Intelligent control method and system for sea buckthorn fruit oil refining process

Abstract

The invention relates to the technical field of industrial control systems, and provides an intelligent control method and system for a sea buckthorn fruit oil refining process. Based on a nonlinear relationship between a concentration parameter and a production parameter of the sea-buckthorn raw material in the first reactor, determining an adaptive temperature and an enzyme dosage, and controlling the heating power and the stirring rate of the first reactor; based on the acid value deviation between the acid value of the sea-buckthorn raw material in the second reactor and the target value and the alkalinity concentration, generating a control parameter and a flow instruction for controlling the second reactor so as to control the second reactor to operate; the pigment concentration and the adsorbent activity at the next moment are predicted according to the pigment concentration, the adsorbent activity and the second temperature of the sea-buckthorn raw material in the third reactor, and a combination of the adsorbent addition amount and the decoloration time is constructed to control the third reactor. Accurate control and self-adaptive optimization in the production process are achieved, the control precision of a control system in the production process is improved, and the process efficiency and product quality of sea buckthorn fruit oil refining are remarkably improved.

Description

Technical Field

[0001] The present application relates to the technical field of industrial control systems, and in particular to an intelligent control method and system for a sea buckthorn oil refining process. Background Art

[0002] Seabuckthorn oil, rich in bioactive ingredients such as unsaturated fatty acids, vitamin E, and carotenoids, has broad application prospects in food, health supplements, cosmetics, and medicine. With growing consumer demand for natural, functional oils, the seabuckthorn oil industry continues to expand, placing higher demands on refining efficiency, quality control, and resource utilization. To overcome the bottlenecks of traditional processes, intelligent industrial control methods have been introduced in the seabuckthorn oil refining industry, aiming to achieve real-time optimization of process parameters, accurate quality prediction, and efficient resource utilization.

[0003] However, in actual control applications, fixed-parameter proportional, integral and differential (PID) control systems or simple rule bases are difficult to cope with the dynamic changes of the refining process, especially when there are many types and quantities of control equipment in the production system. This leads to low control accuracy and high control costs, which in turn causes the process efficiency and product quality of sea buckthorn oil refining to fail to meet the standards. Summary of the Invention

[0004] The present application provides an intelligent control method and system for the sea buckthorn oil refining process, which can at least to some extent solve the problems of low control efficiency and high control cost of the control system in the sea buckthorn oil refining process.

[0005] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by practice of the present application.

[0006] According to one aspect of the present application, an intelligent control method for a sea buckthorn oil refining process is provided, comprising: obtaining concentration parameters and production parameters of a sea buckthorn raw material in a first reactor through an intelligent sensor, determining an adaptation temperature and enzyme dosage based on a nonlinear relationship between the concentration parameters and the production parameters, and controlling the heating power and stirring rate of the first reactor to match the adaptation temperature and enzyme dosage; obtaining the acid value and alkalinity concentration of the sea buckthorn raw material in a second reactor through an intelligent sensor, and generating control parameters and flow instructions for controlling the second reactor based on the acid value deviation between the acid value and the target value and the alkalinity concentration to control the operation of the second reactor; obtaining the pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in a third reactor through an intelligent sensor to predict the pigment concentration and adsorbent activity at the next moment, and constructing a combination of adsorbent addition amount and decolorization time to control the third reactor.

[0007] In the present application, based on the above scheme, the concentration parameters include the initial phospholipid concentration and free fatty acid concentration of the sea buckthorn raw material, and the production parameters include the current first temperature of the first reactor.

[0008] In the present application, based on the aforementioned scheme, the adaptation temperature and enzyme dosage are determined based on the nonlinear relationship between the concentration parameters and the production parameters, and the heating power and stirring rate of the first reactor are controlled to match the adaptation temperature and enzyme dosage, including: calculating the adaptation temperature through a nonlinear function according to the initial phospholipid concentration of the sea buckthorn raw material; the adaptation temperature is used to provide an enzyme living environment; the enzyme dosage is determined according to the nonlinear relationship between the initial phospholipid concentration and the first temperature; according to the fuzzy adaptive control method, the heating power and stirring rate of the first reactor are controlled so that the real-time temperature of the first reactor reaches the adaptation temperature and the enzyme activity matches the enzyme dosage.

[0009] In the present application, based on the aforementioned scheme, the control parameters and flow instructions for controlling the second reactor are generated based on the acid value deviation between the acid value and the target value and the alkalinity concentration to control the operation of the second reactor, including: determining the state parameters of the sea buckthorn raw material based on the acid value deviation between the acid value and the target value; inputting the state parameters into a preset fuzzy rule base, outputting the control mode to which the current working condition belongs, and determining the control parameters and flow instructions according to the control mode; controlling the flow of the second reactor through the control parameters and flow instructions; wherein the second reactor includes a deacidification reaction tank and an alkali solution pump.

[0010] In the present application, based on the above-mentioned scheme, the pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in the third reactor are obtained by the intelligent sensor to predict the pigment concentration and adsorbent activity at the next moment, and construct a combination of adsorbent addition amount and decolorization time to control the third reactor, including: obtaining the pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in the third reactor through the intelligent sensor; the third reactor includes a decolorization reaction tank; based on the pigment concentration, adsorbent activity and second temperature, predicting the pigment concentration and adsorbent activity at the next moment; based on the pigment concentration and adsorbent activity at the next moment, generating a combination of adsorbent addition amount and decolorization time to control the third reactor.

[0011] In the present application, based on the aforementioned scheme, the pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in the third reactor are obtained by the intelligent sensor to predict the pigment concentration and adsorbent activity at the next moment, and construct a combination of adsorbent addition amount and decolorization time to control the third reactor, and it also includes: obtaining the cost information of the adsorbent, obtaining the pigment residual deviation between the actual concentration of the pigment and the target value; determining the objective function based on the cost information and the pigment residual deviation; solving the cost information and pigment residual deviation when the objective function is minimized, as the target cost and target residual information respectively; generating production control information based on the target cost and target residual information.

[0012] In the present application, based on the aforementioned scheme, the pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in the third reactor are obtained by the intelligent sensor to predict the pigment concentration and adsorbent activity at the next moment, and construct a combination of adsorbent addition amount and decolorization time to control the third reactor, and also includes: displaying the data collected by the intelligent sensor in the production process on the system dashboard.

[0013] According to one aspect of the present application, an intelligent control system for a seabuckthorn fruit oil refining process is provided, comprising:

[0014] a first control unit, configured to obtain concentration parameters and production parameters of the sea buckthorn raw material in the first reactor through an intelligent sensor, determine an adaptation temperature and an enzyme dosage based on a nonlinear relationship between the concentration parameters and the production parameters, and control a heating power and a stirring rate of the first reactor to match the adaptation temperature and enzyme dosage;

[0015] a second control unit, configured to obtain the acid value and alkalinity concentration of the sea buckthorn raw material in the second reactor through an intelligent sensor, and generate control parameters and flow instructions for controlling the second reactor based on the acid value deviation from a target value and the alkalinity concentration, so as to control the operation of the second reactor;

[0016] The third control unit is used to obtain the pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in the third reactor through the intelligent sensor to predict the pigment concentration and adsorbent activity at the next moment, and construct a combination of adsorbent addition amount and decolorization time to control the third reactor.

[0017] According to one aspect of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the intelligent control method for the sea buckthorn fruit oil refining process as described in the above embodiment is implemented.

[0018] According to one aspect of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the intelligent control method for the sea buckthorn oil refining process as described in the above embodiments.

[0019] According to one aspect of the present application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to implement the intelligent control method for a sea buckthorn fruit oil refining process provided in the various optional implementations described above.

[0020] In the technical solution of this application, the temperature and enzyme dosage are dynamically adjusted based on a nonlinear relationship during the pretreatment stage to ensure efficient degumming while retaining nutrients. Fuzzy control is used in the deacidification stage to neutralize free fatty acids and avoid overtreatment. In the decolorization stage, a predictive model is used to intelligently match the adsorbent dosage with the decolorization time to achieve optimal resource allocation. This achieves precise control and adaptive optimization of the production process, improves the control accuracy of the control system during the production process, reduces nutritional losses and resource costs, provides reliable technical support for the production of high-quality sea buckthorn oil, and significantly improves the process efficiency and product quality of sea buckthorn oil refining.

[0021] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0023] Figure 1 The flowchart of the intelligent control method of the sea buckthorn fruit oil refining process in one embodiment of the present application is schematically shown.

[0024] Figure 2 A flow chart for controlling the first reactor in one embodiment of the present application is schematically shown.

[0025] Figure 3 The following schematically shows a schematic diagram of an intelligent control system for the sea buckthorn oil refining process in one embodiment of the present application.

[0026] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0027] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0028] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner.In the following description, many specific details are provided so as to provide a full understanding of the embodiments of the present application. However, it will be appreciated by those skilled in the art that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps etc. can be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0029] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0030] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0031] The implementation details of the technical solution of this application are described in detail below:

[0032] Figure 1 The flowchart of the intelligent control method of the sea buckthorn fruit oil refining process according to one embodiment of the present application is shown. Figure 1 As shown, the intelligent control method for the sea buckthorn fruit oil refining process includes at least steps S110 to S130, which are described in detail as follows:

[0033] In step S110, the concentration parameters and production parameters of the sea buckthorn raw material in the first reactor are obtained through an intelligent sensor, and the adaptation temperature and enzyme dosage are determined based on the nonlinear relationship between the concentration parameters and the production parameters, and the heating power and stirring rate of the first reactor are controlled to match the adaptation temperature and enzyme dosage.

[0034] Through the distributed intelligent sensor network deployed in the first reactor, such as near-infrared spectrometers, conductivity sensors and pressure-temperature composite probes, the concentration parameters and production parameters of sea buckthorn raw materials are synchronously collected at a preset sampling period. The concentration parameters include soluble solid content and enzyme reaction substrate concentration gradient, and the production parameters include current temperature field distribution, fluid shear force, and pH dynamic curve.

[0035] After preprocessing by edge computing nodes, the collected multimodal data is fed into a nonlinear relationship modeling module based on a hybrid neural network. This module uses a convolutional neural network to extract spatial features and a long-short-term memory network to capture temporal dependencies. This module fuses multi-sensor data through an attention mechanism to dynamically decouple the complex coupling relationships between concentration parameters. Control instructions are generated using the real-time updated model output (the optimal adaptation temperature and enzyme dosage under the current operating conditions). Model predictive control is used to decompose the temperature target into a duty cycle sequence for the heating element. The variable frequency drive parameters of the agitator blades are also optimized to ensure that the enzymatic reaction proceeds under a uniform temperature field and shear rate in both time and space.

[0036] In one embodiment of the present application, the concentration parameters include the initial phospholipid concentration and free fatty acid concentration of the sea buckthorn raw material, and the production parameters include the current first temperature of the first reactor.

[0037] like Figure 2 As shown, in one embodiment of the present application, based on the nonlinear relationship between the concentration parameter and the production parameter, determining the adaptation temperature and enzyme dosage, and controlling the heating power and stirring rate of the first reactor to match the adaptation temperature and enzyme dosage, comprising:

[0038] S210, calculating an adaptation temperature using a nonlinear function according to the initial phospholipid concentration of the seabuckthorn raw material; the adaptation temperature is used to provide an enzyme survival environment;

[0039] S220, determining an enzyme dosage according to a nonlinear relationship between the initial phospholipid concentration of the seabuckthorn raw material and the first temperature;

[0040] S230 , controlling the heating power and stirring rate of the first reactor according to the fuzzy adaptive control method so that the real-time temperature of the first reactor reaches the adaptation temperature and the enzyme activity matches the enzyme dosage.

[0041] In one embodiment of the present application, the adaptation temperature T is calculated by a nonlinear function according to the initial phospholipid concentration of the seabuckthorn raw material. opt for:

[0042]

[0043] Here, 45°C represents the optimal temperature reference value for phospholipase, ensuring that the enzyme activity is in the high-efficiency range; tanh(·) represents the hyperbolic tangent function, which is used to smoothly adjust temperature changes; and PL0 represents the initial phospholipid concentration.

[0044] Traditional production methods use a fixed temperature. In this example, a suitable temperature is calculated to provide a viable environment for the enzyme. The optimal reaction temperature is dynamically calculated based on the initial phospholipid concentration. When the phospholipid concentration is high, the temperature is increased to accelerate the reaction; when the concentration is low, the temperature is maintained at a lower level to minimize nutrient loss. By adjusting the heating power of the reactor in real time and dynamically optimizing the temperature, the optimal temperature is maintained, resulting in a 15% increase in vitamin retention.

[0045] Optionally, in this embodiment, the temperature is increased to accelerate the reaction at high phospholipid concentrations, while the temperature is decreased to protect nutrients at low phospholipid concentrations. The temperature adjustment range is based on the optimal activity range of the enzyme, and a nonlinear function is used to smoothly transition to avoid sudden temperature changes that affect reaction stability.

[0046] In one embodiment of the present application, the enzyme dosage E is determined based on the nonlinear relationship between the initial phospholipid concentration of the seabuckthorn raw material and the first temperature. dose for:

[0047]

[0048] Wherein, T1 represents the first temperature; the exponent 1.2 is obtained by experimental fitting, reflecting that high concentration of phospholipids requires excessive enzyme to overcome the diffusion resistance.

[0049] As can be seen above, as the first temperature increases, the enzyme dosage decreases. This process dynamically calculates the required enzyme dosage based on the phospholipid concentration and current temperature. By controlling the flow rate of the enzyme pump, enzyme addition is precise. Higher phospholipid concentrations require greater enzyme dosage. At higher temperatures, enzyme activity increases, so the enzyme dosage can be appropriately reduced.

[0050] In practical applications, enzyme dosage must balance reaction efficiency and cost. This protocol uses experimental data fitting to establish the relationship between enzyme dosage, concentration, and temperature. The enzyme dosage requirement increases superlinearly with increasing phospholipid concentration. As the temperature rises, the catalytic efficiency of a single enzyme molecule increases, allowing enzyme dosage to be reduced to lower costs.

[0051] In one embodiment of the present application, after obtaining the video temperature and enzyme dosage, the heating power and stirring rate of the first reactor are controlled using a fuzzy adaptive control method so that the real-time temperature of the first reactor reaches the adaptation temperature and the enzyme activity matches the enzyme dosage. Specifically, the reactor temperature is adjusted to the adaptation temperature, and the enzyme addition amount in the enzyme solution pump flow rate is controlled to be the enzyme dosage.

[0052] In addition, during the operation of the first reactor, when the effective enzyme activity in the enzyme dosage decreases, the phospholipid degradation rate v can be predicted based on the effective enzyme activity in the enzyme dosage and the free fatty acid concentration as follows:

[0053]

[0054] Among them, V max represents the theoretical value of the maximum phospholipid degradation rate, β represents the enzyme sensitivity coefficient to temperature, E represents the effective enzyme activity in the enzyme dosage; [FFA] represents the free fatty acid concentration, K m represents the inhibition constant of free fatty acids on enzyme activity, K i represents the regulating factor of free fatty acid concentration, and PL represents the real-time phospholipid concentration.

[0055] After determining the phospholipid degradation rate, the control parameters are dynamically modified to maintain the phospholipid removal rate despite fluctuations in free fatty acid concentration. Alternatively, a layered control architecture can be employed. The base layer sends heating power commands to the power module via industrial Ethernet. The enhanced layer uses a sliding mode control algorithm to compensate for temperature overshoot caused by the reactor's thermal capacity nonlinearity. Fuzzy PID control is also used to adjust the stirring motor's torque output to maintain the target shear rate.

[0056] The control system optionally includes multi-level safety constraints. If a concentration parameter suddenly changes, causing the enzyme dosage requirement to exceed a threshold, a parameter softening mechanism is triggered. Using a quadratic programming algorithm, the temperature and enzyme dosage are reallocated while maintaining minimum enzymatic efficiency. If a sensor fails, a virtual measurement value is generated based on historical data, and a model switching protocol is activated to invoke a backup control strategy. All executed actions are timestamped and stored in a blockchain node for subsequent process traceability and iterative model optimization.

[0057] Fuzzy logic algorithms dynamically adjust control parameters such as heating power, enzyme pump flow rate, and stirring rate to correct for the effects of environmental fluctuations on the reaction in real time, ensuring that the temperature, enzyme concentration, and mixing efficiency in the reaction tank are always at optimal levels.

[0058] In step S120, the acid value and alkalinity concentration of the sea buckthorn raw material in the second reactor are obtained through an intelligent sensor, and based on the acid value deviation between the acid value and the target value and the alkalinity concentration, control parameters and flow instructions for controlling the second reactor are generated to control the operation of the second reactor.

[0059] The acid value and alkalinity concentration of the seabuckthorn raw material are synchronously collected at a preset sampling frequency through an intelligent sensor array deployed in the second reactor, including an online pH electrode, a conductivity sensor and an ion-selective electrode. The acid value of the seabuckthorn raw material is converted into milligrams of KOH / gram of oil in real time by potentiometric titration, and the alkalinity concentration may include the equivalent concentration of NaOH / KOH).

[0060] After the collected data is de-noised using a digital filtering algorithm, it is input into a hybrid control model based on dynamic deviation compensation. The model first calculates the deviation between the current acid value and the preset target value, and combines it with the alkalinity concentration data to construct a two-variable control space for the reaction buffering capacity index through support vector regression mapping. A reinforcement learning framework is used to search for the optimal control strategy in historical operating data, dynamically generating alkali solution flow adjustment instructions (based on a proportional-integral-differential-feedforward composite control algorithm) and reactor residence time parameters (by adjusting the agitator speed to optimize mixing efficiency). At the same time, process safety constraints (such as the pH mutation rate threshold) are embedded to prevent local over-alkalization.

[0061] In one embodiment of the present application, based on the acid value deviation between the acid value and the target value and the alkalinity concentration, generating control parameters and flow instructions for controlling the second reactor to control the operation of the second reactor includes:

[0062] determining a state parameter of the seabuckthorn raw material based on an acid value deviation between the acid value and a target value;

[0063] Input the state parameters into a preset fuzzy rule library, output the control mode to which the current working condition belongs, and determine the control parameters and flow instructions according to the control mode;

[0064] The flow rate of the second reactor is controlled by the control parameters and the flow rate instruction; wherein the second reactor includes a deacidification reaction tank and an alkali solution pump.

[0065] In one embodiment of the present application, the difference between the current acid value and the target value is first determined as the acid value deviation, which is used to reflect the deviation in the degree of deacidification. The trend of the acid value deviation over time is used to determine whether the deviation is expanding or contracting. The alkali solution concentration, which may include the concentration of the sodium hydroxide solution, directly affects the efficiency of the neutralization reaction.

[0066] Optionally, the second reactor in this embodiment includes a deacidification reaction tank or an alkali solution pump.

[0067] Then, based on the acid value deviation between the acid value and the target value, the state parameter μ(E) of the sea buckthorn raw material is determined as follows:

[0068]

[0069] Wherein, α represents the slope of the acid price deviation within the preset period, E represents the mean of the acid price deviation within the preset period, μ and σ represent the mean and standard deviation of the Gaussian distribution of the acid price within the preset period, respectively, and π represents pi.

[0070] The state parameters obtained in this embodiment are used to quantify the degree of fuzziness of the input. After the state parameters are calculated, they are input into a preset fuzzy rule base, triggering matching rules to determine which control mode the current operating condition belongs to, such as whether the acid price is high and rising rapidly, or the acid price is close to the target but fluctuating. The control mode corresponding to the current operating condition is output, and control parameters and flow instructions are determined based on this control mode. The flow rate of the second reactor is controlled using these control parameters and flow instructions.

[0071] Specifically, the controller's proportional coefficient and integral time are dynamically adjusted. During the proportional coefficient correction process, if the acid value deviation is large, the proportional effect is enhanced for a faster response; if the deviation is small, the proportional effect is weakened to avoid overshoot. Furthermore, during the integral time correction process, if the deviation persists for a long time, the integral time is shortened to accelerate the elimination of steady-state errors; if the system is stable, the integral time is extended to reduce oscillations.

[0072] In step S130, the pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in the third reactor are obtained by the intelligent sensor to predict the pigment concentration and adsorbent activity at the next moment, and a combination of adsorbent addition amount and decolorization time is constructed to control the third reactor.

[0073] In one embodiment of the present application, an intelligent sensor network is deployed in the third reactor, including a hyperspectral imager, an electrochemical activity sensor and a distributed temperature array, to synchronously collect the pigment concentration (which can be obtained through multi-channel spectral decoupling), adsorbent activity (based on the specific surface area attenuation rate and pore structure parameters) and the second temperature (three-dimensional temperature field distribution data) of the sea buckthorn raw material at a preset sampling frequency.

[0074] After the collected data is reduced in dimension by the compressed sensing algorithm, it is input into a hybrid prediction model based on the spatiotemporal graph neural network. The model uses the spatial attention mechanism to extract the interactive features of pigment, adsorbent and temperature in the reactor, and combines it with the LSTM timing module to predict the pigment concentration and adsorbent activity at the next moment (for example, 10 seconds later).

[0075] In one embodiment of the present application, the pigment concentration, adsorbent activity, and second temperature of the sea buckthorn raw material in the third reactor are obtained by an intelligent sensor to predict the pigment concentration and adsorbent activity at the next moment, and to construct a combination of adsorbent addition amount and decolorization time to control the third reactor, including:

[0076] The pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in the third reactor are obtained by an intelligent sensor; the third reactor includes a decolorization reaction tank;

[0077] predicting the pigment concentration and adsorbent activity at a next moment based on the pigment concentration, adsorbent activity, and the second temperature;

[0078] Based on the adsorbent activity and the pigment concentration at the next moment, a combination of adsorbent addition amount and decolorization time is generated to control the third reactor.

[0079] In one embodiment of the present application, the pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in the third reactor are obtained by an intelligent sensor, and the third reactor includes a decolorization reaction tank.

[0080] Specifically, the pigment concentration includes the current concentration of pigments in the sea buckthorn raw material or sea buckthorn fruit oil, including pigments such as carotenoids and chlorophyll. The adsorbent activity indicates the effective activity of the adsorbent (e.g., activated clay), which decays over time. The second temperature represents the real-time temperature of the decolorization reaction tank, which affects the adsorption rate. By monitoring the temperature of the decolorization reaction tank in real time, temperature changes can affect adsorption efficiency and adsorbent life.

[0081] Predict the pigment concentration at the next moment based on the pigment concentration, adsorbent activity and the second temperature and adsorbent activity They are:

[0082]

[0083] in, represents the pigment concentration at the current moment, k1 represents the reaction rate constant, represents the adsorbent activity at the current moment, and Δt represents the time step.

[0084] k2 represents the activity attenuation coefficient, T k Indicates the second temperature.

[0085] y k Represents the observed value, such as the pigment concentration measured by the sensor; H represents the preset combination coefficient, x k represents the current combination of pigment concentration and adsorbent activity, v k represents the observation noise.

[0086] In the above calculations, the pigment degradation rate is proportional to the current concentration, adsorbent activity, and contact time. The activity decay rate is affected by both pigment concentration and temperature. High temperatures accelerate activity loss, and high pigment concentrations increase adsorbent loading.

[0087] Optionally, if the activity of the adsorbent decreases due to long-term use, the amount of adsorbent is dynamically adjusted to compensate for the activity loss; if the temperature increase accelerates the adsorption reaction, the decolorization time is shortened to avoid overheating.

[0088] Alternatively, if the pigment concentration is high, increase the amount of adsorbent and extend the reaction time to ensure complete decolorization. If the adsorbent activity is low but the temperature is suitable, increase the amount of adsorbent rather than extend the reaction time.

[0089] Optionally, based on the generated decision, the adsorbent dosing device flow rate is automatically adjusted and a decolorization countdown is set for the reaction tank. The decolorization results are also monitored in real time. If the target pigment residue is not reached, the system dynamically adjusts the subsequent steps.

[0090] This process, by fusing sensor data with model predictions, dynamically corrects estimates of pigment concentration and adsorbent activity, determining the next-moment pigment concentration and adsorbent activity. This generates a combination of adsorbent addition and decolorization time to control the third reactor. By precisely sensing changes in pigment concentration and adsorbent activity, the lag inherent in traditional methods is avoided. This not only improves the decolorization efficiency and quality stability of sea buckthorn oil, but also significantly reduces production costs, providing reliable support for the large-scale production of high-quality refined oil.

[0091] In one embodiment of the present application, after the pigment concentration, adsorbent activity, and second temperature of the sea buckthorn raw material in the third reactor are obtained by the intelligent sensor to predict the pigment concentration and adsorbent activity at the next moment, and to construct a combination of adsorbent addition amount and decolorization time to control the third reactor, the method further includes:

[0092] Obtain the cost information of the adsorbent and the residual deviation of the pigment between the actual concentration of the pigment and the target value;

[0093] determining an objective function based on the cost information and the pigment residue deviation;

[0094] Solving the cost information and pigment residue deviation when the objective function is minimized, and using them as target cost and target residue information respectively;

[0095] Production control information is generated based on the target cost and target residual information.

[0096] Through the enterprise resource planning system interface, real-time data on the adsorbent's purchase price, inventory loss rate, and transportation cost are obtained. The actual pigment concentration is extracted from the online hyperspectral sensor in the third reactor and compared with a preset target value to generate the pigment residual deviation. This cost information and residual deviation are mapped into a multi-objective optimization framework, constructing an objective function with the adsorbent processing cost per unit mass and the variance of the pigment residual as its core. The cost term is linked to the adsorbent batch price fluctuation through a dynamic weighting mechanism, while the deviation term incorporates a time decay factor to suppress noise interference from historical data. A distributed parallel computing framework is used to run a genetic algorithm on a cluster, enabling rapid population iteration. The minimum value of the cost and residual deviation is extracted as the target cost and target residual information, while maintaining a flexible decision set containing a preset number of suboptimal solutions. Finally, the target residual information is converted into the pulse frequency parameter of the adsorbent metering pump (coarsely adjusted using a fuzzy rule library) and a dynamic threshold for the reactor residence time (fine-tuned using a reinforcement learning strategy). The target cost data is fed back to the supply chain management system to trigger adjustments to the adsorbent procurement strategy, forming a closed loop from cost constraints to process optimization.

[0097] In one embodiment of the present application, the cost information of the adsorbent is obtained, and the residual pigment deviation between the actual concentration of the pigment and the target value is obtained. The cost information includes the adsorbent cost, which is proportional to the amount added, and the residual pigment deviation represents the difference between the actual concentration of the pigment and the target value.

[0098] Determine the objective function M(C) based on the cost information and the pigment residual deviation ads ,ΔY) is:

[0099]

[0100] Among them, C ads represents cost information, ΔY represents the residual pigment deviation, t represents the reaction time, T represents the total reaction time, and γ represents the penalty factor.

[0101] After generating the objective function, the cost information and the residual pigment deviation at the minimum of the objective function are calculated and used as the target cost and target residual information, respectively. Production control information is then generated based on the target cost and target residual information. This process improves the quality stability and production economics of seabuckthorn oil decolorization, providing seabuckthorn oil with low pigment residue and high activity for the subsequent deodorization process.

[0102] The data collected by the intelligent sensors in the production process are displayed on the system dashboard. These data may include the concentration parameters and production parameters of sea buckthorn raw materials, the acid value and alkalinity concentration of sea buckthorn raw materials, as well as the pigment concentration, adsorbent activity and second temperature of sea buckthorn raw materials.

[0103] The Industrial Internet of Things (IIoT) gateway receives multi-source, heterogeneous data streams collected by intelligent sensors on the production line in real time. Edge computing nodes clean the data, remove noise and outliers, align timestamps, and standardize units before storing the structured data in a time-series database. The system's dashboard engine dynamically calls data service interfaces based on a microservices architecture and pushes data via message queues. The front-end utilizes a visual component library to map sensor data into dynamic dashboards (displaying key indicators such as pigment concentration and adsorbent activity in real time), 3D heat maps (showing the reactor temperature distribution), and an abnormal event timeline (marking warning records of deviations exceeding limits).

[0104] The integrated intelligent analysis module allows users to switch data dimensions (e.g., filter by batch or time period) through drag-and-drop operations, trigger root cause analysis algorithms (automatically linking historical operating data), and generate customized reports. Interactive commands are fed back to the backend via a two-way communication protocol, driving adaptive adjustments to the data sampling frequency (e.g., down to milliseconds in abnormal operating conditions) and dynamic reorganization of dashboard layouts, ultimately forming a visual hub for transparent production data and intelligent decision support.

[0105] In the above process, intelligent sensors are used to obtain the concentration parameters and production parameters of the sea buckthorn raw material in the first reactor. Based on the nonlinear relationship between the concentration parameters and production parameters, the adaptive temperature and enzyme dosage are determined, and the heating power and stirring rate of the first reactor are controlled to match the adaptive temperature and enzyme dosage. Intelligent sensors are also used to obtain the acid value and alkalinity concentration of the sea buckthorn raw material in the second reactor. Based on the acid value deviation from the target value and the alkalinity concentration, control parameters and flow instructions for controlling the second reactor are generated to control the operation of the second reactor. The pigment concentration, adsorbent activity, and second temperature of the sea buckthorn raw material in the third reactor are obtained by intelligent sensors to predict the pigment concentration and adsorbent activity at the next moment, and a combination of adsorbent addition amount and decolorization time is constructed to control the third reactor. In the pretreatment stage, the above process dynamically adjusts the temperature and enzyme dosage based on the nonlinear relationship to ensure efficient degumming while retaining nutrients. Fuzzy control is used in the deacidification stage to neutralize free fatty acids and avoid overtreatment. In the decolorization stage, a prediction model is used to intelligently match the adsorbent dosage and decolorization time to achieve optimal resource allocation. It achieves precise control and adaptive optimization of the production process, improves the control accuracy of the control system in the production process, reduces nutritional loss and resource costs, provides reliable technical support for high-quality sea buckthorn oil production, and significantly improves the process efficiency and product quality of sea buckthorn fruit oil refining.

[0106] The following describes an embodiment of a device of the present application, which can be used to implement the intelligent control method for the sea buckthorn oil refining process described in the aforementioned embodiments of the present application. It is understood that the device can be a computer program (including program code) running on a computer device, such as application software; the device can be used to perform the corresponding steps of the method provided in the embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the aforementioned embodiment of the intelligent control method for the sea buckthorn oil refining process of the present application.

[0107] Figure 3 A block diagram of an intelligent control system for a sea buckthorn oil refining process according to an embodiment of the present application is shown.

[0108] Reference Figure 3 As shown, the intelligent control system for the sea buckthorn fruit oil refining process according to one embodiment of the present application includes:

[0109] A first control unit 310 is configured to obtain concentration parameters and production parameters of the sea buckthorn raw material in the first reactor through an intelligent sensor, determine an adaptation temperature and enzyme dosage based on a nonlinear relationship between the concentration parameters and the production parameters, and control the heating power and stirring rate of the first reactor to match the adaptation temperature and enzyme dosage;

[0110] a second control unit 320 for obtaining the acid value and alkalinity concentration of the sea buckthorn raw material in the second reactor through an intelligent sensor, and generating control parameters and flow instructions for controlling the second reactor based on the acid value deviation from the target value and the alkalinity concentration, so as to control the operation of the second reactor;

[0111] The third control unit 330 is used to obtain the pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in the third reactor through the intelligent sensor to predict the pigment concentration and adsorbent activity at the next moment, and construct a combination of adsorbent addition amount and decolorization time to control the third reactor.

[0112] In the present application, based on the above scheme, the concentration parameters include the initial phospholipid concentration and free fatty acid concentration of the sea buckthorn raw material, and the production parameters include the current first temperature of the first reactor.

[0113] In the present application, based on the aforementioned scheme, the adaptation temperature and enzyme dosage are determined based on the nonlinear relationship between the concentration parameters and the production parameters, and the heating power and stirring rate of the first reactor are controlled to match the adaptation temperature and enzyme dosage, including: calculating the adaptation temperature through a nonlinear function according to the initial phospholipid concentration of the sea buckthorn raw material; the adaptation temperature is used to provide an enzyme living environment; the enzyme dosage is determined according to the nonlinear relationship between the initial phospholipid concentration and the first temperature; according to the fuzzy adaptive control method, the heating power and stirring rate of the first reactor are controlled so that the real-time temperature of the first reactor reaches the adaptation temperature and the enzyme activity matches the enzyme dosage.

[0114] In the present application, based on the aforementioned scheme, the control parameters and flow instructions for controlling the second reactor are generated based on the acid value deviation between the acid value and the target value and the alkalinity concentration to control the operation of the second reactor, including: determining the state parameters of the sea buckthorn raw material based on the acid value deviation between the acid value and the target value; inputting the state parameters into a preset fuzzy rule base, outputting the control mode to which the current working condition belongs, and determining the control parameters and flow instructions according to the control mode; controlling the flow of the second reactor through the control parameters and flow instructions; wherein the second reactor includes a deacidification reaction tank and an alkali solution pump.

[0115] In the present application, based on the above-mentioned scheme, the pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in the third reactor are obtained by the intelligent sensor to predict the pigment concentration and adsorbent activity at the next moment, and construct a combination of adsorbent addition amount and decolorization time to control the third reactor, including: obtaining the pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in the third reactor through the intelligent sensor; the third reactor includes a decolorization reaction tank; based on the pigment concentration, adsorbent activity and second temperature, predicting the pigment concentration and adsorbent activity at the next moment; based on the pigment concentration and adsorbent activity at the next moment, generating a combination of adsorbent addition amount and decolorization time to control the third reactor.

[0116] In the present application, based on the aforementioned scheme, the pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in the third reactor are obtained by the intelligent sensor to predict the pigment concentration and adsorbent activity at the next moment, and construct a combination of adsorbent addition amount and decolorization time to control the third reactor, and it also includes: obtaining the cost information of the adsorbent, obtaining the pigment residual deviation between the actual concentration of the pigment and the target value; determining the objective function based on the cost information and the pigment residual deviation; solving the cost information and pigment residual deviation when the objective function is minimized, as the target cost and target residual information respectively; generating production control information based on the target cost and target residual information.

[0117] In the present application, based on the aforementioned scheme, the pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in the third reactor are obtained by the intelligent sensor to predict the pigment concentration and adsorbent activity at the next moment, and construct a combination of adsorbent addition amount and decolorization time to control the third reactor, and also includes: displaying the data collected by the intelligent sensor in the production process on the system dashboard.

[0118] In the above process, intelligent sensors are used to obtain the concentration parameters and production parameters of the sea buckthorn raw material in the first reactor. Based on the nonlinear relationship between the concentration parameters and production parameters, the adaptive temperature and enzyme dosage are determined, and the heating power and stirring rate of the first reactor are controlled to match the adaptive temperature and enzyme dosage. Intelligent sensors are also used to obtain the acid value and alkalinity concentration of the sea buckthorn raw material in the second reactor. Based on the acid value deviation from the target value and the alkalinity concentration, control parameters and flow instructions for controlling the second reactor are generated to control the operation of the second reactor. The pigment concentration, adsorbent activity, and second temperature of the sea buckthorn raw material in the third reactor are obtained by intelligent sensors to predict the pigment concentration and adsorbent activity at the next moment, and a combination of adsorbent addition amount and decolorization time is constructed to control the third reactor. In the pretreatment stage, the above process dynamically adjusts the temperature and enzyme dosage based on the nonlinear relationship to ensure efficient degumming while retaining nutrients. Fuzzy control is used in the deacidification stage to neutralize free fatty acids and avoid overtreatment. In the decolorization stage, a prediction model is used to intelligently match the adsorbent dosage and decolorization time to achieve optimal resource allocation. It achieves precise control and adaptive optimization of the production process, improves the control accuracy of the control system in the production process, reduces nutritional loss and resource costs, provides reliable technical support for high-quality sea buckthorn oil production, and significantly improves the process efficiency and product quality of sea buckthorn fruit oil refining.

[0119] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application is shown.

[0120] It should be noted that the computer system of the electronic device in this embodiment is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0121] In this embodiment, the computer system includes a central processing unit (CPU) 401, which can execute various appropriate actions and processes based on programs stored in a read-only memory (ROM) 402 or programs loaded from a storage unit 408 into a random access memory (RAM) 403. For example, this can execute the intelligent control method for the seabuckthorn oil refining process described in the above embodiment. The RAM 403 also stores various programs and data required for system operation. The CPU 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output interface 405 is also connected to the bus 404.

[0122] The following components are connected to the input / output interface 405: an input section 406 including a keyboard, a mouse, and the like; an output section 407 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 408 including a hard disk and the like; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the input / output interface 405 as needed. Removable media 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like, is installed in the drive 410 as needed so that computer programs read therefrom can be installed into the storage section 408 as needed.

[0123] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product that includes a computer program carried on a computer-readable medium, the computer program including a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 409 and / or installed from a removable medium 411. When the computer program is executed by the central processing unit 401, the various functions defined in the system of the present application are performed.

[0124] It should be noted that the computer-readable medium shown in the embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable computer program. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0125] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. Among them, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0126] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. In some cases, the names of these units do not constitute limitations on the units themselves.

[0127] According to one aspect of the present application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations described above.

[0128] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments, or may exist independently and not be incorporated into the electronic device. The computer-readable medium carries one or more programs, and when executed by the electronic device, the electronic device implements the intelligent control method for the sea buckthorn fruit oil refining process described in the above embodiments.

[0129] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the application, the features and functions of two or more modules or units described above can be concretized in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0130] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0131] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art that are not disclosed herein.

[0132] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. An intelligent control method for seabuckthorn fruit oil refining process, characterized in that: include: obtaining concentration parameters and production parameters of the sea buckthorn raw material in the first reactor through an intelligent sensor, determining an adaptation temperature and an enzyme dosage based on a nonlinear relationship between the concentration parameters and the production parameters, and controlling the heating power and stirring rate of the first reactor to match the adaptation temperature and enzyme dosage; Acquiring the acid value and alkalinity concentration of the sea buckthorn raw material in the second reactor through an intelligent sensor, and generating control parameters and flow instructions for controlling the second reactor based on the acid value deviation from a target value and the alkalinity concentration, so as to control the operation of the second reactor; The pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in the third reactor are obtained by the intelligent sensor to predict the pigment concentration and adsorbent activity at the next moment, and to construct a combination of adsorbent addition amount and decolorization time to control the third reactor.

2. The intelligent control method for seabuckthorn fruit oil refining process according to claim 1, characterized in that: The concentration parameters include the initial phospholipid concentration and free fatty acid concentration of the sea buckthorn raw material, and the production parameters include the current first temperature of the first reactor.

3. The intelligent control method for seabuckthorn fruit oil refining process according to claim 2, characterized in that: The method of determining the adapted temperature and enzyme dosage based on the nonlinear relationship between the concentration parameter and the production parameter, and controlling the heating power and stirring rate of the first reactor to match the adapted temperature and enzyme dosage, comprises: According to the initial phospholipid concentration of the sea buckthorn raw material, the adaptation temperature is calculated by a nonlinear function; the adaptation temperature is used to provide an enzyme survival environment; determining an enzyme dosage according to a nonlinear relationship between the initial phospholipid concentration of the seabuckthorn raw material and the first temperature; According to the fuzzy adaptive control method, the heating power and stirring rate of the first reactor are controlled so that the real-time temperature of the first reactor reaches the adaptation temperature and the activity of the enzyme matches the enzyme dosage.

4. The intelligent control method for seabuckthorn fruit oil refining process according to claim 1, characterized in that: The step of generating control parameters and flow instructions for controlling the second reactor based on the acid value deviation between the acid value and the target value and the alkalinity concentration to control the operation of the second reactor includes: determining a state parameter of the seabuckthorn raw material based on an acid value deviation between the acid value and a target value; Input the state parameters into a preset fuzzy rule library, output the control mode to which the current working condition belongs, and determine the control parameters and flow instructions according to the control mode; The flow rate of the second reactor is controlled by the control parameters and the flow rate instruction; wherein the second reactor includes a deacidification reaction tank and an alkali solution pump.

5. The intelligent control method for seabuckthorn fruit oil refining process according to claim 1, characterized in that: The pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in the third reactor obtained by the intelligent sensor are used to predict the pigment concentration and adsorbent activity at the next moment, and a combination of adsorbent addition amount and decolorization time is constructed to control the third reactor, including: The pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in the third reactor are obtained by an intelligent sensor; the third reactor includes a decolorization reaction tank; predicting the pigment concentration and adsorbent activity at a next moment based on the pigment concentration, adsorbent activity, and the second temperature; Based on the adsorbent activity and the pigment concentration at the next moment, a combination of adsorbent addition amount and decolorization time is generated to control the third reactor.

6. The intelligent control method for seabuckthorn fruit oil refining process according to claim 1, characterized in that: After the pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in the third reactor are obtained by the intelligent sensor to predict the pigment concentration and adsorbent activity at the next moment, and to construct a combination of adsorbent addition amount and decolorization time to control the third reactor, the method further includes: Obtain the cost information of the adsorbent and the residual deviation of the pigment between the actual concentration of the pigment and the target value; determining an objective function based on the cost information and the pigment residue deviation; Solving the cost information and pigment residue deviation when the objective function is minimized, and using them as target cost and target residue information respectively; Production control information is generated based on the target cost and target residual information.

7. The intelligent control method for seabuckthorn fruit oil refining process according to claim 1, characterized in that: After the pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in the third reactor are obtained by the intelligent sensor to predict the pigment concentration and adsorbent activity at the next moment, and to construct a combination of adsorbent addition amount and decolorization time to control the third reactor, the method further includes: The data collected by the smart sensors in the production process are displayed on the system dashboard.

8. An intelligent control system for seabuckthorn oil refining process, characterized in that: include: a first control unit, configured to obtain concentration parameters and production parameters of the sea buckthorn raw material in the first reactor through an intelligent sensor, determine an adaptation temperature and an enzyme dosage based on a nonlinear relationship between the concentration parameters and the production parameters, and control a heating power and a stirring rate of the first reactor to match the adaptation temperature and enzyme dosage; a second control unit, configured to obtain the acid value and alkalinity concentration of the sea buckthorn raw material in the second reactor through an intelligent sensor, and generate control parameters and flow instructions for controlling the second reactor based on the acid value deviation from a target value and the alkalinity concentration, so as to control the operation of the second reactor; The third control unit is used to obtain the pigment concentration, adsorbent activity and second temperature of the sea buckthorn raw material in the third reactor through the intelligent sensor to predict the pigment concentration and adsorbent activity at the next moment, and construct a combination of adsorbent addition amount and decolorization time to control the third reactor.

9. The intelligent control system for seabuckthorn oil refining process according to claim 8, characterized in that: The concentration parameters include the initial phospholipid concentration and free fatty acid concentration of the sea buckthorn raw material, and the production parameters include the current first temperature of the first reactor.

10. The intelligent control system for seabuckthorn oil refining process according to claim 9, characterized in that: The method of determining the adapted temperature and enzyme dosage based on the nonlinear relationship between the concentration parameter and the production parameter, and controlling the heating power and stirring rate of the first reactor to match the adapted temperature and enzyme dosage, comprises: According to the initial phospholipid concentration of the sea buckthorn raw material, the adaptation temperature is calculated by a nonlinear function; the adaptation temperature is used to provide an enzyme survival environment; determining an enzyme dosage according to a nonlinear relationship between the initial phospholipid concentration of the seabuckthorn raw material and the first temperature; According to the fuzzy adaptive control method, the heating power and stirring rate of the first reactor are controlled so that the real-time temperature of the first reactor reaches the adaptation temperature and the activity of the enzyme matches the enzyme dosage.

Images