A shampoo production apparatus and control method
Patent Information
- Application Number
- CN202410957352.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-17
- Publication Date
- 2026-10-16
AI Technical Summary
[0030] The beneficial effects of this invention are as follows: the shampoo of this invention incorporates a variety of natural substances with hair care effects, such as tea seed cake, astragalus, lingzhi, and ginger. When these are made into a shampoo product, it is gentle and non-irritating, which can effectively promote scalp blood circulation, improve the scalp environment, and has a good inhibitory effect on hair loss.
Smart Images
Figure CN122912731A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of shampoo production technology, and more specifically, to a shampoo production equipment and control method. Background Technology
[0002] With the fast pace of modern life and high levels of stress, more and more people are suffering from hair loss. Using shampoos with anti-hair loss effects can improve the degree of hair loss to some extent. This invention provides a new type of shampoo with hair-nourishing and conditioning effects, as well as corresponding production equipment and an improved production equipment control method. Summary of the Invention
[0003] In order to solve the technical problems existing in the background art, the present invention provides a shampoo production equipment and control method.
[0004] This invention provides a shampoo comprising an active composition, said active composition comprising 100-150 parts tea seed cake, 1-3 parts turmeric, 7-10 parts rhubarb, 1-1.5 parts arborvitae leaf, 2-5 parts astragalus, 2-3 parts chuanxiong, 1-5 parts he shou wu, 0.5-2 parts eclipta prostrata, 3-8 parts soapberry, 2-3 parts notopterygium root, 3-8 parts small yellow ginger, 1-2 parts privet fruit, 7-10 parts sophora flavescens, 1-3 parts smilax glabra, 1-2 parts cnidium monnieri, 8-12 parts fresh ginger paste, and 2-5 parts edible white vinegar; wherein the above substances are in parts by weight.
[0005] The present invention also provides a shampoo production equipment, including a raw material extraction unit, a mixing and processing tank, and a filling unit;
[0006] The raw material extraction section is used to extract the active ingredients from tea seed cake, turmeric, rhubarb, arborvitae leaf, astragalus, chuanxiong, fleeceflower root, eclipta prostrata, soapberry, notopterygium root, small yellow ginger, privet fruit, sophora flavescens, smilax glabra, cnidium monnieri, and ginger paste in the active composition to obtain the effective components therein. The effective components are then mixed with edible white vinegar to prepare the active composition.
[0007] The mixing tank is used to homogenize and mix the active composition, base emulsion, and stabilizer to prepare a shampoo with a target pH value.
[0008] The filling section is used to fill the shampoo into the packaging bottle.
[0009] The present invention also provides a control method for shampoo production equipment, comprising the following steps:
[0010] The production record data of the shampoo production equipment is retrieved, and the relevant data of the shampoo in the previous production batch is determined based on the production record data. The relevant data includes the first property data of the active composition, the second property data of the base emulsion, and the third property data of the stabilizer.
[0011] The relevant data are simultaneously input into the first depth prediction model, which predicts the cleaning parameters of the mixing tank. The cleaning parameters include the type of cleaning agent, the unit spray volume of the cleaning agent, the cleaning water temperature, and the cleaning time.
[0012] The cleaning equipment is controlled to perform a cleaning operation on the mixing tank according to the cleaning parameters, and the residue is detected in the mixing tank after the cleaning is completed;
[0013] If the residue test results meet the production requirements, the active composition prepared by the raw material extraction unit, the base emulsion, and the stabilizer are fed into the mixing tank for homogenization to prepare a shampoo with the target pH value, and the filling unit is controlled to fill the shampoo into packaging bottles.
[0014] In some embodiments, the first deep prediction model is trained as follows:
[0015] Multiple sets of cleaning data from the mixing tank were collected. The cleaning data included set cleaning parameters, shampoo setting data, and corresponding calibration data. The cleaning data was divided into a training dataset and a test dataset.
[0016] The first depth prediction model is trained using the training dataset. When the training reaches the target test node, the trained first depth prediction model is tested using the test dataset. If the test result meets the convergence condition, the training ends and the first depth prediction model is obtained after sufficient training. Otherwise, the first depth prediction model is trained using the untrained cleaned data in the training dataset until the test result meets the convergence condition.
[0017] In some embodiments, the controlled cleaning equipment performs a cleaning operation on the mixing tank according to the cleaning parameters, including:
[0018] The cleaning equipment is controlled to perform cleaning operations on the mixing tank according to the cleaning parameters output by the first depth prediction model;
[0019] During the cleaning operation, the relative motion dimension between the mixing tank and the cleaning nozzle of the cleaning equipment is detected, and a first cleaning correction index is determined based on the relative motion dimension.
[0020] The first cleaning correction index is used to correct at least one of the cleaning parameters, namely the unit spray volume of cleaning agent, the cleaning water temperature, and the cleaning time, to obtain the target cleaning parameters.
[0021] The mixing tank is cleaned using the target cleaning parameters.
[0022] In some embodiments, the relative motion dimension is negatively correlated with the cleaning correction index.
[0023] In some embodiments, the method further includes:
[0024] Based on the relevant data of the shampoo in the previous production batch and the current production batch, the same active ingredient is determined, and the remaining amount of active ingredient in each sub-extraction unit corresponding to the same active ingredient in the raw material extraction unit is detected;
[0025] A second cleaning correction index is determined based on the remaining amount of the active ingredient, and the cleaning time in the target cleaning parameter is reduced to the target cleaning time using the second cleaning correction index.
[0026] The relevant data, the target cleaning parameters, and the target cleaning duration are simultaneously input into the second depth prediction model, and the second depth prediction model outputs new target cleaning parameters.
[0027] The present invention also provides an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; characterized in that: the processor invokes the executable program code stored in the memory to execute the method as described in any of the preceding claims.
[0028] The present invention also provides a computer storage medium storing a computer program that, when executed by a processor, performs the method described in any of the preceding claims.
[0029] The present invention also provides a computer program product comprising a computer program stored on a non-transitory computer-readable medium, wherein the computer program, when executed by a processor, implements the method as described in any of the preceding claims.
[0030] The beneficial effects of this invention are as follows: the shampoo of this invention incorporates a variety of natural substances with hair care effects, such as tea seed cake, astragalus, lingzhi, and ginger. When these are made into a shampoo product, it is gentle and non-irritating, which can effectively promote scalp blood circulation, improve the scalp environment, and has a good inhibitory effect on hair loss.
[0031] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description
[0032] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:
[0033] Figure 1 This is a schematic diagram of the main structure of a shampoo production equipment disclosed in an embodiment of the present invention;
[0034] Figure 2 This is a flowchart illustrating a production equipment control method disclosed in an embodiment of the present invention. Detailed Implementation
[0035] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.
[0036] This invention discloses a shampoo comprising an active composition, which includes 100-150 parts of tea seed cake, 100-150 parts of tea seed cake, 1-3 parts of turmeric, 7-10 parts of rhubarb, 1-1.5 parts of arborvitae leaf, 2-5 parts of astragalus, 2-3 parts of chuanxiong rhizome, 1-5 parts of fleeceflower root, 0.5-2 parts of eclipta prostrata, 3-8 parts of soapberry, 2-3 parts of notopterygium root, 3-8 parts of small yellow ginger, 1-2 parts of privet fruit, 7-10 parts of sophora flavescens root, 1-3 parts of smilax glabra rhizome, 1-2 parts of cnidium monnieri fruit, 8-12 parts of ginger paste, and 2-5 parts of edible white vinegar.
[0037] Wherein, the above substances are in parts by weight.
[0038] This invention's shampoo incorporates various natural hair-care ingredients, such as tea seed cake, astragalus, and ginger. The resulting shampoo is gentle and non-irritating, effectively promoting scalp blood circulation, improving the scalp environment, and exhibiting a good inhibitory effect on hair loss. To use, apply the shampoo to the hair at a temperature not exceeding 45°C and gently massage, then rinse thoroughly.
[0039] Preferably, in preparing the above-mentioned active composition, the ratio of rhubarb or sophora flavescens to water is 1:10, and the ratio of other components to water is 1:5.
[0040] Please see Figure 1 This invention discloses a shampoo production equipment, including a raw material extraction unit, a mixing and processing tank, and a filling unit;
[0041] The raw material extraction section is used to extract the active ingredients from tea seed cake, turmeric, rhubarb, arborvitae leaf, astragalus, chuanxiong, fleeceflower root, eclipta prostrata, soapberry, notopterygium root, small yellow ginger, privet fruit, sophora flavescens, smilax glabra, cnidium monnieri, and ginger paste in the active composition to obtain the effective components therein. The effective components are then mixed with edible white vinegar to prepare the active composition.
[0042] The mixing tank is used to homogenize and mix the active composition, base emulsion, and stabilizer to prepare a shampoo with a target pH value.
[0043] The filling section is used to fill the shampoo into the packaging bottle.
[0044] The shampoo production equipment of this invention mainly includes the aforementioned production sections. The raw material extraction section actually comprises multiple sub-extraction sections. Each sub-extraction section can use a suitable extraction method to extract the corresponding active ingredients from each active substance. The extraction method can be any one of water extraction, alcohol extraction, or ultrasonic extraction. These active ingredients are then mixed with edible white vinegar to obtain the active composition. The obtained active composition, base emulsion, and stabilizer are simultaneously introduced into a mixing tank for homogenization to obtain a sufficiently refined and stable emulsion, which is the shampoo of this invention. The target pH value of this shampoo is between 4.5 and 6.5 to adapt to the natural pH of the scalp.
[0045] In addition, the production equipment of the present invention should also include processes such as filtration, sterilization, and flavor adjustment, as well as corresponding production components. Any existing mature products can be used, but since they are not the focus of the present invention, they will not be described in detail here.
[0046] Please see Figure 2 A method for controlling a shampoo production equipment, comprising the following steps:
[0047] The production record data of the shampoo production equipment is retrieved, and the relevant data of the shampoo in the previous production batch is determined based on the production record data. The relevant data includes the first property data of the active composition, the second property data of the base emulsion, and the third property data of the stabilizer.
[0048] The relevant data are simultaneously input into the first depth prediction model, which predicts the cleaning parameters of the mixing tank. The cleaning parameters include the type of cleaning agent, the unit spray volume of the cleaning agent, the cleaning water temperature, and the cleaning time.
[0049] The cleaning equipment is controlled to perform a cleaning operation on the mixing tank according to the cleaning parameters, and the residue is detected in the mixing tank after the cleaning is completed;
[0050] If the residue test results meet the production requirements, the active composition prepared by the raw material extraction unit, the base emulsion, and the stabilizer are fed into the mixing tank for homogenization to prepare a shampoo with the target pH value, and the filling unit is controlled to fill the shampoo into packaging bottles.
[0051] To improve the efficiency of shampoo production equipment, the shampoo production equipment of this invention can be used to produce multiple types of shampoos. Specifically, the mixing tank can be shared, while the raw material extraction unit includes a sub-extraction unit for extracting active substances from various traditional Chinese medicines. During use, the corresponding sub-extraction unit is automatically activated according to the shampoo formula, and the output ports of the activated sub-extraction units are controlled to connect with the mixing zone of the raw material extraction unit. The extracted active ingredients are then mixed in the mixing zone according to a preset ratio to obtain an active composition, which is then transferred to the mixing tank. The advantage of this setup is that a single shampoo production unit can produce multiple types of shampoos. When switching shampoo types, there is no need to specifically clean the sub-extraction units; only the mixing tank needs to be cleaned, effectively reducing cleaning workload and improving shampoo production efficiency.
[0052] Existing methods for cleaning mixing tanks typically follow preset cleaning parameters. However, to ensure cleaning effectiveness, these parameters are often over-set, leading to excessively long cleaning times and high costs, which hinders shampoo production efficiency and reduces production costs. To address these issues, this invention constructs and fully trains a first deep prediction model. This model can deeply process the property data of the active composition, base emulsion, and stabilizer from the previous production batch of shampoo to predict the corresponding cleaning parameters. Using these parameters to clean the mixing tank ensures thorough cleaning while minimizing the amount of cleaning agent and cleaning time, thereby significantly improving shampoo production efficiency and reducing production costs.
[0053] The relevant data includes property data for the active composition, the base emulsion, and the stabilizer. The property data for the active composition characterizes the content of each active ingredient input into the mixing tank; the property data for the base emulsion refers to the types of substances contained in the shampoo's base formulation, such as surfactants, fragrances, pigments, moisturizers, and antioxidants; and stabilizers need to be added to prevent the mixed emulsion from separating. Stabilizers can be phenoxyethanol, parabens, etc. The various oil-phase substances included in the above-mentioned data are prone to residues in the mixing tank. Furthermore, the viscosity indicators of these oil-phase substances are predictable, and the equivalent viscosity indicators of various types of active ingredients after mixing can be obtained by training a first-level deep prediction model. Therefore, after using the first depth prediction model to process these relevant data in depth, a relatively accurate overall viscosity index of shampoo residue can be predicted. Based on this, the corresponding cleaning parameters can be determined. That is, by using a specific cleaning agent, a specific cleaning force (characterized by the unit spray volume of the cleaning agent), a specific cleaning water temperature, and a specific cleaning time, the shampoos with a certain viscosity in the mixing tank can be quickly cleaned, so that the mixing tank after cleaning is free of residual substances that could affect the quality of the next batch of shampoo to be produced.
[0054] The aforementioned data is retrieved from the management platform of the shampoo production equipment. That is, when each batch of shampoo is produced, the production system or personnel will transmit the corresponding relevant data to the management platform, and the management platform will generate the corresponding production record data.
[0055] In some embodiments, the first deep prediction model is trained as follows:
[0056] Multiple sets of cleaning data from the mixing tank were collected. The cleaning data included set cleaning parameters, shampoo setting data, and corresponding calibration data. The cleaning data was divided into a training dataset and a test dataset.
[0057] The first depth prediction model is trained using the training dataset. When the training reaches the target test node, the trained first depth prediction model is tested using the test dataset. If the test result meets the convergence condition, the training ends and the first depth prediction model is obtained after sufficient training. Otherwise, the first depth prediction model is trained using the untrained cleaned data in the training dataset until the test result meets the convergence condition.
[0058] In this embodiment, the first deep prediction model is preferably constructed using a Transformer with an attention mechanism. The training data is the same as the prediction data, except that corresponding labels need to be added to the training data by machine or manually. These labels are used to indicate whether the set cleaning parameters meet the cleaning effect of a specific shampoo. The constructed first deep prediction model is trained multiple times using these training data. When the training reaches the target test node (e.g., 1 / 3 of the data in the training dataset has been used for training), the trained first deep prediction model is tested multiple times using test data. If the convergence condition has been met, the first deep prediction model is considered to have sufficient accurate prediction ability; otherwise, training continues using other training data until the convergence condition in the test is met, at which point training ends.
[0059] In some embodiments, the controlled cleaning equipment performs a cleaning operation on the mixing tank according to the cleaning parameters, including:
[0060] The cleaning equipment is controlled to perform cleaning operations on the mixing tank according to the cleaning parameters output by the first depth prediction model;
[0061] During the cleaning operation, the relative motion dimension between the mixing tank and the cleaning nozzle of the cleaning equipment is detected, and a first cleaning correction index is determined based on the relative motion dimension.
[0062] The first cleaning correction index is used to correct at least one of the cleaning parameters, namely the unit spray volume of cleaning agent, the cleaning water temperature, and the cleaning time, to obtain the target cleaning parameters.
[0063] The mixing tank is cleaned using the target cleaning parameters.
[0064] In this embodiment, since the aforementioned first depth prediction model predicts cleaning parameters based on the criteria of saving cleaning agent and reducing cleaning time, the cleaning parameters may be in a critical state between being able to clean effectively and not being able to clean effectively. To ensure that the mixing tank can be cleaned effectively, the predicted cleaning parameters need to be appropriately increased.
[0065] Meanwhile, managers can pre-determine cleaning methods for the cleaning equipment. These methods primarily differ in the relative motion dimension between the mixing tank and the cleaning nozzles. This relative motion dimension can be one-dimensional, two-dimensional, three-dimensional, or multi-dimensional. For example, if the cleaning nozzle only moves up and down within the mixing tank while the cleaning agent spray angle remains constant, the relative motion dimension is one-dimensional. If the cleaning nozzle moves up and down within the mixing tank while the cleaning agent spray angle changes horizontally (the cleaning nozzle rotates horizontally while spraying), the relative motion dimension is two-dimensional. If the cleaning nozzle moves up and down within the mixing tank while the cleaning agent spray angle is three-dimensional (the cleaning nozzle rotates horizontally while also changing its angle vertically), the relative motion dimension is three-dimensional. Furthermore, the above multiple dimensions can also occur when the cleaning nozzle remains stationary while the mixing tank moves relative to it, which also constitutes the aforementioned multi-dimensional motion. When the mixing tank and the cleaning nozzle move simultaneously, the aforementioned situation of multi-dimensional relative motion occurs. For example, the cleaning nozzle moves up and down in the mixing tank and the cleaning agent spray angle of the cleaning nozzle is three-dimensional, while the mixing tank rotates in the opposite direction to the cleaning nozzle in terms of horizontal rotation angle.
[0066] Therefore, the present invention determines the corresponding cleaning correction index based on the relative motion dimension between the mixing tank and the cleaning nozzle of the cleaning equipment, and then uses the cleaning correction index to increase the cleaning parameters.
[0067] The correction of the cleaning parameters mainly involves adjusting at least one of the following: the unit spray volume of the cleaning agent, the cleaning water temperature, and the cleaning time. Specifically, the unit spray volume of the cleaning agent is increased, the cleaning water temperature is increased, and the cleaning time is increased.
[0068] It should be noted that the relative motion dimension can be derived from a comprehensive analysis of the motion control commands of the mixing tank and the cleaning nozzle obtained from the control system, which will not be elaborated further.
[0069] In some embodiments, the relative motion dimension is negatively correlated with the cleaning correction index.
[0070] In this embodiment, the present invention sets the probability of the mixing tank being cleaned to be greater when the relative motion dimension is larger, and thus sets the cleaning correction index to be smaller, that is, there is no need to excessively increase the cleaning parameters predicted by the first depth prediction model; conversely, the probability of the mixing tank being cleaned to be smaller when the relative motion dimension is smaller, and thus sets the cleaning correction index to be larger, that is, there is a need to increase the cleaning parameters predicted by the first depth prediction model to a greater extent.
[0071] In some embodiments, the method further includes:
[0072] Based on the relevant data of the shampoo in the previous production batch and the current production batch, the same active ingredient is determined, and the remaining amount of active ingredient in each sub-extraction unit corresponding to the same active ingredient in the raw material extraction unit is detected;
[0073] A second cleaning correction index is determined based on the remaining amount of the active ingredient, and the cleaning time in the target cleaning parameter is reduced to the target cleaning time using the second cleaning correction index.
[0074] The relevant data, the target cleaning parameters, and the target cleaning duration are simultaneously input into the second depth prediction model, and the second depth prediction model outputs new target cleaning parameters.
[0075] In this embodiment, after the production of the previous batch of shampoo is completed, a certain amount of active ingredients may remain in the selected sub-extraction sections of the raw material extraction unit. These remaining ingredients can be used for the production of the current batch of shampoo. To minimize the probability of these remaining active ingredients being oxidized and ineffective, it is necessary to speed up the cleaning process of the mixing tank. To this end, the present invention determines a second cleaning correction index based on the amount of active ingredients remaining in the sub-extraction sections (the sum of the remaining amounts in all sub-extraction sections associated with the same active ingredient). This second cleaning correction index is used to reduce the cleaning time in the aforementioned target cleaning parameters to the target cleaning time. Then, using this target cleaning time as a constraint, a second depth prediction model is used to further process the aforementioned relevant data and target cleaning parameters (unit spray volume of cleaning agent, cleaning water temperature) to obtain new target cleaning parameters. These new target cleaning parameters enable the mixing tank to be cleaned within the target cleaning time.
[0076] By analyzing relevant data from the previous and current production batches of shampoo, the same active ingredients can be identified. The remaining amount of these active ingredients in each sub-extraction unit can then be detected. Each sub-extraction unit is equipped with a corresponding residual amount detection sensor; this invention does not limit the type or number of these sensors.
[0077] It should be noted that the amount of each Chinese herbal raw material added in each batch is basically determined according to the above-mentioned shampoo formula and the corresponding batch production volume. However, due to limitations in the quality of the Chinese herbal raw materials, the residual amount of active ingredients in each sub-extraction section may be excessive. Conversely, the residual amount of active ingredients may be very small, in which case it is unnecessary to perform the embodiments of the present invention. Of course, if the formulas of the shampoo in the previous production batch and the current production batch do not contain the same active ingredients, then it is also unnecessary to perform the embodiments of the present invention.
[0078] Furthermore, the second deep prediction model in this invention is also preferably constructed using a Transformer with an attention mechanism. Its training dataset contains multiple sets of cleaning data collected from the mixing tank. This cleaning data includes relevant setting data, target cleaning parameters (unit spray volume of cleaning agent, cleaning water temperature), target cleaning duration, and corresponding calibration data. The training method is the same as that of the aforementioned first deep prediction model and will not be repeated here.
[0079] The present invention also provides an electronic device, comprising: a memory storing executable program code; and a processor coupled to the memory; characterized in that: the processor invokes the executable program code stored in the memory to execute the method as described in the foregoing embodiments.
[0080] The present invention also provides a computer storage medium storing a computer program, which is executed by a processor to perform the methods described in the foregoing embodiments.
[0081] The present invention also provides a computer program product, including a computer program stored on a non-transitory computer-readable medium, wherein the computer program, when executed by a processor, implements the method described in the foregoing embodiments.
[0082] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0083] In the context of this disclosure, a computer storage medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
[0084] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.
[0085] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.
[0086] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.
Claims
1. A shampoo production apparatus, wherein the shampoo comprises an active composition, characterized in that: The active composition includes tea seed cake, turmeric, rhubarb, arborvitae leaf, astragalus, chuanxiong, fleeceflower root, eclipta prostrata, soapberry, notopterygium root, small yellow ginger, privet fruit, sophora flavescens, smilax glabra, cnidium monnieri, ginger paste, and edible white vinegar; the production equipment includes a raw material extraction unit, a mixing and processing tank, and a filling unit; The raw material extraction section is used to extract the active ingredients from tea seed cake, turmeric, rhubarb, arborvitae leaf, astragalus, chuanxiong, fleeceflower root, eclipta prostrata, soapberry, notopterygium root, small yellow ginger, privet fruit, sophora flavescens, smilax glabra, cnidium monnieri, and ginger paste in the active composition to obtain the effective components therein. The effective components are then mixed with edible white vinegar to prepare the active composition. The mixing tank is used to homogenize and mix the active composition, base emulsion, and stabilizer to prepare a shampoo with a target pH value. The filling section is used to fill the shampoo into the packaging bottle.
2. A control method for the shampoo production equipment according to claim 1, characterized in that, The methods and steps include the following: Retrieve production record data from the shampoo production equipment, and determine relevant data of the shampoo in the previous production batch based on the production record data. The relevant data includes the first property data of the active composition, the second property data of the base emulsion, and the third property data of the stabilizer. The relevant data are simultaneously input into the first depth prediction model, which predicts the cleaning parameters of the mixing tank. The cleaning parameters include the type of cleaning agent, the unit spray volume of the cleaning agent, the cleaning water temperature, and the cleaning time. The cleaning equipment is controlled to perform a cleaning operation on the mixing tank according to the cleaning parameters, and the residue is detected in the mixing tank after the cleaning is completed; If the residue test results meet the production requirements, the active composition prepared by the raw material extraction unit, the base emulsion, and the stabilizer are fed into the mixing tank for homogenization to prepare a shampoo with the target pH value, and the filling unit is controlled to fill the shampoo into packaging bottles.
3. The control method according to claim 2, characterized in that: The training method for the first depth prediction model is as follows: Multiple sets of cleaning data from the mixing tank were collected. The cleaning data included set cleaning parameters, shampoo setting data, and corresponding calibration data. The cleaning data was divided into a training dataset and a test dataset. The first depth prediction model is trained using the training dataset. When the training reaches the target test node, the trained first depth prediction model is tested using the test dataset. If the test result meets the convergence condition, the training ends and the first depth prediction model is obtained after sufficient training. Otherwise, the first depth prediction model is trained using the untrained cleaned data in the training dataset until the test result meets the convergence condition.
4. The control method according to claim 3, characterized in that: The controlled cleaning equipment performs a cleaning operation on the mixing tank according to the cleaning parameters, including: The cleaning equipment is controlled to perform cleaning operations on the mixing tank according to the cleaning parameters output by the first depth prediction model; During the cleaning operation, the relative motion dimension between the mixing tank and the cleaning nozzle of the cleaning equipment is detected, and a first cleaning correction index is determined based on the relative motion dimension. The first cleaning correction index is used to correct at least one of the cleaning parameters, namely the unit spray volume of cleaning agent, the cleaning water temperature, and the cleaning time, to obtain the target cleaning parameters. The mixing tank is cleaned using the target cleaning parameters.
5. The control method according to claim 4, characterized in that: The relative motion dimension is negatively correlated with the cleaning correction index.
6. The control method according to claim 4, characterized in that: The method further includes: Based on the relevant data of the shampoo in the previous production batch and the current production batch, the same active ingredient is determined, and the remaining amount of active ingredient in each sub-extraction unit corresponding to the same active ingredient in the raw material extraction unit is detected; A second cleaning correction index is determined based on the remaining amount of the active ingredient, and the cleaning time in the target cleaning parameter is reduced to the target cleaning time using the second cleaning correction index. The relevant data, the target cleaning parameters, and the target cleaning duration are simultaneously input into the second depth prediction model, and the second depth prediction model outputs new target cleaning parameters.