An intelligent digital gasless soda automatic dispensing system

Abstract

The present invention relates to the field of automation technology, and particularly to an intelligent digital non-gasified soda water automatic dispensing system, including: a raw water treatment module for real-time detection of the water quality of groundwater and finished water; a raw material ratio dispensing module for dispensing and transmitting the raw material ratio of soda water; a raw material traceability module for automatically calculating and matching the raw material parameters of soda water entered through the master control module. The present invention implements regulation of various parameters in the water treatment process based on an improved particle swarm algorithm to ensure the consistency of the finished water at different time periods and reduce the influence of the production area environment and seasonal changes on the finished water. A function is also established with the goal of reducing costs, which can maximize the reduction of enterprise consumption costs, and the dispensing ratio is optimized based on an improved ant colony algorithm to improve the taste of soda water, thereby improving the quality and sales volume of soda water.

Description

Technical Field

[0001] The present invention relates to the field of automation technology, and in particular to an intelligent digital non-carbonated soda automatic dispensing system. Background Art

[0002] The production of non-carbonated soda is made up of a variety of raw materials, which endow non-carbonated soda with unique flavors and tastes. At present, the dispensing systems for non-carbonated soda production generally use fixed pipelines to pump various raw materials to be prepared from raw material tanks to a modulation tank through self-flow or pumps according to the requirements of the process formula after weighing by an electronic scale. How to carry out the dispensing of the finished product to make the taste better to improve the quality and sales volume of soda has become the main goal of the current soda automatic dispensing production line. Summary of the Invention

[0003] The purpose of the present invention is to propose an intelligent digital non-carbonated soda automatic dispensing system to solve the defects mentioned in the above background art.

[0004] The technical solution adopted by the present invention is as follows:

[0005] Provide an intelligent digital non-carbonated soda automatic dispensing system, including:

[0006] Raw water treatment module: used for real-time detection of the water quality of groundwater and finished water;

[0007] Raw material ratio dispensing module: used for dispensing and transmitting the raw material ratio of soda water;

[0008] Raw material traceability module: used for automatically calculating the ratio of the input raw material parameters.

[0009] As a preferred technical solution of the present invention: it further includes a total control module, and the total control module is used for controlling and intervening in the raw material ratio data of soda water.

[0010] As a preferred technical solution of the present invention: the raw water treatment module adjusts the parameters in the raw water treatment process based on an improved particle swarm optimization algorithm according to the real-time detection results.

[0011] As a preferred technical solution of the present invention: the specific improved particle swarm optimization algorithm is as follows:

[0012] Taking the reciprocal of the raw water detection error obtained from the output of the parameters as the fitness function, initializing the particle population, and the particles are iteratively updated through the following algorithm to find the optimal solution:

[0013]

[0014]

[0015] Among them, represents the velocity of the i-th particle at the (t + 1)-th iteration, represents the velocity of the i-th particle at the t-th iteration, represents the position of the i-th particle at the (t + 1)-th iteration, represents the position of the i-th particle at the t-th iteration, ω is the inertia weight of the particle, c1 and c2 are learning factors, and r1 and r2 are both random numbers in the range of [0, 1].

[0016] represents the historical optimal individual position at the t-th iteration; represents the global optimal position at the t-th iteration;

[0017]

[0018] Among them, represents the historical optimal individual position at the (t + 1)-th iteration, represents the fitness value of the i-th particle at the (t + 1)-th iteration, represents the historical optimal individual fitness value at the t-th iteration,

[0019] ω is adaptively updated based on the following formula:

[0020]

[0021] Among them, ω max is the maximum value of the inertia weight, ω min is the minimum value of the inertia weight, is the fitness value of the i-th particle at the t-th iteration, f min (t) is the minimum fitness value at the t-th iteration, is the average fitness value at the t-th iteration;

[0022] The particle accepts the new solution based on the following probability:

[0023]

[0024] Among them, σ t is the error of the raw water detection data corresponding to the parameter output after the t-th iteration,

[0025] σ t+1 is the error of the raw water detection data corresponding to the parameter output after the (t + 1)-th iteration, μ is the attenuation coefficient, and K is the water treatment process parameter.

[0026] As a preferred technical solution of the present invention: The raw material ratio adjustment module monitors the ratio data of the raw materials of the soda water and transmits it to the total control module.

[0027] As a preferred technical solution of the present invention: the ratio data includes the raw material storage data of the soda water and the raw material ratio condition data.

[0028] As a preferred technical solution of the present invention: the raw material traceability module constructs the objective function of the raw material ratio and performs dynamic allocation of the raw materials of the soda water.

[0029] As a preferred technical solution of the present invention: the construction of the function of the raw material ratio is specifically as follows:

[0030] There are a total of L steps for adding the raw materials of the soda water. The number of steps corresponds to the types of raw materials and the order of raw material addition. The objective function Z for adding the raw material ratio is established:

[0031]

[0032] where a l is the type of raw material selected in the l-th step, that is, the amount of raw material, and b l is the raw material cost in the l-th step;

[0033]

[0034] where R l is the remaining raw material after executing the l-th step, and Q is the total amount of raw materials;

[0035] The following constraint conditions are satisfied:

[0036]

[0037]

[0038] where R L is the remaining raw material after executing the L-th step, and n l is the proportionality coefficient of the raw material selected in the l-th step.

[0039] As a preferred technical solution of the present invention: the raw material traceability module performs optimization of the raw material ratio and automatic proportioning based on the improved ant colony algorithm.

[0040] As a preferred technical solution of the present invention: the improved ant colony algorithm is specifically as follows:

[0041] Initialize the ant colony parameters, raw material parameter information, and maximum number of iterations, and select the reciprocal of the raw material cost at each step as the heuristic information:

[0042]

[0043] The ants transfer between different locations by walking. The transfer probability of ant j from position u to position v at time k is:

[0044]

[0045] where l uv (k) is the pheromone trail intensity of ant j at time k, and δ uv (k) is the heuristic degree of ant j transferring from position u to position v at time k. μ is the position that ant j is allowed to reach, and τ j is the set of positions that ant j can choose in the next step. r is a random number between (0, 1), and α and β are adjustment coefficients;

[0046] After one cycle is completed, the amount of information l uv (k + 1) of the ant colony on the path (u, V) at the next moment is as follows:

[0047] l uv (k + 1) = (1 - ε)l uv (k) + Δl uv (k)

[0048]

[0049]

[0050] where l uv (k) is the amount of information of the ant at the current moment, and Δl ujv (k) is the optimal pheromone amount left by ant j on the path (u, v) during this cycle. ε is the pheromone evaporation coefficient;

[0051] is the pheromone enhancement coefficient.

[0052] Compared with the prior art, the intelligent digital non - gas soda water automatic dispensing system provided by the present invention has the following beneficial effects:

[0053] Based on the improved particle swarm optimization algorithm, the present invention implements the regulation and control of various parameters in the water treatment process to ensure the consistency of the finished water at different time periods and reduce the influence of the production area environment and seasonal changes on the finished water. A function is also established with the goal of reducing costs, which can maximize the reduction of enterprise consumption costs. And based on the improved ant colony algorithm, the dispensing ratio is optimized to improve the taste of soda water, thereby improving the quality and sales volume of soda water. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is the automatic dispensing flow block diagram of the preferred embodiment of the present invention.

[0055] The meanings of the various marks in the figure are as follows: 100, raw water treatment module; 200, raw material ratio dispensing module; 300, raw material traceability module; 400, total control module. DETAILED DESCRIPTION OF THE INVENTION

[0056] It should be noted that, without conflict, the embodiments in this example and the features in the embodiments can be combined with each other. Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work belong to the scope of protection of the present invention.

[0057] Referring to Figure 1 , a preferred embodiment of the present invention provides an intelligent digital non-gas soda automatic dispensing system, including:

[0058] Raw water treatment module 100: used to detect the water quality of groundwater and finished water in real time;

[0059] Raw material ratio dispensing module 200: used to dispense and transmit the raw material ratio of soda water;

[0060] Raw material traceability module 300: used to automatically calculate the ratio of the input raw material parameters of soda water.

[0061] It further includes a total control module 400, and the total control module 400 is used to control and intervene in the raw material ratio data of soda water.

[0062] The raw water treatment module 100 adjusts the parameters in the raw water treatment process based on the improved particle swarm optimization algorithm according to the real-time detection results.

[0063] The specific improved particle swarm optimization algorithm is as follows:

[0064] Taking the reciprocal of the raw water detection error obtained from the output of the parameters as the fitness function, initializing the particle population, and the particles are iteratively updated through the following algorithm to find the optimal solution:

[0065]

[0066]

[0067] Among them, represents the velocity of the i-th particle at the (t + 1)-th iteration, represents the velocity of the i-th particle at the t-th iteration, represents the position of the i-th particle at the (t + 1)-th iteration, represents the position of the i-th particle at the t-th iteration, ω is the inertia weight of the particle, c1 and c2 are learning factors, and r1 and r2 are both random numbers in the range of [0, 1],

[0068] represents the historical optimal individual position at the t-th iteration; represents the optimal position of the population at the t-th iteration;

[0069]

[0070] wherein, represents the historical optimal position of the individual at the (t + 1)-th iteration, represents the fitness value of the i-th particle at the (t + 1)-th iteration, represents the historical optimal individual fitness value at the t-th iteration,

[0071] ω is adaptively updated based on the following formula:

[0072]

[0073] wherein, ω max is the maximum value of the inertia weight, ω min is the minimum value of the inertia weight, is the fitness value of the i-th particle at the t-th iteration, f min (t) is the minimum fitness value at the t-th iteration, is the average fitness value at the t-th iteration;

[0074] The particle accepts the new solution based on the following probability:

[0075]

[0076] wherein, σ t is the error of the raw water detection data corresponding to the output of the parameter after the t-th iteration, σ t+1 is the error of the raw water detection data corresponding to the output of the parameter after the (t + 1)-th iteration, μ is the attenuation coefficient, and K is the water treatment process parameter.

[0077] The raw material ratio adjustment module 200 monitors the ratio data of the raw materials of the soda water and transmits it to the total control module 400.

[0078] The ratio data includes the raw material storage data and the raw material ratio condition data of the soda water.

[0079] The raw material traceability module 300 constructs the objective function of the raw material ratio and performs dynamic adjustment of the raw materials of the soda water.

[0080] The construction of the function of the raw material ratio is specifically as follows:

[0081] There are a total of L steps for adding the raw materials of the soda water. The number of steps corresponds to the number of raw material types and the order of raw material addition. The objective function Z for adding the raw material ratio is established:

[0082]

[0083] wherein, al The type and quantity of raw materials selected for the l-th step, b l is the raw material cost for the l-th step;

[0084]

[0085] Among them, R l is the remaining raw materials after the l-th step is executed, and Q is the total amount of raw materials;

[0086] It satisfies the following constraint conditions:

[0087]

[0088]

[0089] Among them, R L is the remaining raw materials after the L-th step is executed, n l is the proportionality coefficient of the raw materials selected for the l-th step.

[0090] The raw material traceability module 300 performs optimization of the proportion of raw materials and automatic matching based on the improved ant colony algorithm.

[0091] The specific improved ant colony algorithm is as follows:

[0092] Initialize the ant colony parameters, raw material parameter information, and the maximum number of iterations, and select the reciprocal of the raw material cost for each step as the heuristic information:

[0093]

[0094] The ants transfer between different locations. The transfer probability of ant j from location u to location v at time k is:

[0095]

[0096] Among them, l uv (k) is the pheromone trail intensity of ant j at time k, δ uv (k) is the heuristic degree of ant j transferring from location u to location v at time k, μ is the locations that ant j is allowed to reach, τ j is the set of locations that ant j can choose for the next step, r is a random number between (0, 1), and α and β are adjustment coefficients;

[0097] After one cycle is completed, the amount of information l of the ant colony at the next moment on the path (u, v) uv (k + 1) is as follows:

[0098] l uv (k + 1) = (1 - ε)l uv (k) + Δl uv (k)

[0099]

[0100]

[0101] where l uv (k) is the amount of information of the ant at the current moment, and Δl ujv (k) is the optimal pheromone amount left by ant j on the path (u, v) during this iteration process, and ε is the pheromone evaporation coefficient;

[0102] is the pheromone enhancement coefficient.

[0103] In this embodiment, the raw water treatment module 100 realizes the real-time detection of the quality of groundwater and the real-time detection of the finished water. According to the comparison results before and after, various parameters in the water treatment process are regulated based on the improved particle swarm algorithm to ensure the consistency of the finished water in different time periods and reduce the influence of the production environment and seasonal changes on the finished water:

[0104] Taking the reciprocal of the raw water detection error obtained from the output of the parameters as the fitness function, the particle population is initialized. Taking the 8th iteration as an example, the particles are iteratively updated through the following algorithm to find the optimal solution:

[0105]

[0106]

[0107] where represents the velocity of the i-th particle at the 9th iteration, represents the velocity of the i-th particle at the 8th iteration, represents the position of the i-th particle at the 9th iteration, represents the position of the i-th particle at the 8th iteration, ω is the inertial weight of the particle, c1 and c2 are learning factors, and r1 and r2 are both random numbers in the range of [0, 1], represents the historical optimal individual position at the 8th iteration; represents the group optimal position at the 8th iteration;

[0108]

[0109] where represents the historical optimal individual position at the 9th iteration, represents the fitness value of the i-th particle at the 9th iteration, represents the historical optimal individual fitness value at the 8th iteration,

[0110] The particle accepts the new solution based on the following probability:

[0111]

[0112] Among them, σ8 is the error of the raw water detection data corresponding to the parameters after the 8th iteration, σ9 is the error of the raw water detection data corresponding to the parameters after the 9th iteration, μ is the attenuation coefficient, and K is the water treatment process parameter.

[0113] If the newly generated state error decreases, this state is accepted as the local optimal solution. If the error increases, this state is randomly accepted or discarded with a certain probability. In the initial stage of iteration, the water treatment process parameter is relatively high, and poor inferior solutions can be accepted. However, as the number of iterations increases, the error is gradually reduced, and only better inferior solutions can be accepted. After the iteration has been carried out for a sufficient number of times, the system tends to be stable and reaches an equilibrium state.

[0114] The raw material ratio adjustment module 200 monitors data such as the storage method, storage temperature, mixing temperature, and pressure of the raw materials in combination with the characteristics of the carbonated water, and conducts network monitoring, and transmits the data to the total control module 400 in a timely manner. The operator can perform leather-making control intervention through the total control module 400, or can also perform ratio adjustment according to the product requirements by himself.

[0115] The raw material traceability module 300 inputs the parameters of each batch of raw materials through the total control module 400, and automatically calculates the ratio according to the established objective function of the raw material ratio in combination with the raw material parameters:

[0116] There are a total of L steps for adding the raw materials of the carbonated water. The number of steps corresponds to the number of raw material types and the order of raw material addition, and the objective function Z for adding the raw material ratio is established:

[0117]

[0118] Among them, a l is the raw material type and the amount of raw material selected in the l-th step, and b l is the raw material cost in the l-th step;

[0119]

[0120] Among them, R l is the remaining raw material after executing the l-th step, and Q is the total amount of raw materials;

[0121] The following constraint conditions are satisfied:

[0122]

[0123]

[0124] Among them, R L is the remaining raw material after executing the L-th step, and n l is the proportional coefficient of the raw material selected in the l-th step.

[0125] Optimize the proportion of raw materials and perform automatic proportioning based on the improved ant colony algorithm:

[0126] Initialize the ant colony parameters, raw material parameter information, and the maximum number of iterations, and select the reciprocal of the raw material cost at each step as the heuristic information:

[0127]

[0128] The ants transfer between different locations. At time 7, the transfer probability of ant j from location u to location v is:

[0129]

[0130] Among them, l uv (7) is the pheromone trail intensity of ant j at time 7, and δ uv (7) is the degree of heuristic for ant j to transfer from location u to location v at time 7. μ is the set of locations that ant j is allowed to reach, and τ j is the set of locations that ant j can choose in the next step. r is a random number between (0, 1), and α and β are adjustment coefficients;

[0131] After one cycle is completed, the amount of information l of the ant colony on the path (u, v) at the next moment uv is as follows:

[0132] l uv (8) = (1 - ε)l uv (7) + Δl uv (7)

[0133]

[0134]

[0135] Among them, l uv (7) is the amount of information of the ant at the current moment, and Δl ujv (7) is the optimal pheromone amount left by ant j on the path (u, v) during this cycle. ε is the pheromone evaporation coefficient;

[0136] is the pheromone enhancement coefficient.

[0137] The objective function is established with the goal of reducing costs, which can maximize the reduction of enterprise consumption costs. The improved ant colony algorithm improves the ant colony algorithm by changing the influence ratio of two factors on the ant path selection. Among them, the optimization of pheromone can be achieved through the state transition probability and rules, and further enhance the ability of the ant colony algorithm to search for the global optimal solution, and obtain the best raw material proportioning scheme for soda water.

[0138] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be embraced within the present invention. Any reference signs in the claims should not be construed as limiting the claims involved.

[0139] In addition, it should be understood that although this specification is described in terms of embodiments, not every embodiment only contains an independent technical solution. This narrative manner of the specification is only for clarity. Those skilled in the art should regard the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

Claims

1. An intelligent digital airless soda automatic dispensing system, characterized in that, include: Raw water treatment module (100): used for real-time detection of the water quality of groundwater and finished water; A raw material ratio mixing module (200): used for mixing and transmitting the raw material ratio of soda water; Raw material traceability module (300): used to automatically calculate the proportion of the input raw material parameters of soda water; The raw water treatment module (100) performs parameter control on the parameters in the raw water treatment process based on the improved particle swarm algorithm according to the real-time detection results; The improved particle swarm algorithm is specifically as follows: The inverse of the raw water detection error obtained by the output of the parameters is used as the fitness function to initialize the particle population. The particles are iteratively updated through the following algorithm to find the optimal solution: Among them, represents the velocity of the th particle at the th iteration, represents the velocity of the th particle at the th iteration, represents the position of the th particle at the th iteration, represents the position of the th particle at the th iteration, is the inertial weight of the particle, is the learning factor, Both are a random number between, represents the historical best individual position at the th iteration; represents the global best position of the population at the th iteration; Among them, represents the historical optimal position of the individual at the th iteration, represents the fitness value of the th particle at the th iteration, represents the historical optimal individual fitness value at the th iteration. Adaptive update is performed based on the following formula: Among them, is the maximum value of the inertia weight, is the minimum value of the inertia weight, is the -th particle's fitness value at the -th iteration, is the minimum fitness value at the -th iteration, is the average fitness value at the -th iteration; The particle accepts the new solution based on the following probability: Among them, is the error of the raw water detection data corresponding to the parameters after the th iteration, is the error of the raw water detection data corresponding to the parameters after the th iteration, is the attenuation coefficient, is the water treatment process parameter; The raw material tracing module (300) performs optimization and automatic proportioning of raw material ratios based on an improved ant colony algorithm; The improved ant colony algorithm is specifically as follows: Initialize the ant colony parameters, raw material parameter information, and the maximum number of iterations, and select the inverse of the raw material cost at each step as the heuristic information: Ants transfer between different locations by walking, At all times, the ant The probability of transferring from position to position is as follows: Among them, is the pheromone trail intensity of the ant at time , is the inspiration degree of the ant at time transferring from position to position , is the position that the ant is allowed to reach, is the set of positions that the ant can choose at the next step, is a random number between and , and are adjustment coefficients; After one cycle is completed, at the next moment, the ant colony is on the path of the amount of information as follows: wherein, is the amount of information of the ant at the current moment, is the ant leaving the optimal pheromone amount on the path during this loop, is the pheromone evaporation coefficient; is the pheromone enhancement coefficient.

2. The intelligent digital airless soda automatic dispensing system according to claim 1, wherein: It also includes a general control module (400), wherein the general control module (400) is used to control and intervene in raw material ratio data of soda water.

3. The intelligent digital airless soda automatic dispensing system according to claim 2, wherein: The raw material ratio adjustment module (200) monitors the ratio data of the raw materials of soda water and transmits the data to the main control module (400).

4. The intelligent digital airless soda automatic dispensing system according to claim 3, characterized in that: The proportioning data includes raw material storage data and raw material proportioning condition data of soda water.

5. The intelligent digital non-gas soda automatic dispensing system according to claim 4, wherein: The raw material traceability module (300) constructs an objective function for raw material ratio and performs dynamic allocation of raw materials for soda water.

6. The intelligent digital non-gas soda automatic dispensing system according to claim 5, characterized in that: The function of the raw material ratio is constructed as follows: The raw material addition of soda water totals steps. The number of steps corresponds to the types of raw materials and the order of raw material addition, and an objective function for raw material ratio addition is established : Among them, is the type and amount of raw materials selected in the step, is the raw material cost in the step; wherein, is the remaining raw material after performing the step, is the total amount of raw materials; The following constraints are met: Among them, is the remaining raw material after performing the step, is the proportionality coefficient of the raw material selected in the step.

Images