Method for synchronously extruding marshmallow through multiple channels

Abstract

The invention discloses a method for synchronously extruding marshmallow through multiple channels, and relates to the field of food processing, and the method comprises the following steps: determining a target scheme, preparing syrup raw materials according to the target scheme, setting an initial temperature, extracting syrup historical data, determining initial syrup data of each channel based on the target scheme, the method comprises the following steps: establishing an intelligent color matching extrusion control model based on historical syrup data, comparing a finished product of initial syrup data input and output of each channel with a target scheme, and dynamically adjusting the initial syrup data of each channel according to the target scheme by the intelligent color matching extrusion control model when a cotton candy comparison threshold value is exceeded, final syrup data is formed for each channel. By establishing the intelligent color matching extrusion control model, the quality of a finished product can be pre-judged through the model before actual extrusion, deviation can be found and corrected in time, unnecessary waste and rework in the production process are avoided, and the problems of asynchronous discharging and unstable weight are solved.

Description

Technical Field

[0001] The invention relates to the field of food processing, in particular to a method for synchronously extruding marshmallows through multiple channels. Background Art

[0002] With the continuous development of food processing technology, marshmallow production equipment has gradually evolved from traditional manual operation to automated mechanical production. Traditional marshmallow production relies on single-channel extrusion equipment. Although this equipment can meet basic production needs, it has limited ability to produce multi-color and multi-shaped marshmallows, especially in terms of product consistency and complexity. Existing technical means seem to be unable to cope with it. The shortcoming of existing multi-channel extrusion technology is that traditional extrusion equipment lacks effective control of multi-channel synchronization, which makes it difficult to keep the syrup flow rate, pressure and temperature consistent between different channels, ultimately leading to problems such as asynchronous discharge and unstable weight. In addition, the operation of existing extrusion equipment is complicated and difficult to adapt to rapidly changing production needs, especially in achieving fine color control and shape consistency. There are obvious deficiencies. Summary of the invention

[0003] In view of the above existing problems, the present invention is proposed.

[0004] Therefore, the present invention provides a method for multi-channel synchronous extrusion of marshmallows to solve the problem of lack of intelligent control and real-time monitoring of syrup parameters, and inability to make effective adjustments according to deviations occurring in the real-time production process when facing complex color and shape requirements.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In a first aspect, the present invention provides a method for synchronously extruding marshmallows through multiple channels, comprising:

[0007] Determine the target solution, prepare the syrup raw materials according to the target solution, and set the initial temperature;

[0008] Extract syrup history data and determine initial syrup data for each channel based on the target solution;

[0009] An intelligent color matching extrusion control model is established based on the historical syrup data, the initial syrup data of each channel is input, the finished product of the initial syrup data is output, and compared with the target solution;

[0010] When the marshmallow contrast threshold is exceeded, the intelligent color matching extrusion control model dynamically adjusts the initial syrup data of each channel according to the target scheme to form the final syrup data of each channel;

[0011] Based on the final syrup temperature data of each channel, the temperature of each channel is adjusted in real time through the zone temperature control technology;

[0012] Detect the final syrup data in real time and automatically adjust the extrusion pressure and speed of each channel according to the target plan;

[0013] During the extrusion process, the intelligent color matching extrusion control model continuously monitors the color and shape of the extrudate and compares it with the target solution in real time to finally extrude the marshmallow.

[0014] As a preferred embodiment of the method for synchronously extruding marshmallows through multiple channels of the present invention, the method comprises the following steps: determining a target solution, preparing syrup raw materials according to the target solution, and setting an initial temperature.

[0015] Determine the shape and color of the marshmallows as requested;

[0016] Prepare syrup raw materials and control the proportion of ingredients in syrup raw materials;

[0017] Prepare food grade color according to the color of the target solution;

[0018] Start the temperature control function and set the initial temperature for each color of syrup.

[0019] As a preferred solution of the method for synchronously extruding marshmallows through multiple channels of the present invention, the method comprises: extracting historical syrup data, and determining initial syrup data of each channel based on the target solution, which specifically comprises the following steps:

[0020] Extract the syrup temperature, viscosity, flow rate, color concentration and extrusion pressure of each extrusion channel from the historical database;

[0021] Based on the target color requirements, the syrup parameters of the batch data closest to the target color in the historical data are extracted as the initial reference frame. At the same time, the color concentration is obtained by calculating the amount of pigment added and combining the concentration setting of the same color in the historical data.

[0022] Use the batch data with the viscosity closest to the target solution in the historical data to uniformly set the syrup viscosity of all channels;

[0023] The initial syrup flow rate is calculated based on the flow rate of the extrusion equipment and the cross-sectional area of ​​the extrusion channel. At the same time, the initial syrup flow rate is further fine-tuned based on the syrup component with the highest similarity to the current target solution in the historical data to complete the setting of the syrup flow rate;

[0024] The syrup data obtained from the historical data are integrated into the initial syrup data.

[0025] As a preferred solution of the method for synchronously extruding marshmallows through multiple channels of the present invention, an intelligent color matching extrusion control model is established based on the historical syrup data, the initial syrup data of each channel is input, and the finished product of the initial syrup data is output and compared with the target solution, which specifically includes the following steps:

[0026] extracting historical data and historical finished product quality data from a database, wherein the historical finished product quality data includes color consistency and shape stability;

[0027] Normalize historical data and historical finished product quality data;

[0028] Use visualization tools to observe the relationship between different syrup parameters and the quality of historical finished products, and preliminarily determine the relationship between syrup parameters and the quality of historical finished products;

[0029] A multiple linear regression model was introduced to determine the regression coefficients of syrup parameters based on historical data, and the multiple linear regression model was fitted using the least squares method;

[0030] Input the initial syrup data into the multiple linear regression model and output the predicted value of the finished product quality for each channel;

[0031] Based on historical data and target solutions, the allowable deviation ranges of the finished product color and finished product shape are set as marshmallow comparison thresholds;

[0032] The finished product quality prediction value of each channel is compared with the marshmallow contrast threshold, the color difference and geometric error between the finished product quality prediction value and the target solution are calculated, and the gap between the finished product and the target is evaluated.

[0033] As a preferred solution of the method for synchronously extruding marshmallows through multiple channels of the present invention, when the marshmallow contrast threshold is exceeded, the intelligent color matching extrusion control model dynamically adjusts the initial syrup data of each channel according to the target solution to form the final syrup data of each channel, which specifically includes the following steps:

[0034] When the color difference and geometric shape of the finished product of the initial syrup data exceed the marshmallow contrast threshold, it is judged as unqualified;

[0035] Based on the comparison results between the finished product of the initial syrup data and the target solution, the deviation between the finished product of the initial syrup data and the target solution is calculated according to the multivariate linear regression model, and the adjustment amount of the syrup parameters in each channel is determined;

[0036] The syrup parameters that have the greatest impact on exceeding the threshold are adjusted first according to the adjustment amount of the syrup parameters in each channel, and the remaining syrup parameters are adjusted gradually;

[0037] After the syrup parameters are adjusted, the finished product quality is retested until the color difference and geometric deviation of the finished product return to the marshmallow comparison threshold;

[0038] The syrup parameters that meet the marshmallow contrast threshold are retained as the final syrup data for each channel.

[0039] As a preferred solution of the method for synchronously extruding marshmallows through multiple channels of the present invention, the temperature of each channel is adjusted in real time by using a zoned temperature control technology based on the final syrup temperature data of each channel, which specifically includes the following steps:

[0040] determining the actual temperature of each channel and calculating the deviation of the actual temperature from the syrup temperature data in the final syrup data;

[0041] Based on the temperature deviation, PID is used to calculate the heating power, and the expression is:

[0042]

[0043] Among them, u(t) represents the heating power, K represents the response intensity of the current deviation, e(t) represents the temperature deviation, L represents the influence of the cumulative control deviation on the current control output, t represents the current time, dτ represents the accumulation of temperature deviation in each small time period, S represents the influence of the control temperature change rate on the current heating power, de(t) represents the rate of change of the error over time, and dt represents the small increment of time;

[0044] The channels are adjusted according to the calculated heating power and the syrup temperature is continuously monitored.

[0045] As a preferred solution of the method for synchronously extruding marshmallows through multiple channels of the present invention, the method comprises: detecting the final syrup data in real time, and automatically adjusting the extrusion pressure and speed of each channel according to the target solution, specifically comprising the following steps:

[0046] Based on historical data, neural networks are trained through supervised learning;

[0047] The trained neural network receives the final syrup data in real time, compares it with the target solution based on the current extrusion pressure and speed, and calculates the error;

[0048] The neural network infers based on the error and outputs control signals to adjust the extrusion pressure and speed.

[0049] As a preferred solution of the method for multi-channel synchronous extrusion of marshmallows of the present invention, wherein: during the extrusion process, the intelligent color matching extrusion control model continuously monitors the color and shape of the extrudate, and compares it with the target solution in real time, and finally extrude the marshmallows, specifically comprising the following steps:

[0050] During the extrusion process, the intelligent color matching extrusion control model calculates the Lab color space value of the extrudate in real time and compares it with the target color. At the same time, the shape contour of the extrudate is analyzed through the Fourier descriptor.

[0051] When it is detected that the color and shape of the extrudate deviate from the target solution, the intelligent color matching extrusion control model automatically adjusts the extrusion parameters until marshmallows that meet the target solution are extruded.

[0052] In a second aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the method for multi-channel synchronous extrusion of marshmallows as described in the first aspect of the present invention is implemented.

[0053] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the method for multi-channel synchronous extrusion of marshmallows as described in the first aspect of the present invention is implemented.

[0054] The beneficial effects of the present invention are as follows: by establishing an intelligent color matching extrusion control model, the quality of the finished product can be predicted by the model before the actual extrusion, deviations can be found and corrected in time, unnecessary waste and rework can be avoided in the production process, and the problems of asynchronous discharge and unstable weight can be solved, while significantly improving production efficiency and finished product qualification rate. In addition, through PID control, the temperature can be accurately adjusted to ensure that the syrups in different channels are extruded within a suitable temperature range, reducing manual operation, simplifying the difficulty of operating the extrusion equipment, and avoiding the influence of inconsistent temperature on the quality of the finished product, further improving the consistency and accuracy of the finished product. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0056] Figure 1 This is a flow chart of the method for synchronously extruding marshmallows through multiple channels in Example 1;

[0057] Figure 2 This is a schematic diagram of the intelligent color matching extrusion control model in Example 1 determining the finished product. DETAILED DESCRIPTION

[0058] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0059] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0060] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0061] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a method for synchronously extruding marshmallows through multiple channels, comprising the following steps:

[0062] S1. The producer first determines the appearance characteristics of the target finished product, including shape and color.

[0063] According to market demand or specific order requirements, choose the shape of the marshmallow (such as round, spiral, flower-shaped, etc.) and the color (such as single color, two-color or multi-color gradient).

[0064] S1.1. Prepare syrup raw materials according to the determined marshmallow shape and color requirements.

[0065] The basic ingredients of syrup include sugar, corn syrup and water.

[0066] In order to ensure that the fluidity and viscosity of the syrup are suitable for extrusion, the proportion of the syrup ingredients needs to be strictly controlled. The mass ratio of sugar, water and corn syrup in the syrup is set as: 60% white sugar, 20% water, and 20% corn syrup. This ratio ensures that the viscosity of the syrup after heating and cooling is moderate and can meet the requirements of multi-channel synchronous extrusion.

[0067] S1.2. Prepare food grade pigments according to the color requirements of the target design.

[0068] For example, to achieve a gradient effect from light pink to dark pink, we used red and white food coloring.

[0069] S1.3. To ensure that each color of syrup has the same physical properties during the extrusion process, start the temperature control function and set the initial temperature for each color of syrup. Syrups of different colors may have different thermal responses when heated due to factors such as pigment concentration and ingredient ratio, so it is necessary to set temperature control parameters for the specific situation of each syrup.

[0070] S2. Syrup parameters in each channel (including temperature, viscosity, flow rate, color concentration and extrusion pressure) play a vital role in the quality and consistency of the final product.

[0071] S2.1. According to the target color requirement of the current production batch, select the production batch data closest to the target color from the historical database. By analyzing the color parameters and pigment addition amount of the syrup in these historical batches, a reasonable initial color framework is set for the current production.

[0072] S2.2, Viscosity is an important parameter that determines the fluidity of syrup during extrusion. In order to ensure synchronization and consistency during multi-channel extrusion, the batch data closest to the target solution viscosity is extracted from the historical data as the unified viscosity of all channels.

[0073] S2.3. Estimate the flow rate of the extrusion equipment according to the specifications of the extrusion equipment and the target output, and calculate the initial syrup flow rate according to the flow rate of the extrusion equipment and the cross-sectional area of ​​the extrusion equipment channel. At the same time, the flow rate can be further fine-tuned based on the production records of similar output and syrup composition in the historical data. Through historical data analysis, the flow rate range for successful production under similar conditions can be found, so as to adjust the initial flow rate of the current production.

[0074] Further explanation: By accurately calculating the flow rate of each channel, the syrup can maintain consistency and stability during the extrusion process. Fine-tuning the flow rate further improves the accuracy of production and avoids the problem of unstable fluidity caused by ingredient differences, thereby ensuring the smooth progress of multi-channel synchronous extrusion.

[0075] S2.4. Integrate the syrup data of each channel obtained based on historical data into a complete initial syrup data set. This data set will be used as the initial parameter input of each channel in the production process to guide subsequent extrusion operations.

[0076] For example, to produce a tricolor cotton candy in red, yellow, and blue, each color of syrup is injected through a separate extrusion channel.

[0077] Filter the production records closest to the target color from the historical database.

[0078] Red: In similar production batches, the pigment concentration is 0.5 g / L.

[0079] Yellow: Historical records show a pigment concentration of 0.45 g / L.

[0080] Blue: Historical data indicates a pigment concentration of 0.6 g / L.

[0081] The syrup temperature is 80°.

[0082] The production records that are closest to the current syrup composition and production conditions are extracted from the historical database. In similar tri-color marshmallow production, historical records show that the syrup viscosity ranges from 1500–1600 mPa·s.

[0083] The viscosity of the syrup currently produced is uniformly set to 1550 mPa·s.

[0084] The specification of the extrusion equipment is total flow rate Q = 20L / h. The cross-sectional area of ​​each extrusion channel A = 10cm 2 .

[0085] The initial flow rate of the syrup was calculated to be 5.56 m / s. However, through historical data analysis, it was found that in similar production records, the flow rate was usually between 5.4 and 5.6 m / s. In order to ensure the stable flow of the syrup, the flow rate was fine-tuned to 5.55 m / s.

[0086] Final integration, red channel: temperature is 80°, viscosity: 1550 mPa·s, flow rate: 5.55 m / s, color concentration: 0.5 g / L, extrusion pressure: 20 MPa.

[0087] Yellow channel: temperature is 80°, viscosity: 1550 mPa·s, flow rate: 5.55 m / s, color concentration: 0.45 g / L, extrusion pressure: 20 MPa.

[0088] Blue channel: temperature is 80°, viscosity: 1550mPa·s, flow rate: 5.55m / s,

[0089] Color concentration: 0.6g / L, extrusion pressure: 20Mpa.

[0090] S3. Syrup historical data includes temperature, viscosity, flow rate, color concentration, extrusion pressure, etc.

[0091] Historical finished product quality data for syrups includes color consistency and shape stability.

[0092] S3.1. Normalize the syrup parameters and finished product quality data to ensure that each data dimension is within the same numerical range.

[0093] S3.2. Use scatter plots to visualize the syrup parameters and finished product quality data to obtain a preliminary linear relationship between the syrup parameters and the finished product quality, and to identify which parameters have a greater impact on the finished product quality.

[0094] It can be further explained that visualization can directly show the impact of syrup parameters on the quality of the finished product, and a regression model can be established more accurately in the subsequent steps.

[0095] S3.3. Introduce a multiple linear regression model to express the relationship between the finished product quality (dependent variable) and the syrup parameters (independent variables) using a linear equation.

[0096] S3.3.1. In order to determine the regression coefficient, it is necessary to use historical data to fit the multivariate linear regression model. Assume that there are m historical production batches of data, and each batch of data includes n syrup parameters (independent variables) and the corresponding finished product quality (dependent variable). Use historical data to fit the model;

[0097] Organize historical data into matrix X and matrix Y;

[0098] Independent variable matrix X (size is m×n): each row represents a production batch, each column represents a syrup parameter, and its expression is:

[0099]

[0100] Where X represents the data set of production batches and syrup parameters, m represents the number of production batches (the number of rows in the matrix), n represents the number of syrup parameters (the number of columns in the matrix), and X ij represents the jth syrup parameter of the i-th batch. 11 Indicates the first syrup parameter of the first batch, X 12 Indicates the parameters of the second syrup of the first batch, X 1n represents the nth syrup parameter of the first batch, X 21 Indicates the first syrup parameter of the second batch, X 22 Indicates the second syrup parameter of the second batch, X 2n Indicates the nth syrup parameter of the second batch, X m1 represents the first syrup parameter of the mth batch, X m2 represents the second syrup parameter of the mth batch, X mn Indicates the nth syrup parameter of the mth batch.

[0101] Each element of the dependent variable matrix Y (size is m×2) represents the quality of the finished product of the corresponding batch (color consistency Y1, shape stability Y2), and its expression is:

[0102]

[0103] Among them, Y represents the quality data of all batches of finished products, m represents the number of production batches (the number of rows in the matrix), and Y 1,m Indicates the color consistency of the mth batch, Y 2,m represents the shape stability of the mth batch, Y 1,1 and Y 2,1 Indicates the color consistency and shape stability of the first batch, Y1,2 and Y 2,2 Indicates the color consistency and shape stability of the second batch, Y 1,3 and Y 2,3 Indicates the color consistency and shape stability of the 3rd batch.

[0104] The least squares method is used in the fitting process to determine the regression coefficient, which is expressed as:

[0105]

[0106] in, It represents the regression coefficient vector [β0, β1…β n ] T , X T represents the transpose of the independent variable matrix, X T X represents the product of the transpose of the independent variable matrix X and X itself, which contains the inner product information between the variables. It is an n×n square matrix. T Y represents the product of the independent variable matrix X and the dependent variable matrix Y, and its size is n×2.

[0107] S3.4. Input the initial syrup data into the model and output the predicted value of the finished product quality for each channel. The expression is:

[0108]

[0109] in, represents the predicted value of color consistency, represents the predicted value of shape stability, W represents syrup temperature, V represents syrup viscosity, F represents syrup flow rate, C represents color concentration, P represents extrusion pressure, Represents a constant term, which refers to the basic value of color consistency when all syrup parameters are 0. It represents the regression coefficient of syrup temperature W on color consistency, which refers to the magnitude of color consistency change when the temperature increases by 1 unit. It represents the regression coefficient of syrup viscosity V on color consistency, which refers to the magnitude of color consistency change when the viscosity increases by 1 unit. It represents the regression coefficient of syrup flow rate F on color consistency, which refers to the magnitude of color consistency change when the flow rate increases by 1 unit. It represents the regression coefficient of color concentration C on color consistency, which refers to the magnitude of color consistency change when the color concentration increases by 1 unit. It represents the regression coefficient of extrusion pressure P on color consistency, which refers to the magnitude of color consistency change when the extrusion pressure increases by 1 unit. Represents a constant term, which refers to the basic value of shape stability when all syrup parameters are 0. It represents the regression coefficient of the syrup temperature W on the shape stability, which refers to the magnitude of the change in shape stability when the temperature increases by 1 unit. The regression coefficient of syrup viscosity V on shape stability refers to the magnitude of shape stability change when the syrup viscosity increases by 1 unit. It represents the regression coefficient of the syrup flow rate F on the shape stability, which refers to the magnitude of the change in shape stability when the syrup flow rate increases by 1 unit. It represents the regression coefficient of color concentration C on shape stability, which refers to the magnitude of shape stability change when the color concentration increases by 1 unit. It represents the regression coefficient of extrusion pressure P on shape stability, which refers to the magnitude of shape stability change when the extrusion pressure increases by 1 unit.

[0110] S3.5. Extract the color and shape error range of qualified products from historical data, set the allowable deviation range of each quality indicator as the comparison threshold of marshmallows. After setting the allowable deviation range, it is clear when the production parameters need to be adjusted to ensure that the quality of the finished product is within a controllable range.

[0111] S3.5.1. The comparison method is to compare the finished product quality prediction value of each channel with the set marshmallow comparison threshold, and evaluate the gap between the finished product and the target by calculating the color difference and geometric error between the finished product quality prediction value and the target solution.

[0112] Specifically, the color difference means calculating the difference between the predicted color of each channel and the target color, and judging whether the difference is within the allowable range; the geometric error means calculating the geometric error and judging whether it meets the allowable shape error.

[0113] By comparison, it is clear whether the quality of the finished product under the current syrup parameters meets the target requirements. If it exceeds the allowable range, the parameters are adjusted in time to avoid quality problems.

[0114] S4. When the color difference and geometric shape errors exceed the contrast threshold, it is unqualified and enters the adjustment stage.

[0115] S4.1. Calculate the deviation between the finished product quality and the target solution based on the actual measured color and geometric errors.

[0116] For example, if the measured color consistency is 0.92 and the color consistency of the target solution is 0.95, the deviation in color consistency is 0.03.

[0117] S4.2. In order to reduce the color difference of color consistency and the geometric error of geometric shape, the adjustment amount of syrup parameters is back-calculated using the regression model.

[0118] According to the regression coefficient of the regression model, the influence of each syrup parameter on the quality of the finished product was determined.

[0119] For example, if the regression coefficient for temperature is The largest value means that temperature has the strongest impact on color consistency, so temperature adjustment is given priority.

[0120] S4.3. After each adjustment, the color and geometric shape of the finished product are detected in real time, and the color difference and geometric error are recalculated to determine whether they still exceed the threshold.

[0121] If the initial adjustment of the parameters does not completely eliminate the deviation, gradually adjust other syrup parameters until the color and geometric shape errors of the finished product are within the allowable range.

[0122] For example, if the regression coefficient of temperature is the largest, adjust the temperature first, and then retest the color and geometry of the finished product. If the color difference or geometric error is improved after adjustment but still exceeds the allowable range, adjust the parameter with the regression coefficient second only to the temperature until it meets the allowable range.

[0123] When the test shows that the color difference and geometric error of the finished product are within the allowable range, the current syrup parameter settings are retained as the final syrup parameters of each channel.

[0124] It is further explained that through automatic adjustment, the need for human intervention is reduced, the automation level and accuracy of the production process are improved, and the risk of operational errors is reduced.

[0125] S5. Obtain the actual temperature of each extrusion channel, and calculate the deviation between the actual temperature and the syrup temperature data in the final syrup data. For example, the target temperature is 85° C., and the current actual temperature is 83° C.

[0126] S5.1. PID controller is a controller that adjusts the output through three parts (proportional, integral, and differential). Substituting the temperature difference into the PID calculation formula, the expression is:

[0127]

[0128] Among them, u(t) represents the heating power, K represents the response intensity of the current deviation of the control, is the proportional coefficient, e(t) represents the temperature deviation, L represents the influence of the cumulative control deviation on the current control output, is the integral coefficient. The larger the value, the greater the influence of the past error on the current heating power. t represents the current time, dτ represents the accumulation of temperature deviation in each small time period, S represents the influence of the control temperature change rate on the current heating power, is the differential coefficient. The larger the value, the more sensitive the response to the error change trend. The heating power will make rapid adjustments according to the error change speed. de(t) represents the error change rate over time, and dt represents a small increment of time.

[0129] Assume that the current temperature deviation e(t) = 2°C, the proportional coefficient K = 5, the past cumulative deviation is 10°C·s, the integral coefficient L = 1, the current temperature deviation change rate is 0.5°C / s, and the differential coefficient S = 2, then the final heating power u(t) = 10+10+1 = 21. Therefore, the current heating power should be set to 21 power units to reduce the temperature deviation.

[0130] S5.2, after the heating power is adjusted, the syrup temperature of each channel will continue to be monitored in real time. If the temperature deviation persists, the PID controller will continue to calculate the heating power according to the new temperature deviation and make continuous adjustments until the actual temperature is consistent with the target temperature.

[0131] S6. Real-time monitoring of syrup parameters of each channel. The neural network compares the real-time syrup data with the target solution, calculates the error of extrusion pressure and speed, and transmits the error as feedback information to the neural network model.

[0132] S6.1. After receiving the error, the neural network infers how to adjust the pressure and speed based on the current pressure and speed errors and the physical properties of the syrup.

[0133] For example, if the current extrusion pressure is too low, the neural network recommends increasing the pressure to maintain the fluidity of the syrup; if the speed is too fast, it recommends slowing down the speed to prevent affecting the geometry of the finished product.

[0134] According to the inference results, the control signal is output and directly transmitted to the extrusion equipment. The extrusion equipment will adjust the pressure valve or motor speed of the extrusion equipment according to the instructions of the neural network, thereby adjusting the extrusion pressure and speed.

[0135] The neural network will continuously infer and adjust the extrusion parameters based on the latest error until the error gradually decreases and remains within the allowed range.

[0136] It is further explained that the errors in extrusion pressure and speed can be quickly reduced through rapid adjustment of the neural network, preventing product failures due to improper parameter settings, significantly reducing the scrap rate, and at the same time reducing the tediousness and errors of manual operations, improving production efficiency, and reducing labor costs.

[0137] S7. During the extrusion process, the color of the marshmallow needs to be consistent with the preset target color. To ensure color accuracy, the color of the marshmallow extrudate is monitored in real time and converted into Lab color space values.

[0138] The Lab color space value is a color model close to human visual perception, which can better represent the brightness and chromaticity differences of colors. It consists of three components: L* represents the brightness of the color, a* represents the color axis from green to red, and b* represents the color axis from blue to yellow.

[0139] Compare the real-time color of the extrudate to the target color in the target recipe to see if it deviates from the target color.

[0140] S7.1. Monitor the outer contour of the extrudate and extract the boundary contour of the marshmallow. The contour information is converted into a two-dimensional coordinate sequence to represent the outer boundary of the marshmallow.

[0141] The two-dimensional coordinates of the contour are converted into frequency domain representation using Fourier transform to obtain the Fourier descriptor. The Fourier descriptor of the extrudate is compared with the Fourier descriptor in the target solution to see if it deviates from the target shape.

[0142] S7.2. When it is detected that the color or shape of the extrudate deviates from the target solution, the intelligent color matching extrusion control model will automatically adjust the parameters in the extrusion process according to the size and direction of the deviation until the extrudate meets the target solution.

[0143] It is further explained that since the color and shape of the extrudate directly affect the sensory experience of consumers, the precise control of the intelligent color matching extrusion control model can ensure the visual consistency and aesthetics of the product, thereby improving the product's market competitiveness and customer satisfaction.

[0144] This embodiment also provides a computer device, which is suitable for the method of multi-channel synchronous marshmallow extrusion, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the method of multi-channel synchronous marshmallow extrusion as proposed in the above embodiment.

[0145] This embodiment also provides a computer device, which is suitable for the method of multi-channel synchronous marshmallow extrusion, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the method of multi-channel synchronous marshmallow extrusion as proposed in the above embodiment.

[0146] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0147] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for realizing multi-channel synchronous extrusion of marshmallows as proposed in the above embodiment is realized; the storage medium can be realized by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0148] In summary, the present invention can: establish an intelligent color matching extrusion control model, predict the quality of the finished product through the model before actual extrusion, find deviations in time and make corrections, avoid unnecessary waste and rework in the production process, and significantly improve production efficiency and finished product qualification rate. In addition, through PID control, the temperature can be accurately adjusted to ensure that the syrups in different channels are extruded within a suitable temperature range, avoid the influence of inconsistent temperature on the quality of the finished product, and further improve the consistency and accuracy of the finished product.

[0149] Example 2, referring to Table 1, is the second example of the present invention. To further verify the technical solution of the present invention, experimental simulation data of a method for synchronously extruding marshmallows through multiple channels are provided.

[0150] An experimental verification was conducted on a method of multi-channel synchronous extrusion of marshmallows. Three different colors of syrup (red, yellow, and blue) were used as experimental materials, and the control was carried out through an intelligent color matching extrusion control model, zoned temperature control technology, and a method of dynamically adjusting extrusion parameters. To enhance the comparative nature of the experiment, two comparative technologies were introduced: comparative technology A and comparative technology B. Comparative technology A uses the traditional single-channel extrusion method and does not have the real-time multi-channel synchronous control function; comparative technology B uses basic multi-channel extrusion technology, but lacks the intelligent color matching control model and dynamic parameter adjustment function.

[0151] Comparative Technology A: The traditional method of using a single channel to extrude marshmallows does not have the ability to extrude multiple channels simultaneously. This method relies on manual control of temperature and pressure, and cannot achieve real-time monitoring and automatic adjustment of extrusion parameters. Therefore, the color and shape stability of the finished product is poor, and large color differences and geometric deviations are prone to occur.

[0152] Comparative Technology B: It has multi-channel extrusion function, but lacks intelligent control. The parameters in the extrusion process (such as temperature, pressure, and extrusion speed) still rely on manual setting and calibration. Although it has basic zone temperature control function, it cannot dynamically adjust the extrusion parameters according to real-time detection results. When extruding multiple channels simultaneously, it is difficult to ensure the consistency of color and shape of different channels due to the lack of intelligent monitoring mechanism.

[0153] The experimental plan is as follows:

[0154] Syrup preparation: Red, yellow and blue syrups were prepared under the method of multi-channel synchronous extrusion of marshmallows. The composition ratio of syrup is 60% sugar, 30% water and 10% pigment. The initial syrup temperature of each channel is set to 80℃. The pigment of each syrup is based on the Lab color space requirements of the target color.

[0155] Historical data extraction: The historical data of each channel is extracted through the database, including the temperature, viscosity, flow rate, color concentration and extrusion pressure of the syrup. Based on the color requirements of the target solution, the historical data closest to the target color is used as the initial reference, and the initial syrup flow rate and viscosity of each channel are set in combination with the historical data.

[0156] Intelligent color matching extrusion control model: Based on historical data, an intelligent color matching extrusion control model is established to simulate and predict the quality of the finished product in each channel. The color and shape of the syrup during the extrusion process are monitored and adjusted in real time to ensure that the final product meets the target plan.

[0157] Dynamic adjustment of parameters: When the color or shape deviation is detected during the extrusion process and exceeds the threshold of the target solution, the intelligent color matching extrusion control model will dynamically adjust the extrusion pressure, speed and temperature of each channel according to the feedback data. The zone temperature control technology is adopted to accurately control the temperature of each channel through the PID controller to ensure that the syrup temperature is stable within the target range.

[0158] Data monitoring and control: During the experiment, the extrusion speed and pressure of each channel are automatically adjusted by real-time monitoring of the temperature, flow rate, viscosity and other parameters of the syrup to ensure the consistency of the color and shape of the finished product. The data acquisition equipment records the temperature, pressure, color and shape data of each channel and compares them with comparison technology A and comparison technology B.

[0159] Finished product inspection: Use a colorimeter and shape analyzer to inspect the color and shape of the extrudate, and compare the deviation between the actual finished product of each channel and the target solution. The experimental data records the changes in parameters of each channel before and after extrusion and the actual deviation of the finished product. The details are shown in Table 1 below:

[0160] Table 1 Experimental data record table

[0161]

[0162]

[0163] It can be seen intuitively from the experimental data that the multi-channel synchronous extrusion marshmallow method is significantly better than comparison technology A and comparison technology B in controlling color and shape.

[0164] Advantages of color control:

[0165] In the experiment, the invented method showed color deviations in the three channels at the beginning of extrusion;

[0166] They are 4.1, 3.8 and 4.3 respectively. Although the initial deviation is small, it still exceeds the threshold of the target solution. After real-time adjustment, the final color deviation dropped to between 0.6-0.9, which basically met the requirements of the target solution. In comparison technologies A and B, the color deviation is always in the range of 5.8-6.2, indicating that these two comparison technologies are difficult to effectively control the color. Comparison technology A lacks multi-channel synchronous control, and the color deviation is more obvious. Although comparison technology B has multi-channel functions, it does not have an intelligent color matching control model and cannot dynamically adjust the pigment ratio and extrusion parameters, resulting in a large color deviation.

[0167] Advantages of shape control:

[0168] The invented method not only performs well in color, but also has advantages in shape control. In the experiment, the shape deviation of the extrudate of the invented method was 1.4-1.6mm at the beginning. After dynamic adjustment of the intelligent control model, the final shape deviation was reduced to 0.3-0.5mm, which is close to the geometric error range set by the target solution. In contrast, the shape deviation of comparison technology A is as high as 2.8mm, and the shape deviation of comparison technology B also reaches 2.3mm. This shows that the invented method can significantly improve the shape consistency of the finished product by real-time monitoring of the shape contour through Fourier descriptors and dynamically adjusting the extrusion pressure and speed.

[0169] Precision of temperature control:

[0170] The inventive method uses zoned temperature control technology and PID controller, which can accurately keep the syrup temperature of each channel near the target value (±0.1°C). In the experiment, the final syrup temperature of the inventive method was stabilized at around 80.0°C. In comparison, although the temperature control effects of comparison technologies A and B are similar, due to the lack of dynamic adjustment of other parameters, the temperature stability cannot effectively improve the quality of the finished product.

[0171] Optimization of pressure and speed control:

[0172] Experiments show that the invented method can adjust the extrusion pressure and speed of each channel according to real-time feedback. The final extrusion speed fluctuated in the range of 5.4-5.6cm / s, while the extrusion speeds of the comparison technologies A and B were fixed at 5.0-5.2cm / s and failed to be optimized according to real-time data. The invented method can ensure the stability of the syrup flow rate by dynamically adjusting the extrusion speed, thereby improving the shape and color consistency of the finished product.

[0173] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for synchronously extruding cotton candy through multiple channels, characterized in that: include, Determine the target solution, prepare the syrup raw materials according to the target solution, and set the initial temperature; Extract syrup history data and determine initial syrup data for each channel based on the target solution; An intelligent color matching extrusion control model is established based on the historical syrup data, the initial syrup data of each channel is input, the finished product of the initial syrup data is output, and compared with the target solution; When the marshmallow contrast threshold is exceeded, the intelligent color matching extrusion control model dynamically adjusts the initial syrup data of each channel according to the target scheme to form the final syrup data of each channel; Based on the final syrup temperature data of each channel, the temperature of each channel is adjusted in real time through the zone temperature control technology; Detect the final syrup data in real time and automatically adjust the extrusion pressure and speed of each channel according to the target plan; During the extrusion process, the intelligent color matching extrusion control model continuously monitors the color and shape of the extrudate and compares it with the target solution in real time to finally extrude the marshmallow.

2. The method for multi-channel synchronous extrusion of marshmallows according to claim 1, characterized in that: Determine the target solution, prepare the syrup raw materials according to the target solution, and set the initial temperature. The specific steps include the following: Determine the shape and color of the marshmallows as requested; Prepare syrup raw materials and control the proportion of ingredients in syrup raw materials; Prepare food grade color according to the color of the target solution; Start the temperature control function and set the initial temperature for each color of syrup.

3. The method for multi-channel synchronous extrusion of cotton candy according to claim 2, characterized in that: Extract the syrup historical data and determine the initial syrup data for each channel based on the target solution. The specific steps include: Extract the syrup temperature, viscosity, flow rate, color concentration and extrusion pressure of each extrusion channel from the historical database; Based on the target color requirements, the syrup parameters of the batch data closest to the target color in the historical data are extracted as the initial reference frame. At the same time, the color concentration is obtained by calculating the amount of pigment added and combining the concentration setting of the same color in the historical data. Use the batch data with the viscosity closest to the target solution in the historical data to uniformly set the syrup viscosity of all channels; The initial syrup flow rate is calculated based on the flow rate of the extrusion equipment and the cross-sectional area of ​​the extrusion channel. At the same time, the initial syrup flow rate is further fine-tuned based on the syrup component with the highest similarity to the current target solution in the historical data to complete the setting of the syrup flow rate; The syrup data obtained from the historical data are integrated into the initial syrup data.

4. The method for multi-channel synchronous extrusion of cotton candy according to claim 3, characterized in that: Based on the historical data of syrup, an intelligent color matching extrusion control model is established. The initial syrup data of each channel is input, and the finished product of the initial syrup data is output and compared with the target solution. The specific steps include the following: extracting historical data and historical finished product quality data from a database, wherein the historical finished product quality data includes color consistency and shape stability; Normalize historical data and historical finished product quality data; Use visualization tools to observe the relationship between different syrup parameters and the quality of historical finished products, and preliminarily determine the relationship between syrup parameters and the quality of historical finished products; A multiple linear regression model was introduced to determine the regression coefficients of syrup parameters based on historical data, and the multiple linear regression model was fitted using the least squares method; Input the initial syrup data into the multiple linear regression model and output the predicted value of the finished product quality for each channel; Based on historical data and target solutions, the allowable deviation ranges of the finished product color and finished product shape are set as marshmallow comparison thresholds; The finished product quality prediction value of each channel is compared with the marshmallow contrast threshold, the color difference and geometric error between the finished product quality prediction value and the target solution are calculated, and the gap between the finished product and the target is evaluated.

5. The method for multi-channel synchronous extrusion of cotton candy according to claim 4, characterized in that: When the marshmallow contrast threshold is exceeded, the intelligent color matching extrusion control model dynamically adjusts the initial syrup data of each channel according to the target solution to form the final syrup data of each channel, which specifically includes the following steps: When the color difference and geometric shape of the finished product of the initial syrup data exceed the marshmallow contrast threshold, it is judged as unqualified; Based on the comparison results between the finished product of the initial syrup data and the target solution, the deviation between the finished product of the initial syrup data and the target solution is calculated according to the multivariate linear regression model, and the adjustment amount of the syrup parameters in each channel is determined; The syrup parameters that have the greatest impact on exceeding the threshold are adjusted first according to the adjustment amount of the syrup parameters in each channel, and the remaining syrup parameters are adjusted gradually; After the syrup parameters are adjusted, the finished product quality is retested until the color difference and geometric deviation of the finished product return to the marshmallow comparison threshold; The syrup parameters that meet the marshmallow contrast threshold are retained as the final syrup data for each channel.

6. The method for multi-channel synchronous extrusion of cotton candy according to claim 5, characterized in that: Based on the final syrup temperature data of each channel, the temperature of each channel is adjusted in real time through the zone temperature control technology, which specifically includes the following steps: determining the actual temperature of each channel and calculating the deviation of the actual temperature from the syrup temperature data in the final syrup data; Based on the temperature deviation, PID is used to calculate the heating power, and the expression is: Among them, u(t) represents the heating power, K represents the response intensity of the current deviation, e(t) represents the temperature deviation, L represents the influence of the cumulative control deviation on the current control output, t represents the current time, dτ represents the accumulation of temperature deviation in each small time period, S represents the influence of the control temperature change rate on the current heating power, de(t) represents the rate of change of the error over time, and dt represents the small increment of time; The channels are adjusted according to the calculated heating power and the syrup temperature is continuously monitored.

7. The method for multi-channel synchronous extrusion of marshmallows according to claim 6, characterized in that: Real-time detection of final syrup data, and automatic adjustment of extrusion pressure and speed of each channel according to the target solution, including the following steps: Based on historical data, neural networks are trained through supervised learning; The trained neural network receives the final syrup data in real time, compares it with the target solution based on the current extrusion pressure and speed, and calculates the error; The neural network infers based on the error and outputs control signals to adjust the extrusion pressure and speed.

8. The method for multi-channel synchronous extrusion of marshmallows according to claim 7, characterized in that: During the extrusion process, the intelligent color matching extrusion control model continuously monitors the color and shape of the extrudate and compares it with the target solution in real time, and finally extrudes the marshmallow. The specific steps include the following: During the extrusion process, the intelligent color matching extrusion control model calculates the Lab color space value of the extrudate in real time and compares it with the target color. At the same time, the shape contour of the extrudate is analyzed through the Fourier descriptor. When it is detected that the color and shape of the extrudate deviate from the target solution, the intelligent color matching extrusion control model automatically adjusts the extrusion parameters until marshmallows that meet the target solution are extruded.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for multi-channel synchronous extrusion of marshmallows according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for multi-channel synchronous extrusion of marshmallows according to any one of claims 1 to 8 are implemented.

Images