Vegetable oil processing and conveying control method and system

Abstract

The invention discloses a vegetable oil processing and conveying control method and system, and relates to the technical field of vegetable oil processing.The method comprises the steps that operation parameters of a conveying pipeline are collected in real time, and the operation parameters comprise inlet pressure, outlet pressure, oil temperature, real-time flow and pipe wall vibration data; calculating a real-time pressure difference, a real-time flow resistance coefficient and a characteristic frequency amplitude based on the operation parameters; outputting a quantized blockage risk index R through a preset blockage risk prediction model; comparing the R with a preset risk threshold to determine a risk level; executing a hierarchical active control intervention strategy according to the risk level; the system comprises a conveying pipeline unit, a data acquisition module, a data processing and risk assessment module and a control execution module, early warning and accurate intervention of the blockage risk are achieved, a complete closed loop from monitoring, assessment to control is formed, the safety and reliability of the conveying system are remarkably improved, meanwhile, the quality of product oil is guaranteed, and the production cost is reduced. And the maintenance cost is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of edible oil processing and conveying, in particular to a plant oil processing and conveying control method and system. BACKGROUND

[0002] In the process of plant oil refining, the blockage of conveying pipelines is a long-standing technical problem. In particular, for high-viscosity and easily crystallized oil products such as palm oil and coconut oil, during the conveying stage after the deodorization process and before the storage of finished products, due to the decrease in temperature, the glycerides and waxes in the oil product are prone to precipitate and adhere to the pipe wall, forming deposits, which reduces the flow area of the pipeline and increases the flow resistance, eventually leading to complete blockage. The traditional solution mainly relies on periodic disassembly and cleaning or simple heating treatment, which has problems such as response lag, impact on production continuity, and possible contamination of finished oil products. There is a lack of an intelligent control method that can monitor in real time, accurately predict, and automatically intervene, resulting in low production efficiency, high maintenance costs, and quality and safety risks. Therefore, it is urgent to develop a plant oil conveying control technology that can achieve early warning, accurate assessment, and hierarchical intervention to ensure production safety, improve operational efficiency, and ensure product quality. SUMMARY

[0003] The purpose of the present application is to provide a plant oil processing and conveying control method and system, which solves the technical problems of blockage discovery lag, impact on product quality and production continuity caused by the lack of real-time monitoring and accurate early warning of plant oil conveying pipelines. Through real-time monitoring, intelligent prediction, and hierarchical intervention, early warning and accurate control of the blockage risk of the conveying pipeline are achieved, thereby effectively avoiding production interruption, ensuring the quality of finished oil products, and significantly reducing maintenance costs.

[0004] To achieve the above purpose, the present application realizes the following technical scheme: a plant oil processing and conveying control method, comprising the following steps: Real-time acquisition of the operating parameters of the conveying pipeline, including inlet pressure, outlet pressure, oil temperature, real-time flow rate, and pipe wall vibration data, and calculation of real-time pressure difference, real-time flow resistance coefficient, and characteristic frequency amplitude; Based on the operating parameters, a quantitative blockage risk index R is output through a pre-set blockage risk prediction model, the blockage risk index R is compared with a pre-set risk threshold interval, and the current blockage risk level is determined; According to the blockage risk level, a corresponding hierarchical active control intervention strategy is executed.

[0005] Through multi-parameter fusion monitoring and modelized risk assessment, the accurate quantification of the blockage risk is realized, which provides a scientific basis for hierarchical intervention and overcomes the limitations of traditional single parameter judgment.

[0006] The risk of plugging index R is compared with a preset risk threshold interval to determine the current plugging risk level, specifically: The comprehensive plugging risk index R is compared with R1 and R2: If 0 ≤ R < R1, the risk level is determined to be the first level; If R1 ≤ R < R2, the risk level is determined to be the second level; If R ≥ R2, the risk level is determined to be the third level; Wherein, R1 is a preset first risk threshold, R2 is a preset second risk threshold, and R2 > R1.

[0007] By setting a clear risk threshold interval, a standardized risk level determination standard is established, ensuring the objectivity and consistency of risk determination, and facilitating system automation execution.

[0008] The corresponding hierarchical active control intervention strategy is executed according to the plugging risk level, including: When the risk level is the first level, maintain the current operating state; When the risk level is the second level, execute the first intervention strategy, including increasing the oil temperature and changing the flow rate of the pipeline in a pulse flushing mode; When the risk level is the third level, execute the second intervention strategy, including executing a combination strategy of pulse flushing, process isolation and cleaning and maintenance.

[0009] Through hierarchical intervention strategy design, progressive response from prevention to treatment is realized, avoiding resource waste caused by excessive intervention, and effectively controlling different levels of risk.

[0010] The first intervention strategy is specifically: According to the current oil temperature, the oil temperature is increased to a preset temperature at a preset heating rate, and the flow rate is periodically fluctuated between 110% to 130% of the current flow rate for a first preset time period. The second intervention strategy is specifically: sending a first scheduling signal to the upstream and a second scheduling signal to the downstream to make the current pipeline enter an isolation state; after entering the isolation state, cleaning and maintaining the current pipeline, and increasing the flow rate to the maximum value allowed by the system in a pulse flushing mode for a second preset time period.

[0011] Through the organic combination of temperature control and pulse flushing, a mild and effective physical plugging removal means is provided, effectively solving the initial plugging problem.

[0012] In the second intervention strategy, the current pipeline is cleaned and maintained, specifically: The food-grade cleaning aid is injected at an injection rate of 0.1% to 0.5% of the total volume flow, and the oil flowing through the conveying pipeline during the implementation of the second intervention strategy is guided into a treatment tank at the front end of the refining process for reflux treatment without entering the downstream storage process.

[0013] Through the combination of chemical cleaning and reflux treatment, thorough cleaning in the case of severe blockage is ensured, and the quality safety of finished oil is guaranteed through the isolation reflux mechanism.

[0014] The oil temperature is raised to a preset temperature at a preset heating rate according to the current oil temperature, specifically: according to the thermal sensitivity coefficient of different oils, the heating value is calculated to raise the oil temperature, and the final temperature does not exceed the preset upper limit temperature of the oil.

[0015] Through the introduction of thermal sensitivity coefficient, the individualized temperature control of different oils is realized, which maximizes the risk of thermal damage to heat-sensitive oils while ensuring the effect of cleaning.

[0016] The preset heating rate is dynamically adjusted according to the difference between the current oil temperature and the preset upper limit temperature of the oil: When the difference is greater than a first temperature threshold, a first heating rate is used; When the difference is less than or equal to the first temperature threshold, a second heating rate is used; Wherein, the second heating rate is less than the first heating rate.

[0017] By dynamically adjusting the heating rate, the heating efficiency and control accuracy are considered, which quickly reaches the cleaning temperature and effectively prevents the influence of temperature overshoot on oil quality.

[0018] After executing any intervention strategy, the effect verification and response process is started, specifically: The operating parameters are re-collected and the blockage risk level is determined again; If the risk level has dropped to the first level, the normal operation state is restored; If the risk level has not dropped to the first level, the corresponding operation is performed according to the current level: If it is currently at the second level, the intervention strategy of the next higher level is automatically started; If it is still at the third level, a system alarm is triggered, and a maintenance request signal is generated.

[0019] Through the effect verification and response mechanism, a complete control loop is formed, ensuring the effectiveness of the intervention measures, and intelligently adjusting the subsequent strategy according to the actual effect.

[0020] A vegetable oil processing and conveying control system for executing the above method, comprising: The conveying pipeline unit comprises a main conveying pipeline, an integrated bypass return pipeline and a quick isolation valve group; The data acquisition module comprises a pressure sensor, a temperature sensor, a flow meter and a vibration sensor. The data processing and risk assessment module is used for calculating real-time pressure difference, real-time flow resistance coefficient and characteristic frequency amplitude based on the collected operation parameters, and outputting a comprehensive plugging risk index through a plugging risk prediction model to determine a risk level. The control execution module comprises a temperature control unit, a flow adjustment unit, a system scheduling unit and a cleaning and maintenance unit, and is used for executing corresponding grading active control intervention strategies according to the risk level.

[0021] Through the modular system design, complete functional integration from data acquisition to control execution is realized, and reliable hardware support is provided for implementation of the method.

[0022] The cleaning and maintenance unit comprises a cleaning aid storage tank and a metering pump, which are used for injecting cleaning aids under the third intervention strategy, and guiding flushing oil products to a treatment tank at the front end of a refining process through the integrated bypass return pipeline.

[0023] Through the special cleaning and maintenance unit design, controllability and safety of the chemical cleaning process are ensured, and equipment support is provided for high-quality plugging removal. In summary, the present application has the following beneficial effects: through the organic combination of multi-sensor data fusion, intelligent risk assessment and grading active intervention, a complete vegetable oil conveying pipeline anti-plugging control system is constructed; the system realizes the fundamental change from passive response to active prevention, can accurately early warn and take moderate intervention in the early stage of plugging, and effectively avoids the production stoppage loss caused by serious plugging; through the organic combination of physical and chemical plugging removal means and the strict quality protection mechanism, the plugging removal effect is ensured while the finished oil quality is protected; the whole scheme has the outstanding advantages of accurate early warning, timely response, moderate intervention, safety and reliability, and significantly improves the continuity, stability and economy of the vegetable oil processing process. BRIEF DESCRIPTION OF DRAWINGS

[0024] The drawings described herein are used to provide further understanding of the present application, constitute a part of the present application, the illustrative embodiments of the present application and the description thereof are used to explain the present application, and do not constitute an improper limitation on the present application. In the drawings: Figure 1 is a schematic diagram of the control method principle of the present application. DETAILED DESCRIPTION

[0025] In order to more clearly explain the overall concept of the present application, the following will be described in detail in an exemplary manner with reference to the drawings of the specification.

[0026] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, the present application can be practiced without the specific details. In other instances, well-known methods have not been described in detail in order not to unnecessarily obscure aspects of the present application.

[0027] In addition, in the description of the present application, it needs to be understood that the terms "top", "bottom", "inner", "outer", "axial", "radial", "circumferential" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation of the present application.

[0028] In the present application, unless otherwise explicitly specified and limited, the terms "mounting", "connection", "connecting", "fixing" and the like should be understood in a broad sense, for example, can be fixed connection, can also be detachable connection, or integral; can be mechanical connection, can also be electrical connection, or communication; can be directly connected, or indirectly connected through an intermediate medium; can be the internal communication of two elements or the interaction relationship between two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0029] In the present application, unless otherwise explicitly specified and limited, the first feature is "on" or "under" the second feature, which can be direct contact between the first and second features, or indirect contact between the first and second features through an intermediate medium. In the description of the specification, the description referring to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0030] A vegetable oil processing and conveying control system, the system is deployed at the end of the vegetable oil refining process, specifically in the conveying pipe section after the deodorization process and before the finished oil storage tank, for realizing real-time blockage risk monitoring, evaluation and active intervention control of high-viscosity, easy-crystallization / gelatinization vegetable oil such as palm oil, coconut oil, etc. during conveying. The system is composed of four core modules including: Conveying pipeline unit, data acquisition module, data processing and risk evaluation module and execution control module, each module works cooperatively to form a closed-loop control logic, ensuring safe, continuous and efficient conveying; The conveying pipeline unit is the main target processing unit of the application. After the deodorization process, when the vegetable oil flows through the conveying section, glycerol ester or wax is easily precipitated due to rapid oil temperature drop, resulting in local deposition and blockage, so it needs to be treated. The conveying pipeline unit comprises: The main conveying pipeline is made of food-grade 316L stainless steel, and the inner wall is polished to reduce the adhesion of vegetable oil. The width of the main conveying pipeline depends on the production capacity, and the length depends on the site planning. The integrated bypass return pipe is made of food-grade 316L stainless steel, and the inner wall is polished. The rapid isolation valve group includes an upstream cut-off valve and a downstream cut-off valve. The cleaning aid injection interface is provided with an electronic metering pump. The pulse flushing variable frequency pump and the regulating valve. The online filter is provided with a differential pressure alarm function. The pipeline heating jacket has a temperature control function, and a temperature control unit is installed. Electric heating or steam heating can be used.

[0031] The data acquisition module is configured at the key nodes of the conveying pipeline to collect real-time operation parameters of the conveying pipeline. Specifically as follows: The inlet pressure sensor is located at the outlet side of the deodorization tower to collect inlet pressure data of the conveying pipeline. The inlet pressure sensor can be evenly arranged at multiple positions at the outlet side of the deodorization tower, and the average value is used to determine the inlet pressure data. The outlet pressure sensor is located at the front side of the storage tank inlet to collect outlet pressure data. The outlet pressure sensor can be evenly arranged at multiple positions at the front side of the inlet, and the average value is used to determine the outlet pressure data. The temperature sensor is evenly arranged along the length direction of the conveying pipeline to collect oil temperature. The average value of the temperature sensors is used to determine the oil temperature. The electromagnetic flowmeter is located downstream of the conveying pipeline inlet to collect real-time volume flow data.

[0032] The vibration sensor is evenly arranged on the outer wall of the conveying pipeline, and multiple vibration sensors are arranged to collect pipe wall vibration signals. The inlet pressure sensor, outlet pressure sensor, temperature sensor, electromagnetic flowmeter and vibration sensor are connected to the central controller through an industrial bus. A data processing and risk assessment module is configured to determine a current blockage risk level based on the operating parameters through a preset blockage risk prediction model, which includes a real-time parameter preprocessing unit, a calculation of real-time pressure difference and real-time flow resistance coefficient, a time-frequency analysis of vibration signals, and an extraction of characteristic frequency amplitude A, such as the maximum amplitude of the main frequency. For example, the system will perform a weighted average on multiple amplitude A values calculated by sensors at different positions of the pipeline, and finally output a unified characteristic frequency amplitude A that can represent the vibration state of the entire pipeline. The blockage risk prediction model is a multiple-input single-output (MISO) regression model, such as an XGBoost or lightweight neural network, to improve prediction accuracy. The input variables are real-time pressure difference, real-time flow resistance coefficient, oil temperature, real-time flow rate, and characteristic frequency amplitude A. The output is a comprehensive blockage risk index R. The risk level determination unit presets two threshold values: R1 and R2, for example, R1 = 0.3 and R2 = 0.6, which can be dynamically adjusted according to the type of oil.

[0033] The control execution module is configured to execute corresponding hierarchical active control intervention strategies based on the blockage risk level, which includes the following units: The temperature control unit can be an electric heater or a steam regulating valve, which adjusts the temperature through a PID temperature controller. The flow regulation unit includes a variable frequency delivery pump and a flow closed-loop controller, which supports pulse flushing mode, with flow rate periodically fluctuating between 110% and 130% of the reference value, for example, with a period of 30s, high flow rate for 20s and low flow rate for 10s. The flow rate can be increased to the maximum flow rate designed by the system, such as 120% of the rated flow rate. The system scheduling unit sends a first scheduling signal, such as a "reduction / suspension" signal, to the upstream deodorization process, and a second scheduling signal, such as a switch to backflow instruction, to the downstream storage tank feeding system, triggering pipeline isolation, closing upstream and downstream shut-off valves, and enabling bypass backflow.

[0034] The cleaning and maintenance subsystem includes a food-grade cleaning aid tank and a precision metering pump, with an injection rate of 0.1% to 0.5% vol. The cleaning process includes injecting the aid, starting the maximum flow rate pulse flushing, and continuing for a third preset duration, such as 15-30 minutes, to direct the flushing oil to a pre-refining processing tank, such as a non-product tank or a separation tank, to avoid contamination.

[0035] A vegetable oil processing and conveying control method includes the following steps: Step S10, real-time acquisition of operating parameters of the conveying pipeline, including inlet pressure, outlet pressure, oil temperature, real-time flow rate, and pipe wall vibration data, and calculation of real-time pressure difference, real-time flow resistance coefficient, and characteristic frequency amplitude. Step S20: Based on the operating parameters, output a quantified congestion risk index R through a preset congestion risk prediction model, compare the congestion risk index R with a preset risk threshold range, and determine the current congestion risk level. Step S30: Execute the corresponding graded active control intervention strategy according to the blockage risk level.

[0036] Specifically, the operating parameters of the delivery pipeline are collected in real time, including at least inlet pressure, outlet pressure, oil temperature, and real-time flow rate. Based on the operating parameters, the current congestion risk level is determined by a preset congestion risk prediction model. The congestion risk prediction model is configured to output a quantified congestion risk index R, and the congestion risk index R is compared with a preset risk threshold range to determine the current congestion risk level.

[0037] Calculate the real-time differential pressure and real-time flow resistance coefficient based on the aforementioned operating parameters; The formula for calculating the real-time pressure difference ΔP is ΔP = P in - P out ;P in For the inlet pressure, P out To alleviate export pressure; The formula for calculating the real-time flow resistance coefficient K is: K = ΔP / Q 2 Q represents real-time traffic.

[0038] The real-time acquisition of pipeline operating parameters also includes pipe wall vibration data; the pipe wall vibration data is analyzed to obtain the characteristic frequency amplitude A, and the characteristic frequency amplitude A, together with the real-time pressure difference ΔP and the real-time flow resistance coefficient K, is input into the blockage risk prediction model; the blockage risk prediction model outputs a comprehensive blockage risk index R. Based on the level of congestion risk, implement corresponding tiered proactive control and intervention strategies.

[0039] The step of comparing the congestion risk index R with a preset risk threshold range to determine the current congestion risk level specifically involves: The overall congestion risk index R is compared with R1 and R2: If 0 ≤ R < R1, then the risk level is determined to be Level 1; If R1 ≤ R < R2, then the risk level is determined to be level two; If R ≥ R2, then the risk level is determined to be Level 3; Wherein, R1 is the preset first risk threshold, R2 is the preset second risk threshold, and R2 > R1.

[0040] the executing corresponding hierarchical active control intervention strategy according to the risk level of the blockage, comprising: when the risk level is the first level, maintaining the current running state; when the risk level is the second level, executing a first intervention strategy, comprising increasing the oil temperature and changing the flow rate of the conveying pipeline in a pulse flushing mode; when the risk level is the third level, executing a second intervention strategy, comprising executing a combined strategy of pulse flushing, flow isolation and cleaning and maintenance.

[0041] the first intervention strategy, specifically: according to the current oil temperature, increasing the oil temperature to a preset temperature at a preset temperature increasing rate, periodically fluctuating the flow rate between 110% and 130% of the current flow rate in a preset period, and maintaining the first preset time length; the second intervention strategy specifically comprises: sending a first scheduling signal to the upstream and a second scheduling signal to the downstream, so that the current conveying pipeline enters an isolation state; after entering the isolation state, cleaning and maintaining the current pipeline, and increasing the flow rate to the maximum value allowed by the system in a pulse flushing mode and maintaining the second preset time length.

[0042] In the working condition of the first intervention strategy, the cleaned substances have no substantial negative impact on the quality of the final product oil; the core reason is that the nature of the cleaned substances is "homologous, trace and soluble / dispersible", and in the early stage corresponding to the first intervention strategy and the low risk level, the deposits on the inner wall of the pipeline are mainly saturated fatty acids and waxes, which are crystals separated from the oil itself, and they are part of the oil and not foreign contaminants, and they are homologous substances of vegetable oil. Moreover, at this stage, the deposition is in the early stage, the amount of substances flushed down is small, and the first intervention strategy includes the step of increasing the oil temperature. The increase in temperature will cause these tiny crystals to re-dissolve or be dispersed into extremely fine particles, uniformly dispersed back into the oil, and restore its uniform liquid state, which is soluble and dispersible.

[0043] Moreover, the entire production system also provides the final guarantee: in the vegetable oil refining process, the oil will pass through a precision terminal filter, such as a filter with a precision of 1-5 microns, before entering the finished product tank. Any trace of tiny particles that have not completely dissolved will be effectively captured and removed by this final "checkpoint".

[0044] In summary, through the first intervention strategy, the homologous substances separated from the vegetable oil are subjected to gentle "stirring" in the form of pulse flushing to change the flow rate, and heating, and the separated substances will re-dissolve into the vegetable oil, and the nature of the vegetable oil is not changed, and the system and the final precision filter ensure the purity of the vegetable oil.

[0045] If left unattended until the blockage is serious, the third intervention strategy is triggered, at which point the deposits become stubborn, large in quantity, and may be oxidized, at which point the oil is actually contaminated, which is why the high-level strategy must initiate the "backflow treatment". Therefore, the first intervention strategy is a preventive measure that addresses the problem at its inception, thereby avoiding future real impacts on the oil.

[0046] In the second intervention strategy, the current pipeline is cleaned and maintained, specifically: A food-grade cleaning aid is injected at an injection rate of 0.1% to 0.5% of the total volume flow, and the oil flowing through the delivery pipeline during the execution of the second intervention strategy is directed to a treatment tank at the front end of the refining process for backflow treatment without entering the downstream storage process.

[0047] The oil temperature is raised to a preset temperature at a preset heating rate based on the current oil temperature, specifically: based on the thermal sensitivity coefficient of different oils, the heating value is calculated to raise the oil temperature, and the final temperature does not exceed the preset upper limit temperature of the oil.

[0048] The preset heating rate is dynamically adjusted based on the difference between the current oil temperature and the preset upper limit temperature of the oil: When the difference is greater than a first temperature threshold, a first heating rate is used; When the difference is less than or equal to the first temperature threshold, a second heating rate is used; Wherein, the second heating rate is less than the first heating rate.

[0049] After executing any intervention strategy, the effect verification and response process is started, specifically: The operating parameters are re-collected and the blockage risk level is re-determined; If the risk level has dropped to the first level, the normal operating state is restored; If the risk level has not dropped to the first level, the corresponding operation is performed according to the current level: If the current level is the second level, the next higher level intervention strategy is automatically started; If the current level is still the third level, a system alarm is triggered and a maintenance request signal is generated.

[0050] Specifically, when the vegetable oil is palm oil, the system collects the following data in real time through various sensors: Inlet pressure: P in = 0.28 MPa; Outlet pressure P out = 0.22 MPa; Average oil temperature T = 48 ℃; Real-time volume flow Q = 12 m 3 / h; The pipe wall vibration signal is analyzed by FFT, and the main frequency characteristic frequency amplitude A = 0.85 mm / s 2 .

[0051] Calculate the real-time pressure difference ΔP = P in −P out = 0.28-0.22=0.06 MPa; Calculate the real-time flow resistance coefficient, in order to unify the units, the unit of Q needs to be converted to m 3 / s, Q = 12 m 3 / h = 12 / 3600 = 0.00333 m 3 / s; K = ΔP / Q2 = 0.06*106 / 0.003332≈5.41*10 9 Pa·s 2 / m 6 .

[0052] In one embodiment, the blockage risk prediction model can adopt a look-up table method based on empirical data, as a model simplification scheme, the table is as follows: Specifically, according to the current data, referring to the table, it can be known that: Based on the characteristics of the transported vegetable oil and the historical data analysis, the weight distribution of each parameter is carried out, and the contribution weight of each parameter to the blockage risk is: ΔP weight: w1 = 0.30, the pressure difference directly reflects the flow resistance; K weight: w2 = 0.35, the flow resistance coefficient comprehensively reflects the deposition degree; A weight: w3 = 0.20, vibration reflects the change of structure state; T weight: w4 = 0.10, temperature affects the flowability of oil; Q weight: w5 = 0.05, flow is an auxiliary reference parameter; ∑weight = 1.0; Then calculate the R value: ΔP = 0.06 MPa, falls in the interval of 0.05-0.07, normalized to 0-1: (0.06-0.05) / (0.07-0.05)=0.5; K = 5.41×10 9 , falls in the interval of 5.0-6.0, normalized: (5.41-5.0) / (6.0-5.0)=0.41; A = 0.85 mm / s 2 , falling in the interval 0.8-1.0, normalized: (0.85-0.8) / (1.0-0.8)=0.25; T = 48 ℃, falling in the interval 45-50, normalized: (48-45) / (50-45)=0.6; Q = 12 m 3 / h, falling in the interval 10-14, normalized: (12-10) / (14-10)=0.5; Then the contribution of each parameter to the R value is calculated: R ΔP = 0.70 + 0.5 × (0.75 - 0.70) = 0.725; R K = 0.70 + 0.41 × (0.75 - 0.70) = 0.7205; R A = 0.70 + 0.25 × (0.75 - 0.70) = 0.7125; R T = 0.70 + 0.6 × (0.75 - 0.70) = 0.730; R Q = 0.70 + 0.5 × (0.75 - 0.70) = 0.725; Then the R value is calculated by weighted comprehensive calculation: R = w1×R ΔP + w2×R K + w3×R A + w4×R T + w5×R Q = 0.30×0.725 + 0.35×0.7205 + 0.20×0.7125 + 0.10×0.730 + 0.05×0.725 = 0.2175 + 0.252175 +0.1425 + 0.0730 + 0.03625 = 0.721425; The final determination is: R ≈ 0.72.

[0053] Overall, the plugging risk prediction model adopts a table method to obtain a sub-item R value by linear interpolation of each measured parameter in a preset interval, and then obtains a final risk index by weighted comprehensive calculation according to a predetermined weight.

[0054] In another embodiment, the blockage risk prediction model can also employ Gradient Boosting Decision Tree (GBDT) as the blockage risk prediction model, and the GBDT model calculates the R value through the following process: Normalize input: scale the original sensor data to the range expected by the model.

[0055] Tree sequence prediction: each decision tree makes a simple prediction based on the input features, a leaf node weight value, and subsequent trees focus on correcting the residual of all previous trees.

[0056] Weighted sum: multiply the prediction results of all trees by the learning rate and add them to the initial prediction value to get an unsealed score F(x).

[0057] Probability conversion: finally, F(x) is converted to the final risk index R between 0 and 1 through the Sigmoid function.

[0058] For example, the input features [ΔP=0.06, K=5.41, A=0.85, T=48, Q=12] are evaluated and corrected in turn by the trained 80 decision trees, and the final output R ≈ 0.72.

[0059] Regarding the preset first risk threshold R1 and the preset second risk threshold R2, the threshold settings are usually set based on historical data, experimental experience, oil characteristics and process requirements, for example, R1 can be set between 0.25-0.35, R1 is the early warning line, indicating that the system has deviated from the normal operating state and preventive intervention should be started; R2 can be between 0.55-0.65, R2 is the safety intervention line, indicating that the system has entered a moderate risk and active removal measures must be started.

[0060] R1 and R2 can be adjusted according to different oil, here is a reference table of R1 and R2: According to the calculated comprehensive blockage risk index: R = 0.72, in this embodiment, the oil type is palm oil, the preset risk threshold according to the table, the first risk threshold R1 = 0.30, the second risk threshold R2 = 0.60, then according to the algorithm, if 0 ≤ R < R1, the risk level is determined to be the first level; if R1 ≤ R < R2, the risk level is determined to be the second level; If R ≥ R2, the risk level is determined to be the third level; it is judged that R > R2 belongs to the third level, and the second intervention strategy is executed, that is, a first scheduling signal is sent to the upstream, and a second scheduling signal is sent to the downstream, so that the current conveying pipeline enters an isolation state; after entering the isolation state, the current pipeline is cleaned and maintained, and the flow rate is increased to the maximum value allowed by the system in a pulse flushing mode, and maintained for a second preset time length.

[0061] The second intervention strategy is specifically executed as follows: Step 1: Send a scheduling signal to isolate the pipeline: the system sends a signal to the upstream and downstream, for example: send a "pipeline maintenance - suspend feeding" signal to the upstream deodorization process, and the upstream equipment stops conveying oil products to the pipeline; send a "quality isolation - batch backflow" signal to the downstream storage process, and the downstream equipment stops receiving oil products from the pipeline and prepares to receive backflow oil products.

[0062] At the same time, the rapid isolation valve group is actuated: the upstream and downstream cut-off valves are closed to isolate the current conveying pipeline section from the upstream and downstream; the bypass backflow pipe is enabled to guide the oil products in the pipeline to the backflow processing line.

[0063] Step 2, cleaning and maintenance: after the pipeline is isolated, the cleaning and maintenance program is started: First, inject cleaning aids: control the precision metering pump to inject food-grade cleaning aids such as lecithin dispersants at a volume ratio of 0.3%.

[0064] Assuming that the volume of oil in the pipeline is V (unit: m³), the injection flow rate of the cleaning aids is 0.003 * V (m³ / h), but usually needs to be continuously injected in proportion.

[0065] The injection rate is relative to the flow rate of the oil in the pipeline. Since the pipeline has been isolated, the isolated pipeline is in a circulating cleaning state, so the injection rate here is the proportion of the circulating flow rate during cleaning.

[0066] Then pulse flushing: start the variable frequency pump to increase the flow rate to the maximum value allowed by the system in a pulse mode, and set the maximum value to 18 m 3 / h, and maintain the pulse mode for 30 minutes.

[0067] Pulse mode parameters: cycle 30 seconds, 20 seconds at 18 m 3 / h, and 10 seconds at 10.8 m 3 / h (60% of the maximum flow rate).

[0068] Step 3, Reflux treatment: During the cleaning maintenance, all the oil products flowing through the pipeline, i.e. containing cleaning aids and flushed out deposits, are guided through a bypass reflux pipe to a treatment tank at the front end of the refining process, such as a pre-degumming or pre-deacidification treatment tank, which will be reprocessed through the refining process, ensuring that it does not enter the finished product storage tank.

[0069] Step 4, Effect verification and response: After 30 minutes of cleaning maintenance, the operating parameters are re-collected and the risk index R is recalculated.

[0070] If the R value drops below 0.3, i.e. the first level, the normal operation is resumed: the isolation valve is opened, the cleaning aid injection is stopped, the normal flow rate is restored, and a recovery signal is sent upstream and downstream.

[0071] If the R value is still above 0.3, the corresponding operation is performed according to the current level: If the current level is the second level (0.3 ≤ R < 0.6), the higher level intervention strategy is automatically started, i.e. the second intervention strategy is executed again, but the parameters may be adjusted, such as extending the cleaning time or increasing the aid concentration; If the current level is still the third level (R ≥ 0.6), the system alarm is triggered and a maintenance request signal is generated, notifying the maintenance personnel to perform mechanical cleaning or higher level treatment.

[0072] For example, data collected after cleaning: ΔP = 0.02 MPa; K = 1.8×10 9 Pa·s 2 / m 6 ; A = 0.12 mm / s 2 ; T = 50℃, which may be increased during cleaning; Q = 12 m 3 / h, normal flow rate is restored during verification; The R value is recalculated, assuming that the calculated R = 0.18, since 0.18 < 0.3, it is determined to be the first level, and the system resumes normal operation.

[0073] If the R value after cleaning is still 0.45, it is determined to be the second level, and the system will execute the second intervention strategy again, but the parameters may be adjusted, such as extending the cleaning time to 45 minutes or increasing the aid injection rate to 0.5%; If the R value after cleaning is still 0.65, it is determined to be the third level, and the system triggers an alarm and generates a maintenance request, notifying the maintenance personnel.

[0074] In one embodiment, assuming that the R value calculated by the clogging risk prediction model is 0.45, the preset R1 and R2 are 0.3 and 0.6 respectively, and R1 ≤ R < R2, the first intervention strategy is executed, and when the first strategy is executed, the preset temperature rise rate, the preset temperature and the temperature threshold value, the first temperature rise rate, the second temperature rise rate, the first temperature threshold value and the safety upper limit temperature are involved; The preset temperature is set based on the balance between the optimal dissolution temperature range of the target oil product deposit and the oil product thermal oxidation sensitive temperature.

[0075] The safety upper limit temperature is set according to the critical temperature at which the thermal decomposition threshold of key components of the oil product (such as vitamin E and polyphenol) and the oxidation rate significantly accelerates, and is an absolute red line to ensure the quality of the oil product.

[0076] The first temperature threshold value (switching point) is determined according to the thermal time constant of the control system and the stability margin of the PID controller, and is a boundary for preventing temperature overshoot and achieving smooth switching from rapid temperature rise to precise temperature control.

[0077] The first temperature rise rate (fast): in a larger temperature difference range with less thermal inertia influence, a higher rate is used to maximize the temperature rise efficiency and quickly enter the effective clogging removal temperature range.

[0078] The second temperature rise rate (fine): in a small temperature difference range close to the target temperature, a lower rate is used to compensate for system thermal inertia, ensure temperature control accuracy and eliminate overshoot.

[0079] Moreover, when setting the temperature parameters, the heat transfer characteristics and control accuracy of the equipment should be considered, and the corresponding parameters should be set in advance and stored in the system.

[0080] When the first intervention strategy is executed, the pre-stored data in the system can be directly called, and a corresponding data reference table is given as follows: The system automatically calls the parameters in the corresponding column according to the detected oil type: The preset temperature is dynamically selected within the given range according to the risk level R value: R = 0.3-0.4: take the lower limit of the range; R = 0.4-0.5: take the median of the range; R = 0.5-0.6: take the upper limit of the range; For example: the current oil is palm oil, R = 0.45; Call parameters: preset temperature: 66℃ (median of the interval 65-68); Safety upper limit temperature: 80℃; First temperature threshold: 15℃; First temperature rise rate: 3.5℃ / min (used when the current temperature is ≤51℃); Second heating rate: 1.1℃ / min (used when current temperature > 51℃).

[0081] For example: Current oil temperature: 48℃; Real-time flow rate: 13.2 m 3 / h; Risk level: Second level (R = 0.45); Temperature control parameters are called according to oil type (palm oil) and risk level (R = 0.45): Pre-set temperature: 66℃ (mid-value in the interval of 65-68); Safe upper limit temperature: 80℃; First temperature threshold: 15℃; First heating rate: 3.5℃ / min; Second heating rate: 1.1℃ / min; Rate switching temperature: 66-15 = 51℃; Temperature control execution process: First stage: Electric heat tracing starts, fast heating from 48℃ → 51℃, the theoretical time consumption is about 51 seconds, but due to the system response time, the actual time consumption may be 1 minute and 5 seconds; Second stage: Fine heating, temperature from 51℃ → 66℃; Starting temperature: 51℃; Target temperature: 66℃; Heating rate: 1.1℃ / min; Theoretical time consumption: (66-51) / 1.1 ≈ 13.64 minutes, plus the system response time, the actual time consumption may reach 13 minutes and 10 seconds; During the fine heating process, the electric heat tracing power will gradually decrease, for example, from full power of 18kW to 12kW.

[0082] Temperature control performance analysis: Overall heating process: Total heating amplitude: 48℃ → 66℃, rising by 18℃, total time consumption is about 14 minutes and 15 seconds; Average heating rate: 1.27℃ / min; Temperature control accuracy: ±0.3℃; Maximum temperature difference: 2.2℃ for the full length of the pipeline; Total energy consumption: 2.95kWh.

[0083] Pulse flushing is executed synchronously: Flushing parameter settings: Based on the current flow rate of 13.2 m 3 / h: Pulse cycle: 30 seconds; High flow rate period: 20 seconds (duty ratio 67%) Low flow rate period: 10 seconds (duty ratio 33%) Peak flow rate: 13.2 × 130% = 17.2 m 3 / h; Valley flow rate: 13.2 × 110% = 14.5 m 3 / h; Execution duration: 30 minutes, synchronized with temperature control.

[0084] After the first intervention strategy is executed, the oil temperature is 66℃, the inlet pressure is 0.60 MPa, the outlet pressure is 0.46 MPa, the real-time flow is 13.2 m 3 / h, and the vibration amplitude is 0.11 mm / s 2 ; The calculation parameters are ΔP = 0.14 MPa, K = 1.0×10 9 Pa·s 2 / m 6 ; The model output R value is 0.21 The risk level is re-determined as R = 0.21, R1 = 0.30, and 0.21 < 0.30, which belongs to the first level; the determination result is that the risk level is reduced from the second level to the first level; and the system response is to return to the normal operation state.

[0085] The following examples are used to illustrate the verification process: The system automatically performs effect verification at a preset time: The first intervention strategy is verified 30 minutes after the intervention starts, the second intervention strategy is verified 60 minutes after the intervention starts, and the verification basis is to recalculate the risk index R and compare it with the preset threshold.

[0086] Example 1: successful degradation (R = 0.18); recalculation of the risk index: R = 0.18; threshold comparison: 0.18 < R1 (0.30); determination result: the risk level has been reduced to the first level; execution action: immediately return to the normal operation state; system record: generate an intervention success report and record the improvement effect; Example 2: intervention needs to be upgraded (R = 0.48); recalculation of the risk index: R = 0.48; threshold comparison: 0.30 ≤ 0.48 < 0.60; system response: determination result: the risk level is still at the second level; execution action: automatically start a higher level intervention strategy; upgrade process: immediately execute the second intervention strategy (process isolation + chemical cleaning).

[0087] Example 3: manual intervention is needed (R = 0.78); recalculation of the risk index: R = 0.78; threshold comparison: 0.78 ≥ R2 (0.60); system response: determination result: the risk level is still at the third level; execution action: trigger a three-level audible and light alarm, generate an emergency maintenance request work order, notify the maintenance team to intervene immediately, and the system enters a safe protection state.

[0088] The places not mentioned in the present application can be implemented by using or referring to the existing technology.

[0089] The various embodiments in the specification are described in progressive manner, and the same or similar parts between the various embodiments can be mutually referred to, and each embodiment focuses on the difference from other embodiments.

[0090] The above only describes the embodiments of the present application and is not intended to limit the present application. The present application can have various modifications and changes for those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the scope of claims of the present application.

Claims

1. A method for controlling the processing and conveying of vegetable oil, characterized in that, Includes the following steps: Real-time acquisition of pipeline operating parameters, including inlet pressure, outlet pressure, oil temperature, real-time flow rate, and pipe wall vibration data, and calculation of real-time pressure difference, real-time flow resistance coefficient, and characteristic frequency amplitude; Based on the operating parameters, a quantified congestion risk index R is output through a preset congestion risk prediction model. The congestion risk index R is compared with a preset risk threshold range to determine the current congestion risk level. Based on the level of congestion risk, implement corresponding tiered proactive control and intervention strategies.

2. The method according to claim 1, characterized in that, The step of comparing the congestion risk index R with a preset risk threshold range to determine the current congestion risk level specifically involves: The overall congestion risk index R is compared with R1 and R2: If 0 ≤ R < R1, then the risk level is determined to be Level 1; If R1 ≤ R < R2, then the risk level is determined to be level two; If R ≥ R2, then the risk level is determined to be Level 3; Wherein, R1 is the preset first risk threshold, R2 is the preset second risk threshold, and R2 > R1.

3. The method according to claim 1, characterized in that, The step of implementing corresponding graded proactive control and intervention strategies based on the congestion risk level includes: When the risk level is Level 1, maintain the current operating status; When the risk level is Level 2, the first intervention strategy is implemented, which includes increasing the oil temperature and changing the flow rate in the delivery pipeline using a pulse flushing mode. When the risk level is level three, the second intervention strategy is implemented, which includes a combination of pulse flushing, process isolation and cleaning and maintenance.

4. The method according to claim 1, characterized in that, The first intervention strategy is as follows: Based on the current oil temperature, the oil temperature is raised to the preset temperature at a preset heating rate. Within a preset period, the flow rate is periodically fluctuated between 110% and 130% of the current flow rate and maintained for a first preset duration. The second intervention strategy specifically involves sending a first scheduling signal upstream and a second scheduling signal downstream to put the current transport pipeline into an isolation state. After entering the isolation state, the current pipeline is cleaned and maintained, and the flow rate is increased to the maximum design value allowed by the system in pulse flushing mode and maintained for the second preset duration.

5. The method according to claim 4, characterized in that, In the second intervention strategy, the current pipeline is cleaned and maintained, specifically as follows: Food-grade cleaning aids are injected at an injection rate of 0.1% to 0.5% of the total volumetric flow rate. Oil flowing through the delivery pipeline during the second intervention strategy is directed to a processing tank upstream of the refining process for recirculation treatment, instead of entering the downstream storage process.

6. The method according to claim 5, characterized in that, The step of raising the oil temperature to a preset temperature at a preset heating rate based on the current oil temperature specifically involves: calculating the heating value based on the thermal sensitivity coefficient of different oils to raise the oil temperature, and ensuring that the final temperature does not exceed the preset safe upper limit temperature of the oil.

7. The method according to claim 5, characterized in that, The preset heating rate is dynamically adjusted based on the difference between the current oil temperature and the preset safe upper limit temperature of the oil. When the difference is greater than the first temperature threshold, the first heating rate is used; When the difference is less than or equal to the first temperature threshold, the second heating rate is used; Wherein, the second heating rate is less than the first heating rate.

8. The method according to claim 5, characterized in that, After implementing any intervention strategy, initiate the effect verification and response process, specifically as follows: The operating parameters were re-collected and the congestion risk level was determined again. If the risk level has been reduced to Level 1, then normal operation will resume. If the risk level does not drop to Level 1, then perform the corresponding operation based on the current level: If the current level is Level 2, a higher-level intervention strategy will be automatically activated; If the current level is still Level 3, a system alarm will be triggered and a maintenance request signal will be generated.

9. A vegetable oil processing and conveying control system, used to execute the method according to any one of claims 1 to 8, characterized in that, include: The delivery pipeline unit includes the main delivery pipeline, an integrated bypass return pipeline, and a fast isolation valve assembly; The data acquisition module includes a pressure sensor, a temperature sensor, a flow meter, and a vibration sensor; The data processing and risk assessment module is used to calculate real-time differential pressure, real-time flow resistance coefficient and characteristic frequency amplitude based on the collected operating parameters, and output a comprehensive blockage risk index through the blockage risk prediction model to determine the risk level; The control execution module includes a temperature control unit, a flow regulation unit, a system scheduling unit, and a cleaning and maintenance unit, which are used to execute corresponding graded active control intervention strategies according to the risk level.

10. The system according to claim 9, characterized in that, The cleaning and maintenance unit includes a cleaning aid storage tank and a metering pump for injecting cleaning aids under the third intervention strategy and guiding the flushing oil to the processing tank at the front end of the refining process through the integrated bypass return pipe.

Images