A method for intelligently controlling the production process of fatty acid balanced fat powder

Abstract

The present invention relates to the field of intelligent control technology, specifically a method for intelligently controlling the production process of fatty acid balanced fat powder, wherein oil, emulsifier and water are mixed in proportion and sheared in a shear mixing container; a heating model of oil and water raw materials is constructed to calculate the time and insulation power required for the heater to heat the oil and water raw materials to the target temperature; during the heating process, a shearing operation is performed simultaneously, and a calculation model for the change of oil droplet diameter is constructed based on the relationship between the oil droplet particle diameter and the shearing time and the shearing temperature, and the shearing time required to reach the target diameter is calculated; the longer time between the heating time and the shearing time is used as the working time, and the state of the oil-water emulsion is detected by a convolutional neural network after the end; the oil-water emulsion after shear mixing is spray-dried to form fat powder particles, and the particles are sieved, packaged and stored. The method realizes efficient and accurate fat powder production through intelligent control.

Description

Technical Field

[0001] The invention relates to the field of intelligent control technology, in particular to a method for intelligently controlling a fatty acid balanced fat powder production process. Background Art

[0002] Fatty acid balanced fat powder is a nutritional supplement product that regulates the proportion of fatty acid intake. It is mainly composed of oil, emulsifier and part of water, and is made through emulsification and spray drying processes.

[0003] At present, the production process of fatty acid balanced fat powder is mainly the traditional mixing, drying and packaging process, which lacks intelligent control means. The traditional fat powder production process often relies on experience-based operations, which will lead to large fluctuations in product quality and is not conducive to maintaining product stability and quality consistency. In addition, the key parameters of the production process cannot be monitored and adjusted in real time during the production process, resulting in unstable product quality and low production efficiency.

[0004] With the advancement of science and technology, the application of intelligent production technology is becoming more and more extensive, especially in food processing and production. The use of intelligent technology can more accurately control various parameters in the production process, thereby improving product quality, reducing human errors, reducing production costs, and achieving efficient and sustainable production. The existing technology does not guarantee the stability of the quality of the produced fat powder from the perspective of intelligent control.

[0005] In view of this, the present invention proposes a method for intelligently controlling the production process of fatty acid balanced fat powder. Summary of the invention

[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a method for intelligently controlling the production process of fatty acid balanced fat powder, comprising: mixing oil, emulsifier and water according to a ratio, shearing the oil-water raw materials in a shear mixing container; constructing a heating model for the oil-water raw materials, calculating the heating time and insulation power required for the heater to heat the oil-water raw materials to the target temperature based on the detection data of the multi-point temperature sensor and the set target temperature, and adjusting and controlling the heating of the oil-water raw materials according to the calculated heating data; shearing the oil-water raw materials simultaneously during the heating process of the oil-water raw materials, and constructing an oil droplet diameter change calculation model based on the relationship between the diameter of the oil droplet particles in the oil-water raw materials and the shear time and the shear temperature, and calculating the shear time required to shear the oil droplet particle diameter to the target diameter based on the oil droplet diameter change calculation model; taking the longest time between the heating time and the shear time as the working time of the shear mixing, and when the working time is over, detecting whether the oil-water raw materials are sheared into an oil-water emulsion by a convolutional neural network; spray drying the oil-water emulsion after the shear mixing to form fat powder particles, and sieving, packaging and storing the fat powder particles.

[0007] Preferably, the oil, emulsifier and water are proportioned according to the type of oil product, and the oil and water raw materials are sheared and mixed in a shear mixing container to form an oil-water emulsion;

[0008] Setting multiple temperature sensors in the shear mixing container, including setting temperature sensors at the bottom, middle and top of the container; setting multiple heaters in the shear mixing container to heat the oil-water raw materials in the container;

[0009] Assume the target temperature of the oil-water raw material is T P , the ambient temperature is T E , use multiple heaters to heat the oil and water raw materials of oil products, emulsifiers and water, the number of heaters is n, and the power of the heater is set to P A , the specific heat capacity of the oil-water raw material is c, and the heat loss of the oil-water raw material is Q loss , the total mass of oil and water raw materials is m;

[0010] Construct an oil-water raw material heating model and calculate the time it takes for the heater to heat the oil-water raw material to the target temperature T P The required heating time t1; and when the oil-water raw material is heated to the target temperature T P The required insulation power.

[0011] Preferably, the oil-water raw material heating model is:

[0012] n·P A t1-Q loss ·t1=m·c·(T P -T E )

[0013] Q loss =Q C +Q R

[0014] Q C =h c ×A×(T t -T E )

[0015]

[0016] Among them, Q C is the heat loss due to convection heat transfer, h c is the convective heat transfer coefficient, A is the surface area outside the emulsification container, T t is the instantaneous temperature of the oil-water raw material; Q R is the heat loss due to radiation heat transfer, ∈ is the thermal radiation emissivity of the outer surface of the container, σ is the Stefan-Boltzmann constant; t1 is the heating time required to heat up to the target temperature;

[0017] Calculate the heating time t1 and insulation power P based on the oil-water raw material heating model w ;

[0018] Heating time t1 is:

[0019]

[0020] Insulation power: P w =Q loss / n.

[0021] Preferably, based on the relationship between the diameter of oil droplets in the oil-water raw material and the shearing time and the shearing temperature, a calculation model for the change of the diameter of oil droplets in the oil-water raw material is constructed:

[0022]

[0023] Where D(t, T) is the diameter of the oil droplet in the oil-water feedstock, D start is the initial oil droplet diameter, D min is the minimum oil droplet diameter that can be sheared by the shear mixer; k is the decay constant, which is used to adjust the influence of time and temperature and is set to 0.001; T ref is the reference temperature, set to 20°C; t is the working time of the shear mixer; T is the temperature of the oil-water raw material when the shear mixer is working;

[0024] Calculate the diameter of the oil droplets in the oil-water raw material to be sheared to the target diameter D target The time t2 required:

[0025]

[0026] Among them, D target is the target diameter of the oil droplet particle, D target ≥D min .

[0027] Preferably, the temperature of the oil-water raw material is detected by a multi-point temperature sensor in the shear mixing container; when the oil-water raw material is added, the sensor is started to detect the temperature of the oil-water raw material, and the ambient temperature detection value is transmitted to the heating model of the oil-water raw material to calculate the heating time;

[0028] When t1>t2, at t1+t c When the oil and water raw materials are heated, t c is the current time point, the heater enters the insulation state; at this time, if the diameter of the oil droplet particle produced by the shear mixer D(t1, T)>D target , then continue to shear and mix the oil and water raw materials until t2+t c time;

[0029] When t1≤t2, the shear mixer always performs shear mixing on the oil-water raw materials within the time length of t2.

[0030] Preferably, the heating and heat preservation strategy of the heater is:

[0031] After the heating time t1 is reached and the heating is completed, the multi-point temperature sensors in the shear mixing container detect the temperature values ​​of the oil-water raw materials at multiple points;

[0032] Set the temperature difference threshold T th , when the heating time t1 is reached, if the temperature T detected by all sensors s With the target temperature T P The difference is less than or equal to the temperature difference threshold T th , that is, |T s -T P |≤T th When the oil and water raw materials are heated, the heater enters the insulation state;

[0033] In |T s -T P |>T th When the temperature detection value T s With T P For comparison, when T s <T P , the heater continues to heat the oil-water raw materials. When the oil-water raw materials are heated to temperature T P Enter the insulation state when T s >T P When the temperature reaches T, the shear mixer is controlled to stop heating until the oil-water raw material cools to the temperature T P Enter the keep warm state.

[0034] Preferably, in max{t1+t c , t2+t c} time point, the current oil-water raw material is detected, max{·} is a function that takes the maximum value, and the convolutional neural network is trained for oil droplet diameter detection in the oil-water raw material;

[0035] Extract max{t1+t c , t2+t c} oil-water raw materials at a fixed time point, drop a certain amount of oil-water raw materials vertically onto a glass sheet at a fixed height, obtain a visual image of the oil-water raw materials on the glass sheet, remove image noise, enhance the visual image, enhance the outline of the oil droplet particles in the oil-water raw materials, use a convolutional neural network to extract the diameter distribution data of the oil droplet particles in the oil-water raw materials, and calculate the diameter size and probability distribution of the oil droplet particles according to the pixel ratio of the visual image;

[0036] The oil-water emulsion is sprayed into the drying chamber through a sprayer, the water in the emulsion is evaporated in the drying chamber, the dried fat powder particles are collected, the collected fat powder is filtered, a filter with a set filter mesh is used to filter the fat powder out of the filter, unqualified fat powder particles formed during the spraying and drying process that are larger than the sieve hole diameter are screened out, and the qualified fat powder that has passed the screen is packaged and stored.

[0037] A system for intelligently controlling the production process of balanced fatty acid fat powder, which is implemented based on the method for intelligently controlling the production process of balanced fatty acid fat powder, and comprises: an oil proportioning module, a mixing and heating module, a shear mixing model module, a particle detection module, and a drying and packaging storage module;

[0038] The oil proportioning module is used to mix the oil, emulsifier and water according to the proportion, and shear the oil and water raw materials in the shear mixing container;

[0039] The mixed heating module is used to construct an oil-water raw material heating model, calculate the heating time and insulation power required for the heater to heat the oil-water raw materials to the target temperature based on the detection data of the multi-point temperature sensor and the set target temperature, and adjust and control the heating of the oil-water raw materials based on the calculated heating data;

[0040] The shear mixing model module is used to shear the oil-water raw materials simultaneously during the heating process of the oil-water raw materials, and to construct an oil droplet diameter change calculation model based on the relationship between the oil droplet particle diameter in the oil-water raw materials and the shearing time and the shearing temperature, and to calculate the shearing time required to shear the oil droplet particle diameter to the target diameter based on the oil droplet diameter change calculation model;

[0041] The particle detection module uses the longest time between the heating time and the shearing time as the working time of the shear mixing, and when the working time is over, detects whether the oil-water raw material is sheared into the oil-water raw material through a convolutional neural network;

[0042] The drying and packaging storage module is used to spray-dry the oil-water raw materials that have been sheared and mixed to form fat powder particles, and to screen, package and store the fat powder particles.

[0043] An electronic device comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the method for intelligently controlling the production process of fatty acid balanced fat powder by calling the computer program stored in the memory.

[0044] A readable storage medium stores instructions. When the instructions are executed on a computer, the computer executes the method for intelligently controlling the production process of fatty acid balanced fat powder.

[0045] Beneficial effects of the present invention: The present invention can accurately control the ratio of fat to emulsifier, as well as the conditions of heating and shear mixing through intelligent control, thereby ensuring the quality consistency of the oil-water emulsion. This is crucial to the size, distribution and stability of the final fat powder particles.

[0046] The present invention improves production efficiency. The intelligent production method can monitor and adjust production parameters in real time, reduce dependence on manual operation, speed up production, and improve production efficiency. In addition, by optimizing the heating and shearing processes, energy can be saved and production costs can be reduced.

[0047] The present invention enhances the process controllability of the fat preparation process. By constructing the oil-water raw material heating model and the oil droplet particle diameter change model, the production process can be more scientifically predicted and controlled, and the process repeatability and predictability can be achieved. This method is particularly suitable for food production that requires high quality standards and strict specifications.

[0048] The present invention uses a convolutional neural network to automatically detect the diameter of oil droplets, which not only improves the detection efficiency, but also can monitor the production quality in real time. Through data analysis, the production process can be further optimized and unqualified production links can be adjusted in time.

[0049] The present invention reduces environmental impact, and can reduce energy waste and raw material consumption by more accurately controlling the heating and emulsification processes, thereby reducing environmental impact during the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A flow chart of a method for intelligently controlling the production process of fatty acid balanced fat powder provided by the present invention;

[0051] Figure 2 A system structure diagram of an intelligent control process for producing fatty acid balanced fat powder provided by the present invention;

[0052] Figure 3 It is a schematic diagram of the structure of an electronic device provided by the present invention;

[0053] Figure 4 It is a schematic diagram of the structure of the readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0054] In order to better understand the present application, a more detailed description will be made of various aspects of the present application with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of exemplary embodiments of the present application, and are not intended to limit the scope of the present application in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0055] In the accompanying drawings, the size, dimensions and shapes of the elements have been slightly adjusted for ease of illustration. The drawings are for illustration only and are not strictly drawn to scale. As used herein, the terms "substantially", "approximately" and similar terms are used as terms of approximation, not as terms of degree, and are intended to illustrate the inherent deviations in measurements or calculations that will be recognized by those of ordinary skill in the art. In addition, in this application, the order in which the steps are described does not necessarily represent the order in which these processes occur in actual operation, unless otherwise specified or can be derived from the context.

[0056] It should also be understood that expressions such as "include", "including", "have", "contain" and / or "comprising" are open rather than closed expressions in this specification, which indicate the presence of the stated features, elements and / or components, but do not exclude the presence of one or more other features, elements, components and / or combinations thereof. In addition, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features rather than just the individual elements in the list. In addition, when describing embodiments of the present application, "may" is used to mean "one or more embodiments of the present application". And, the term "exemplary" is intended to refer to an example or illustration.

[0057] Unless otherwise specified, all words (including engineering terms and scientific and technological terms) used in this article have the same meaning as those commonly understood by ordinary technicians in the field to which this application belongs. It should also be understood that, unless clearly stated in this application, words defined in common dictionaries should be interpreted as having the same meaning as their meaning in the context of the relevant technology, and should not be interpreted in an idealized or overly formal sense.

[0058] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0059] Example 1

[0060] Reference Figure 1 The first embodiment of the present invention provides a method for intelligently controlling the production process of fatty acid balanced fat powder.

[0061] According to the type of oil product, the oil, emulsifier and water are proportioned, and the oil and water raw materials are sheared and mixed in a shear mixing container to form an oil-water emulsion.

[0062] Assume the mass of the oil product is m oil When the oil product is vegetable oil, the emulsifier m r The dosage is: mr =0.01×m oil , the amount of water used is: m water =1.0×m oil ; When the oil product is animal oil, the emulsifier m r The dosage is: m r =0.005×m oil ; The amount of water used is: m water =0.8×m oil ; When the oil product is a mixture of vegetable oil and animal fat, set m v is the mass of vegetable oil, m a is the mass of animal oil, then the emulsifier m r The dosage is: m r =0.01×m v +0.005×m a ; The amount of water used is: m water =1.0×m v +0.8×m a .

[0063] The pretreated oil is mixed with an emulsifier and water to construct an oil-water raw material heating model, and shear mixing is performed during the heating process.

[0064] Multi-point temperature sensors are set in the shear mixing container, including temperature sensors at the bottom, middle and top of the container; multiple heaters are set in the shear mixing container to heat the oil-water raw materials in the container.

[0065] Assume the target temperature of the oil-water raw material is T P , the ambient temperature is T E , use multiple heaters to heat the oil and water raw materials of oil products, emulsifiers and water, the number of heaters is n, and the power of the heater is set to P A , the specific heat capacity of the oil-water raw material is c, and the heat loss of the oil-water raw material is Q loss , the total mass of oil and water raw materials is m.

[0066] Construct an oil-water raw material heating model and calculate the time it takes for the heater to heat the oil-water raw material to the target temperature T P The required heating time t1; and when the oil-water raw material is heated to the target temperature T P The required insulation power.

[0067] The oil-water raw material heating model is:

[0068] n·P A t1-Q loss ·t1=m·c·(T P -T E )

[0069] Q loss =Q C +Q R

[0070] Q c =h c ×A×(T t -T E )

[0071]

[0072] Among them, Q C is the heat loss due to convection heat transfer, h c is the convective heat transfer coefficient, A is the surface area outside the emulsification container, T t is the instantaneous temperature of the oil-water raw material; Q R is the heat loss due to radiation heat transfer, ∈ is the thermal radiation emissivity of the outer surface of the container, σ is the Stefan-Boltzmann constant; t1 is the heating time required to heat up to the target temperature.

[0073] Calculate the heating time t1 and insulation power P based on the oil-water raw material heating model w .

[0074] Heating time t1 is:

[0075]

[0076] Insulation power: P w =Q loss / n.

[0077] Based on the relationship between the diameter of oil droplets in oil-water raw materials and shear time and shear temperature, a calculation model for the change of oil droplet diameter in oil-water raw materials is constructed:

[0078]

[0079] Where D(t, T) is the diameter of the oil droplet in the oil-water feedstock, D start is the initial oil droplet diameter, D min is the minimum oil droplet diameter that can be sheared by the shear mixer; k is the decay constant, which is used to adjust the influence of time and temperature and is set to 0.001; T ref is the reference temperature, set to 20°C; t is the working time of the shear mixer; T is the temperature of the oil-water raw material when the shear mixer is working;

[0080] Calculate the diameter of the oil droplets in the oil-water raw material to be sheared to the target diameter D target The time t2 required:

[0081]

[0082] Among them, D target is the target diameter of the oil droplet particle, D target ≥D min .

[0083] The temperature of the oil-water raw materials is detected by multi-point temperature sensors in the shear mixing container; when the oil-water raw materials are added, the sensor is started to detect the temperature of the oil-water raw materials, and the ambient temperature detection value is transmitted to the heating model of the oil-water raw materials. The ambient temperature detection value is the temperature of the oil-water raw materials when the oil-water raw materials are added, and the heating time is calculated.

[0084] When t1>t2, at t1+t c When the oil and water raw materials are heated, t c is the current time point, the heater enters the insulation state; at this time, if the diameter of the oil droplet particle produced by the shear mixer D(t1, T)>D target , then continue to shear and mix the oil and water raw materials until t2+t c time;

[0085] When t1≤t2, the shear mixer always performs shear mixing on the oil-water raw materials within the time length of t2.

[0086] Heater heating and insulation strategy:

[0087] After the heating time t1 is reached and the heating is completed, the multi-point temperature sensors in the shear mixing container detect the temperature values ​​of the oil-water raw materials at multiple points;

[0088] Set the temperature difference threshold T th , when the heating time t1 is reached, if the temperature T detected by all sensors s With the target temperature T P The difference is less than or equal to the temperature difference threshold T th , that is, |T s -T P |≤T th When the oil and water raw materials are heated, the heater enters the insulation state;

[0089] In |T s -T P |>T th When the temperature detection value T s With T P For comparison, when T s <T P , the heater continues to heat the oil-water raw materials. When the oil-water raw materials are heated to temperature T P Enter the insulation state when T s >T PWhen the temperature reaches T, the shear mixer is controlled to stop heating until the oil-water raw material cools to the temperature T P Enter the keep warm state.

[0090] The convolutional neural network is used to detect the diameter of oil droplets in the oil-water raw material after shear mixing; c , t2+t c} time point, the current oil-water raw material is detected, max{·} is a function that takes the maximum value, and the convolutional neural network is trained for oil droplet diameter detection in oil-water raw materials.

[0091] Extract max{t1+t c , t2+t c}At a certain time point, a certain amount of oil-water raw materials are dropped vertically onto a glass sheet at a fixed height to obtain a visual image of the oil-water raw materials on the glass sheet, the image noise is removed, the visual image is enhanced, the outline of the oil droplet particles in the oil-water raw materials is enhanced, and a convolutional neural network is used to extract the diameter distribution data of the oil droplet particles in the oil-water raw materials, and the diameter size and probability distribution of the oil droplet particles are calculated according to the pixel ratio of the visual image.

[0092] The convolutional neural network is trained to detect the diameter size of oil-water raw material droplet particles, obtain visual images of oil droplet particles in the oil-water raw material, manually divide labels for the visual images, mark images with qualified diameter sizes as 1, and mark images with unqualified diameter sizes as 0, and use the visual images and labels of the oil droplet particles in the oil-water raw material as a data set to train the convolutional neural network, the data set includes a training set, a validation set and a test set; the ratio of the training set, the validation set and the test set is: 70%:15%:15%.

[0093] The training set is used as the input of the convolutional neural network, and the qualified probability of the oil droplet particle diameter size is used as the output. Minimizing the loss function is used as the training goal of the convolutional neural network, and the training is stopped when the loss function converges.

[0094] The trained convolutional neural network is used to detect the diameter size distribution results of the oil-water raw material droplet particles, and the qualified oil-water raw materials are marked as oil-water emulsions.

[0095] The oil-water emulsion that has completed shear mixing is spray-dried to prepare fat powder particles, and the prepared fat powder particles are screened, packaged and stored.

[0096] The oil-water emulsion is sprayed into the drying chamber through a sprayer, and the water in the emulsion is quickly evaporated by high-temperature air in the drying chamber. The dried fat powder particles are collected and filtered. A filter with a specific filter mesh is constructed to filter the fat powder out of the filter, and unqualified fat powder particles with larger particles formed during the spraying and drying process are screened out. The qualified fat powder that has passed the screen is packaged and stored.

[0097] Example 2

[0098] Reference Figure 2 The second embodiment of the present invention provides a system for intelligently controlling the production process of fatty acid balanced fat powder.

[0099] The system comprises an oil proportioning module, a mixing and heating module, a shear mixing model module, a particle detection module and a drying and packaging storage module.

[0100] The oil proportioning module is used to mix the oil, emulsifier and water according to a proportion, and shear the oil and water raw materials in the shear mixing container.

[0101] The mixed heating module is used to construct an oil-water raw material heating model. Based on the detection data of multi-point temperature sensors and the set target temperature, the heating time and insulation power required for the heater to heat the oil-water raw materials to the target temperature are calculated, and the heating of the oil-water raw materials is adjusted and controlled according to the calculated heating data.

[0102] The shear mixing model module is used to shear the oil-water raw materials simultaneously during the heating process of the oil-water raw materials, and to construct an oil droplet diameter change calculation model based on the relationship between the oil droplet particle diameter in the oil-water raw materials and the shear time and shear temperature. Based on the oil droplet diameter change calculation model, the shear time required to shear the oil droplet particle diameter to the target diameter is calculated.

[0103] The particle detection module uses the longest time between the heating time and the shearing time as the working time of shear mixing, and when the working time is over, detects whether the oil-water raw material is sheared into the oil-water raw material through a convolutional neural network.

[0104] The drying and packaging storage module is used to spray-dry the oil-water raw materials that have been sheared and mixed to form fat powder particles, and to screen, package and store the fat powder particles.

[0105] Example 3

[0106] Figure 3 FIG. 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 3As shown, according to another aspect of the present invention, an electronic device 500 is also provided. The electronic device 500 may include one or more processors and one or more memories. The memories store computer readable codes, and when the computer readable codes are executed by the one or more processors, the method for intelligently controlling the production process of fatty acid balanced fat powder as described above can be executed.

[0107] The method or system according to the embodiment of the present invention can also be used by Figure 3 The architecture of the electronic device shown is implemented.

[0108] like Figure 3 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a ROM 503, a RAM 504, a communication port 505 connected to a network, an input / output component 506, a hard disk 507, and the like.

[0109] The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, can store a method for intelligently controlling the production process of fatty acid balanced fat powder provided by the present invention.

[0110] A method for intelligently controlling a fatty acid balanced fat powder production process comprises: mixing oil, emulsifier and water according to a proportion, shearing the oil-water raw material in a shear mixing container; constructing a heating model for the oil-water raw material, calculating the heating time and insulation power required for the heater to heat the oil-water raw material to the target temperature based on detection data of a multi-point temperature sensor and a set target temperature, and adjusting and controlling the heating of the oil-water raw material with the calculated heating data; shearing the oil-water raw material simultaneously during the heating process of the oil-water raw material, and constructing an oil droplet diameter change calculation model based on the relationship between the diameter of oil droplet particles in the oil-water raw material and the shear time and the shear temperature, and calculating the shear time required for shearing the oil droplet particle diameter to the target diameter based on the oil droplet diameter change calculation model; taking the longest time between the heating time and the shear time as the working time of the shear mixing, and when the working time is over, detecting whether the oil-water raw material is sheared into an oil-water emulsion by a convolutional neural network; spray drying the oil-water emulsion after the shear mixing to form fat powder particles, and sieving, packaging and storing the fat powder particles.

[0111] Furthermore, the electronic device 500 may also include a user interface 508. Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.

[0112] Example 4

[0113] Figure 4It is a schematic diagram of the structure of a readable storage medium provided by an embodiment of the present invention.

[0114] like Figure 4 As shown, a readable storage medium 600 according to one embodiment of the present invention.

[0115] The readable storage medium 600 has computer readable instructions stored thereon.

[0116] When the computer-readable instructions are executed by a processor, a method for intelligently controlling a fatty acid-balanced fat powder production process according to an embodiment of the present invention described with reference to the above drawings may be executed.

[0117] The storage medium 600 includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. In addition, according to an embodiment of the present invention, the process described above with reference to the flowchart may be implemented as a computer software program.

[0118] For example, the present invention provides a non-transitory machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be run by a processor to execute instructions corresponding to the method steps provided by the present invention, such as: mixing oil, emulsifier and water according to a ratio, and shearing the oil-water raw material in a shear mixing container; constructing an oil-water raw material heating model, based on the detection data of a multi-point temperature sensor and the set target temperature, calculating the heating time and insulation power required for the heater to heat the oil-water raw material to the target temperature, and adjusting and controlling the heating of the oil-water raw material according to the calculated heating data. ; During the heating process of the oil-water raw materials, the oil-water raw materials are sheared at the same time, and based on the relationship between the diameter of the oil droplet particles in the oil-water raw materials and the shearing time and the shearing temperature, an oil droplet diameter change calculation model is constructed, and based on the oil droplet diameter change calculation model, the shearing time required to shear the oil droplet particle diameter to the target diameter is calculated; the longest time between the heating time and the shearing time is used as the working time of the shear mixing, and when the working time is over, a convolutional neural network is used to detect whether the oil-water raw materials are sheared into an oil-water emulsion; the oil-water emulsion after the shear mixing is spray-dried to form fat powder particles, and the fat powder particles are sieved, packaged and stored.

[0119] When the computer program is executed by the central processing unit (CPU), the above functions defined in the method of the present invention are performed. The method, apparatus, and device of the present invention may be implemented in many ways. For example, the method, apparatus, and device of the present invention may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware.

[0120] The above sequence for the steps of the method is for illustration only, and the steps of the method of the present invention are not limited to the sequence specifically described above unless otherwise specifically stated.

[0121] In addition, in some embodiments, the present invention can also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present invention. Therefore, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

[0122] In addition, the parts of the above technical solutions provided in the embodiments of the present invention that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0123] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for intelligently controlling the production process of fatty acid balanced fat powder, characterized in that: include: Mixing oil, emulsifier and water according to a proportion to form an oil-water raw material, and shearing the oil-water raw material in a shear mixing container; Construct an oil-water raw material heating model, calculate the heating time and insulation power required to heat the oil-water raw materials to the target temperature based on the detection data of multi-point temperature sensors and the set oil-water raw material heating target temperature, and adjust and control the heating of the oil-water raw materials based on the calculated heating data; Assume the target temperature of the oil-water raw material is T P , the ambient temperature is T E , the number of heaters is n, and the power of the heater is set to P A , the specific heat capacity of the oil-water raw material is c, and the heat loss of the oil-water raw material is Q loss , the total mass of the oil-water raw material is m; the heating model of the oil-water raw material is: n·P A ·t1-Q loss ·t1=m·c·(T P -T E ) Q loss =Q C +Q R Q C =h c ×A×(T t -T E ) Among them, Q C is the heat loss due to convection heat transfer, h c is the convective heat transfer coefficient, A is the surface area outside the emulsification container, T t is the instantaneous temperature of the oil-water raw material; Q R is the heat loss due to radiation heat transfer, ∈ is the thermal radiation emissivity of the outer surface of the container, σ is the Stefan-Boltzmann constant; t1 is the heating time required to heat up to the target temperature; The oil-water raw materials are sheared at the same time during the heating process, and a calculation model for the change of oil droplet diameter is constructed based on the relationship between the diameter of oil droplet particles in the oil-water raw materials and the shearing time and the shearing temperature. Based on the calculation model for the change of oil droplet diameter, the shearing time required to shear the oil droplet particle diameter to the target diameter is calculated, and the operation of the shearer is controlled according to the shearing time; The calculation model for the change of oil droplet diameter in oil-water raw materials is: Where D(t,T) is the diameter of the oil droplet in the oil-water feedstock, D start is the initial oil droplet diameter, D min is the minimum oil droplet diameter that can be sheared by the shear mixer; k is the decay constant, which is used to adjust the influence of time and temperature; T ref is the reference temperature; t is the working time of the shear mixer; T is the temperature of the oil-water raw material when the shear mixer is working; In the shearing and mixing process of the oil-water raw materials, the longest time between the heating time and the shearing time is taken as the working time of the shearer. When the shearer is finished working, the convolutional neural network is used to detect whether the oil-water raw materials are sheared and mixed to form an oil-water emulsion. The oil-water emulsion after shear mixing is spray-dried to prepare fat powder particles, and the fat powder particles are sieved, packaged and stored.

2. The method for intelligently controlling the production process of fatty acid balanced fat powder according to claim 1, characterized in that: According to the type of oil product, the oil, emulsifier and water are proportioned, and the oil and water raw materials are sheared and mixed in a shear mixing container to form an oil-water emulsion; Setting multiple temperature sensors in the shear mixing container, including setting temperature sensors at the bottom, middle and top of the container; setting multiple heaters in the shear mixing container to heat the oil and water raw materials in the container; using multiple heaters to heat the oil and water raw materials of the oil product, emulsifier and water; Construct an oil-water raw material heating model and calculate the time it takes for the heater to heat the oil-water raw material to the target temperature T P The required heating time t1; and when the oil-water raw material is heated to the target temperature T P The required insulation power.

3. The method for intelligently controlling the production process of fatty acid balanced fat powder according to claim 2, characterized in that: Calculate the heating time t1 and insulation power P based on the oil-water raw material heating model w ; Heating time t1 is: Insulation power: P w =Q loss / n.

4. The method for intelligently controlling the production process of fatty acid balanced fat powder according to claim 3, characterized in that: Calculate the diameter of the oil droplets in the oil-water raw material to be sheared to the target diameter D target The time t2 required: Among them, D target is the target diameter of the oil droplet particle, D target ≥D min .

5. The method for intelligently controlling the production process of fatty acid balanced fat powder according to claim 4, characterized in that: The temperature of the oil-water raw materials is detected by multi-point temperature sensors in the shear mixing container; when the oil-water raw materials are added, the sensor is started to detect the temperature of the oil-water raw materials, and the ambient temperature detection value is transmitted to the heating model of the oil-water raw materials to calculate the heating time; When t1>t2, at t1+t c When the oil and water raw materials are heated, t c is the current time point, the heater enters the insulation state; at this time, if the diameter of the oil droplet particle produced by the shear mixer D(t1,T)>D target , then continue to shear and mix the oil and water raw materials until t2+t c time; When t1≤t2, the shear mixer always performs shear mixing on the oil-water raw materials within the time length of t2.

6. The method for intelligently controlling the production process of fatty acid balanced fat powder according to claim 5, characterized in that: The heating and insulation strategies of the heater are: After the heating time t1 is reached and the heating is completed, the multi-point temperature sensors in the shear mixing container detect the temperature values ​​of the oil-water raw materials at multiple points; Set the temperature difference threshold T th , when the heating time t1 is reached, if the temperature T detected by all sensors s With the target temperature T P The difference is less than or equal to the temperature difference threshold T th , that is, |T s -T P |≤T th When the oil and water raw materials are heated, the heater enters the insulation state; In |T s -T P |>T th When the temperature detection value T s With T P For comparison, when T s <T P , the heater continues to heat the oil-water raw materials. When the oil-water raw materials are heated to temperature T P Enter the insulation state when T s >T P When the temperature reaches T, the shear mixer is controlled to stop heating until the oil-water raw material cools to the temperature T P Enter the keep warm state.

7. The method for intelligently controlling the production process of fatty acid balanced fat powder according to claim 6, characterized in that: In max{t1+t c ,t2+t c } time point, the current oil-water raw material is detected, max{·} is a function that takes the maximum value, and the convolutional neural network is trained for oil droplet diameter detection in the oil-water raw material; Extract max{t1+t c ,t2+t c } oil-water raw materials at a fixed time point, drop a certain amount of oil-water raw materials vertically onto a glass sheet at a fixed height, obtain a visual image of the oil-water raw materials on the glass sheet, remove image noise, enhance the visual image, enhance the outline of the oil droplet particles in the oil-water raw materials, use a convolutional neural network to extract the diameter distribution data of the oil droplet particles in the oil-water raw materials, and calculate the diameter size and probability distribution of the oil droplet particles according to the pixel ratio of the visual image; The oil-water emulsion is sprayed into the drying chamber through a sprayer, the water in the emulsion is evaporated in the drying chamber, the dried fat powder particles are collected, the collected fat powder is filtered, a filter with a set filter mesh is used to filter the fat powder out of the filter, unqualified fat powder particles formed during the spraying and drying process that are larger than the sieve hole diameter are screened out, and the qualified fat powder that has passed the screen is packaged and stored.

8. A system for intelligently controlling the production process of fatty acid balanced fat powder, which is implemented based on the method for intelligently controlling the production process of fatty acid balanced fat powder according to any one of claims 1 to 7, characterized in that: Including, oil proportioning module, mixing and heating module, shear mixing model module, particle detection module and drying and packaging storage module; The oil proportioning module is used to mix the oil, emulsifier and water according to the proportion, and shear the oil and water raw materials in the shear mixing container; The mixed heating module is used to construct an oil-water raw material heating model, calculate the heating time and insulation power required for the heater to heat the oil-water raw materials to the target temperature based on the detection data of the multi-point temperature sensor and the set target temperature, and adjust and control the heating of the oil-water raw materials based on the calculated heating data; The shear mixing model module is used to shear the oil-water raw materials simultaneously during the heating process of the oil-water raw materials, and to construct an oil droplet diameter change calculation model based on the relationship between the oil droplet particle diameter in the oil-water raw materials and the shearing time and the shearing temperature, and to calculate the shearing time required to shear the oil droplet particle diameter to the target diameter based on the oil droplet diameter change calculation model; The particle detection module uses the longest time between the heating time and the shearing time as the working time of the shear mixing, and when the working time is over, detects whether the oil-water raw material is sheared into the oil-water raw material through a convolutional neural network; The drying and packaging storage module is used to spray-dry the oil-water raw materials that have been sheared and mixed to form fat powder particles, and to screen, package and store the fat powder particles.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the method for intelligently controlling the production process of fatty acid balanced fat powder according to any one of claims 1 to 7 by calling the computer program stored in the memory.

10. A readable storage medium, characterized in that: The readable storage medium stores instructions, and when the instructions are executed on a computer, the computer executes the method for intelligently controlling the production process of fatty acid balanced fat powder as described in any one of claims 1 to 7.

Images