value of the hyperparameter represented by the real-time leading white whale as the optimal solution; If so, the whale fall step of the algorithm is used to update the white whale position obtained in step 4 of the current iteration, further update the white whale position and iterate, and repeat steps A2 to A5 until the number of iterations reaches the preset maximum iteration value and then stops. The value of the hyperparameter represented by the real-time leading white whale is used as the optimal solution.

[0040] B=B0×(1-t / (2Tmax)), B0 is a number that changes randomly between (0,1). With continuous iterations, the fluctuation range of B will be reduced to (0,0.5), and the probability of entering the development step will increase significantly.

[0041] W=0.1-0.05×(t / Tmax).

[0042] In some embodiments, the step of updating the beluga whale position through the algorithm development step is specifically: Adjust the random jump intensity C1 in the development step through the Funh chaos map: Where r1 represents a random number of (0,1), t represents the number of completed iterations, Tmax represents the preset maximum number of iterations, H represents the chaotic value obtained by Funh chaotic mapping, and when t=0, H is a non-zero random number of (-1,1); According to the adjusted random jump intensity, the first pre-updated position X1 of the beluga whale is calculated by the Levy flight strategy: Among them, i represents the i-th beluga whale, Indicates the current position of the leading white whale, represents the Levy walk function, represents the position of the random white whale k after completing t iterations, represents the position of the ith beluga whale after completing t iterations, and r2 represents a random number (0,1); Through the dynamic reverse learning strategy, the reverse solution Q of the corresponding hyperparameter is calculated according to the current solution q of each hyperparameter corresponding to the first pre-update position of the White Whale, and the reverse solution set of each hyperparameter at the pre-update position is used as the second pre-update position corresponding to the White Whale: Among them, u and l represent the upper and lower limits of the numerical optimization interval of the corresponding hyperparameter type, r3 and r4 represent random numbers (0,1); The beluga whales before this position update are taken as the first population, the beluga whales at the first pre-update position are taken as the second population, the old population and the beluga whales at the second pre-update position are obtained as the third population, the fitness of all beluga whales in the first population, the second population and the third population are obtained, and the beluga whales with the same preset number are selected from large to small according to the fitness as the population after this development step. At this time, the position of each beluga whale in the population is the position of the beluga whale finally updated in this development step.

[0043] Similarly, in this embodiment, in updating the position of the beluga whales through the exploration step of the algorithm, the beluga whales before this position update are taken as the first population, and the beluga whales after this position update are taken as the second population. The fitness of all beluga whales in the first population and the second population is obtained, and the beluga whales with the same preset number are selected from large to small according to the fitness as the population after this exploration step.

[0044] It should be noted that the position update in the exploration step of this scheme before the population after this exploration step is screened out by fitness also belongs to the pre-update, that is, it is only calculated by the algorithm formula, and the calculation method is the same as the calculation of the updated position of the Beluga whale in the exploration step in the existing Beluga whale optimization algorithm. It belongs to the existing technology and will not be repeated here.

[0045] Similarly, the calculation of the balance factor B and the falling probability W in the White Whale optimization algorithm of this scheme and the specific calculation method of updating the White Whale position in the whale falling step are also the same as the calculation method of the existing White Whale optimization algorithm. The Levy flight strategy has been introduced into the existing White Whale optimization algorithm to enhance the convergence of the algorithm. The Levy flight strategy is a random search mode that simulates the foraging behavior of organisms. The Levy walk function is an algorithm to implement the Levy flight strategy. The specific formula belongs to the existing technology and will not be repeated here. In the White Whale optimization algorithm, the random jump intensity is used to measure the intensity of the Levy walk. In the original White Whale optimization algorithm, the random jump intensity ,Such calculation methods do not fully consider the adaptive requirements of the ,algorithm in the entire search process, resulting in poor search ,performance of the algorithm in some cases.

[0046] Therefore, in this scheme, the random jump intensity is adjusted by using the Funh chaotic mapping. According to the Fuch mapping formula, the nonlinear transformation in the Fuch mapping makes the chaotic value present complex dynamic behavior in the iteration process. Compared with other chaotic mappings, such as the Tent mapping, the Fuch mapping is not easy to fall into a periodic cycle, thereby ensuring the randomness of the chaotic sequence. Therefore, the Fuch chaotic mapping shows stronger chaotic characteristics and more balanced ergodicity, which helps to improve the ergodicity and optimization accuracy of the algorithm, more effectively coordinate the relationship between global search and local search, and enhance the algorithm's adaptability.

[0047] In some embodiments, step T1 further includes: monitoring the real-time distillation negative pressure of the negative pressure distillation furnace by a vacuum pressure sensor during the distillation process; Step T2 also includes: if the error between the monitored real-time distillation negative pressure and the currently required distillation negative pressure is greater than a preset threshold, the power of the negative pressure device is adjusted by the second PID controller to thereby adjust the real-time distillation negative pressure.

[0048] The negative pressure device may optionally use a vacuum pump, a vacuum valve, etc.

[0049] In some embodiments, the vacuum pressure sensor is temperature compensated by a pre-trained second deep belief network model.

[0050] In some embodiments, the hyperparameters of the second deep belief network model are optimized by a White Whale optimization algorithm, which is the same as the White Whale optimization algorithm for optimizing the deep belief network model described above.

[0051] Embodiment 2 The present invention also provides a tea beverage processing distillation temperature control system provided by the present invention, which specifically comprises: A tea liquid data acquisition module, used to acquire tea liquid data of the tea liquid, including the name of the tea liquid, the name of the main component to be extracted and the non-destructive temperature of each main component and the corresponding boiling point-negative pressure relationship curve; The adjustment and analysis module is used to determine the current optimal extraction component and the current required distillation negative pressure and distillation temperature and perform control and adjustment according to the non-destructive temperature corresponding to each main component required to be extracted from the current tea liquid and the corresponding boiling point-negative pressure relationship curve; A duration estimation module, used to estimate the estimated distillation duration for distillation using the currently required distillation temperature and distillation negative pressure; Monitoring module, used to monitor the real-time distillation temperature; The control module is used to adjust the power of the heating device and thus adjust the real-time distillation temperature according to the monitored real-time distillation temperature and the currently required distillation temperature.

[0052] The specific implementation method of each of the above modules is the same as the tea beverage processing distillation temperature control method provided by the present invention, and will not be repeated here.

[0053] Embodiment 3 The present invention also provides an electronic device, including: a processor, a sending device, an input device, an output device and a memory. The processor can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit, or one or more integrated circuits, and is used to execute relevant programs to implement the technical solution provided in the embodiment of the present application. The memory can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device or a random access memory (RAM), and is used to store computer program code. The computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes a method as described in any of the above possible implementation methods.

[0054] Embodiment 4 The present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes a method as described in any possible implementation manner.

[0055] The beneficial effects of the present invention are: The present invention determines the current optimal extraction component and the current required distillation negative pressure and distillation temperature and performs control and adjustment according to the non-destructive temperature corresponding to each main component required to be extracted from the current tea liquid and the corresponding boiling point-negative pressure relationship curve, thereby ensuring that the required components are effectively extracted during distillation while avoiding the components being destroyed by high temperature and affecting the distillation quality. During the distillation process, the estimated distillation time for distillation using the current required distillation temperature and distillation negative pressure is estimated to determine the timing of analyzing and adjusting the required temperature in the next stage, thereby improving the distillation efficiency. During the process, the distillation temperature is monitored and adjusted in real time by a temperature sensor, thereby further ensuring the distillation quality. The present invention uses the value obtained by subtracting the preset adjustment parameter from the minimum non-destructive temperature as the distillation temperature, so that there is room for temperature jumps during the distillation process, ensuring that the minimum non-destructive temperature is not exceeded, thereby preventing the corresponding main components from being destroyed and thus reducing the distillation quality; The present invention uses a deep belief network model to perform temperature compensation on a temperature sensor, thereby improving the accuracy of temperature monitoring and ensuring the timeliness of adjusting the distillation temperature. It also improves the steps of the White Whale optimization algorithm to improve the accuracy of hyperparameter optimization of the deep belief network model, improve the compensation accuracy of the deep belief network model, further improve the temperature monitoring accuracy, and ensure the timeliness of adjusting the distillation temperature.

[0056] In the description of the specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0057] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method of each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (RandomAccess Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0058] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for controlling the distillation temperature of tea beverage processing, characterized in that: It includes the following steps: S1. After boiling the tea drink raw materials to obtain tea liquid, cool it down to a preset temperature; S2. Obtain the tea liquid data of the tea liquid, including the name of the tea liquid, the name of the main components to be extracted, the non-destructive temperature, and the corresponding boiling point-vacuum relationship curve; S3. According to the non-destructive temperature corresponding to each main component to be extracted from the current tea liquid and the corresponding boiling point-vacuum relationship curve, determine the current optimal extraction component, the current required distillation vacuum and distillation temperature, and perform control and adjustment; S4. Estimate the estimated distillation duration for distillation using the current required distillation temperature and distillation vacuum. After reaching the current estimated distillation duration, extract the current optimal extraction component from the main components to be extracted from the current tea liquid, and then repeat steps S3 and S4 until the tea liquid in the vacuum distillation furnace is completely evaporated; During the execution of steps S3 to S4, the following steps are also simultaneously executed: T1. During the distillation process, monitor the real-time distillation temperature of the vacuum distillation furnace through a temperature sensor; T2. If the error between the monitored real-time distillation temperature and the current required distillation temperature is greater than the preset threshold, adjust the power of the heating device of the vacuum distillation furnace through a PID controller to adjust the real-time distillation temperature, so that the error between the real-time distillation temperature and the current required distillation temperature is less than the preset threshold.

2. The tea beverage processing distillation temperature control method according to claim 1, characterized in that: The determination of the current required distillation vacuum and distillation temperature and the control and adjustment specifically include the following steps: S31. Screen out the minimum non-destructive temperature among the non-destructive temperatures of the main components to be extracted currently, and use the main component corresponding to the minimum non-destructive temperature as the optimal extraction component; S32, calculating the currently required distillation temperature T based on the minimum non-destructive temperature, ,in, It represents the minimum non-destructive temperature, A1 represents the first preset adjustment parameter, A1>0; S33. According to the boiling point-vacuum relationship curve corresponding to the optimal extraction component, obtain the first adjustment vacuum P1 and the second adjustment vacuum P2 corresponding to the optimal extraction component, P1 < P2. The first adjustment vacuum makes the boiling point FD of the optimal extraction component satisfied, and the second adjustment vacuum makes the boiling point FD of the optimal extraction component satisfied. Finally, calculate the distillation vacuum P, where P = (P1 + P2) / 2, A2 > 0, and A2 represents the second preset parameter; S34. After adjusting the vacuum value of the vacuum distillation furnace to P, adjust the distillation temperature to T.

3. The tea beverage processing distillation temperature control method according to claim 1, characterized in that: The estimation of the estimated distillation duration for distillation using the current required distillation temperature and distillation vacuum is specifically: According to the current required distillation temperature and distillation vacuum, the tea liquid data of the current tea liquid, the real-time remaining tea liquid volume, and the name of the current optimal extraction component, estimate and obtain the estimated distillation duration through a pre-trained prediction model or by staff combining experience.

4. The tea beverage processing distillation temperature control method according to claim 3, characterized in that: The real-time remaining tea liquid volume is obtained by monitoring the tea liquid in the vacuum distillation furnace through a liquid level sensor.

5. The tea beverage processing distillation temperature control method according to claim 1, characterized in that: The temperature sensor is temperature compensated through a pre-trained deep belief network model.

6. The tea beverage processing distillation temperature control method according to claim 5, characterized in that: The deep belief network model is optimized for hyperparameters through a beluga optimization algorithm.

7. The tea beverage processing distillation temperature control method according to claim 6, characterized in that: The optimization of hyperparameters through the beluga optimization algorithm is specifically: A1. Initialize the hyperparameter space. According to the hyperparameter space, randomly generate a preset number of beluga whales to form an initial population. The hyperparameter space represents the type of hyperparameters to be optimized and the corresponding numerical optimization range. Each beluga whale represents a set of hyperparameter combinations. A2. For each beluga whale, train the deep belief network model to perform the temperature compensation task, and calculate the fitness based on the training output results. The mean square error or mean absolute error can be selected as the fitness; A3. Select the individual with the highest fitness in the current population and use it as the leader beluga whale; A4. Determine the position update step of the current iteration according to the balance factor B of the current iteration. If B>0.5, the current iteration updates the position of the white whale through the exploration step of the algorithm. If B≤0.5, the current iteration updates the position of the white whale through the development step of the algorithm. A5. Determine whether the balance factor B of the current iteration is less than the falling probability W of the current iteration: If not, iterate with the white whale position updated in step A4, and repeat steps A2 to A5 until the number of iterations reaches the preset maximum iteration value, and then stop, and take the value of the hyperparameter represented by the real-time leading white whale as the optimal solution; If so, the whale fall step of the algorithm is used to update the white whale position obtained in step 4 of the current iteration, further update the white whale position and iterate, and repeat steps A2 to A5 until the number of iterations reaches the preset maximum iteration value and then stops. The value of the hyperparameter represented by the real-time leading white whale is used as the optimal solution.

8. The tea beverage processing distillation temperature control method according to claim 7, characterized in that: The steps of developing the algorithm to update the position of the white whale are as follows: Adjust the random jump intensity C1 in the development step through the Funh chaos map: ， ， Where r1 represents a random number of (0,1), t represents the number of completed iterations, Tmax represents the preset maximum number of iterations, H represents the chaotic value obtained by Funh chaotic mapping, and when t=0, H is a non-zero random number of (-1,1); According to the adjusted random jump intensity, the first pre-updated position X1 of the beluga whale is calculated by the Levy flight strategy: ， Among them, i represents the i-th beluga whale, Indicates the current position of the leading white whale, represents the Levy walk function, represents the position of the random white whale k after completing t iterations, represents the position of the ith beluga whale after completing t iterations, and r2 represents a random number (0,1); Through the dynamic reverse learning strategy, the reverse solution Q of the corresponding hyperparameter is calculated according to the current solution q of each hyperparameter corresponding to the first pre-update position of the White Whale, and the reverse solution set of each hyperparameter at the pre-update position is used as the second pre-update position corresponding to the White Whale: ， Among them, u and l represent the upper and lower limits of the numerical optimization interval of the corresponding hyperparameter type, r3 and r4 represent random numbers (0,1); The beluga whales before this position update are taken as the first population, the beluga whales at the first pre-update position are taken as the second population, the old population and the beluga whales at the second pre-update position are obtained as the third population, the fitness of all beluga whales in the first population, the second population and the third population are obtained, and the beluga whales with the same preset number are selected from large to small according to the fitness as the population after this development step.

9. The tea beverage processing distillation temperature control method according to claim 1, characterized in that: Step T1 also includes: monitoring the real-time distillation negative pressure of the negative pressure distillation furnace by a vacuum pressure sensor during the distillation process; Step T2 also includes: if the error between the monitored real-time distillation negative pressure and the currently required distillation negative pressure is greater than a preset threshold, the power of the negative pressure device is adjusted by the second PID controller to thereby adjust the real-time distillation negative pressure.

10. A tea beverage processing distillation temperature control system, applied to the tea beverage processing distillation temperature control method according to any one of claims 1 to 9, characterized in that: include: A tea liquid data acquisition module, used to acquire tea liquid data of the tea liquid, including the name of the tea liquid, the name of the main component to be extracted and the non-destructive temperature of each main component and the corresponding boiling point-negative pressure relationship curve; The adjustment and analysis module is used to determine the current optimal extraction component and the current required distillation negative pressure and distillation temperature and perform control and adjustment according to the non-destructive temperature corresponding to each main component required to be extracted from the current tea liquid and the corresponding boiling point-negative pressure relationship curve; A duration estimation module, used to estimate the estimated distillation duration for distillation using the currently required distillation temperature and distillation negative pressure; Monitoring module, used to monitor the real-time distillation temperature; The control module is used to adjust the power of the heating device and thus adjust the real-time distillation temperature according to the monitored real-time distillation temperature and the currently required distillation temperature.

Images