Mixer for blending high-quality oil products and control system thereof

Abstract

The invention provides a mixer for blending high-quality oil products and a control system of the mixer, and relates to the technical field of oil product blending monitoring, the mixer monitors injection pressure data and concentration data of spray holes in different injection stages in real time, and equally divides sections with the same aperture in a main pipeline into a plurality of areas with the same diameter; the method comprises the following steps of: constructing an injection pressure gradient index # imgabs0 # and a comprehensive variable coefficient # imgabs1 # of an ith same-diameter area after an oil blending AI analysis model is constructed and trained, constructing an aperture compensation factor # imgabs2 # of a jth injection hole in the ith same-diameter area based on a Bernoulli equation, evaluating and outputting a classification output result of the aperture compensation factor # imgabs2 #, and generating a corresponding strategy for the corresponding classification output result.

Description

Technical Field

[0001] The present invention relates to the technical field of oil blending monitoring, and particularly to a mixer for high-quality oil blending and its control system. Background Art

[0002] In the traditional oil blending process, mixers usually inject oils of different components into the mixing tank using fixed spray holes and a single flow control method. Due to the lack of an accurate real-time feedback adjustment mechanism, problems such as uneven blending, large local concentration deviation, and large pressure fluctuations in the injection area are likely to occur. This extensive mixing method not only affects the quality consistency of the final oil product but also easily leads to problems such as increased energy consumption, equipment fatigue operation, and safety hazards.

[0003] Traditional mixers are difficult to achieve fine monitoring of the spray hole injection state. Especially when blending multi-component oils, in the face of raw material combinations with different viscosities, densities, and flow rates, the pressure distribution at the spray holes often shows non-linear fluctuations, which easily leads to local under-injection or over-injection, reducing the mixing uniformity. In addition, the traditional system also does not have the ability to identify and respond to whether the spray hole arrangement is uniform or whether the spray hole diameter is abnormal (such as blockage, wear, etc.), resulting in lagging maintenance and increasing the burden on operators.

[0004] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure. Therefore, it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide a mixer for high-quality oil blending and its control system to solve the problems raised in the above background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions: A control system for high-quality oil blending, comprising: A central control module, which real-time monitors the injection pressure data and concentration data of the spray holes at different injection stages, and equally divides the paragraphs with the same aperture in the main pipeline into several same-diameter regions to construct the injection pressure gradient index of the i-th same-diameter region and the comprehensive coefficient of variation , and based on the Bernoulli equation, constructs the aperture compensation factor of the j-th spray hole in the i-th same-diameter region , and after constructing and training the AI analysis model for oil blending, the injection pressure gradient index of the i-th same-diameter region and the comprehensive coefficient of variation as well as the aperture compensation factor of the j-th spray hole in the i-th same-diameter region Input it into the oil blending AI analysis model, and based on its classification output results, generate corresponding strategies for the corresponding classification output results.

[0007] Furthermore, the central control module includes: The injection monitoring module is used to collect and obtain the injection pressure data of each nozzle at different injection stages, collect the distance between each nozzle and the main pipe, and collect the actual aperture size data of each nozzle, establish a first data set, use neural network technology to establish a pressure response model and train it, and based on the first data set, construct the injection pressure gradient index of the i-th same-diameter region ; The injection monitoring module includes a same-diameter region division unit and a pressure acquisition unit; The same-diameter region division unit is used for the nozzle section with the same designed aperture on the main pipe, which is divided into one same-diameter section, including the same-diameter section with multiple nozzles with a diameter of 18mm or 22mm arranged continuously; In each same-diameter section, it is divided according to the total number of nozzles to form multiple same-diameter regions; set the length of each same-diameter section as L, there are N nozzles in this same-diameter section, and the layout of the nozzles in this same-diameter section is equally divided into M same-diameter regions, and the expression is ; where K is the number of nozzles included in each same-diameter region; The pressure acquisition unit is used to set pressure sensors at several nozzles of the oil mixer to obtain the injection pressure data at different injection stages; and collect the distance between each nozzle and the main pipe and the actual aperture size data of each nozzle, establish a first data set, and the first data set includes: Total pressure at the branch pipe inlet 、Pressure drop of the j-th nozzle in the i-th same-diameter region 、Total number of nozzles in the i-th same-diameter region 、Length of the i-th same-diameter region And the distance of the j-th nozzle relative to the starting point in this same-diameter region .

[0008] Furthermore, the injection monitoring module further includes a pressure model establishment unit; The pressure model establishment unit is used to use a convolutional neural network to construct an initial convolutional neural network model, train and test the initial convolutional neural network model with the first data set, and use the trained initial convolutional neural network model as a pressure response model to construct the injection pressure gradient index of the i-th same-diameter region , and the acquisition steps include: S11. In each same-diameter region, obtain the axial position coordinates of all nozzles on the branch pipe to establish a nozzle coordinate data set: , to represent the coordinate positions of the first nozzle to the th nozzle in the i-th same-diameter area, obtained from CAD drawings, construction design drawings or actual installation measurements; S12. Calculate the actual distances between all adjacent nozzles in the i-th same-diameter area using coordinate differences, and calculate the spacing. The expression is: ; thus obtaining the nozzle spacing data set for the i-th same-diameter area: ; S13. According to the nozzle spacing data set obtained in S12, calculate the average nozzle spacing and the standard deviation in the i-th same-diameter area: S14. Based on the average spacing and the standard deviation in the i-th same-diameter area, calculate and obtain the nozzle arrangement uniformity factor of the i-th same-diameter area through the following formula: When , it indicates that the arrangement in this same-diameter area meets the uniformity standard. When , it indicates that the arrangement in this same-diameter area does not meet the uniformity standard, there is a risk of affecting the mixing effect, and the first warning instruction is triggered, including: adjusting the nozzle spacing by ±3% - ±5%, and reducing the overall injection flow rate by 5% - 10% until ; When , it indicates that the arrangement in this same-diameter area does not meet the uniformity standard, indicating a risk of highly uneven arrangement, and the second warning instruction is triggered, including: adjusting the nozzle spacing by ±10% - ±20%, and reducing the overall injection flow rate by 11% - 20% until ; then restore the normal injection flow rate; S15. After the first warning instruction and the second warning instruction are executed, extract the total pressure at the branch pipe inlet in the first data set, the pressure drop of the j-th nozzle in the i-th same-diameter area, the total number of nozzles in the i-th same-diameter area, the length of the i-th same-diameter area, and the distance of the j-th nozzle from the starting point in this same-diameter area. Combine with the nozzle arrangement uniformity factor of the i-th same-diameter area, and calculate and obtain the jet pressure gradient index of the i-th same-diameter area through the following formula: In the formula, The term is used to normalize the pressure drop to the pressure loss per unit length, which is the basic gradient definition; The term in square brackets means: the weighted average of the pressure drops of all the nozzles in the region, where the influence of the nozzle position on the pressure drop is introduced. The closer to the end of the region (farther from the liquid inlet), the greater the pressure drop; represents the adjustment position sensitivity weight, which is set to 1 - 2; represents the non-uniformity correction factor. If the nozzle distribution is non-uniform, it will cause a sharp local pressure drop; represents the uniformity empirical weight, which is set to 0.1 - 0.5.

[0009] Furthermore, the central control module further includes: An index fluctuation analysis module, which is used to set multiple groups of oil sampling points in the tank where the mixer is located, regularly detect the oil concentration and related indexes at different spatial positions in each same-diameter region, establish a spatial index data set, and construct the comprehensive coefficient of variation of the i-th same-diameter region to evaluate the uniformity of the oil after mixing; The index fluctuation analysis module includes an index acquisition unit. The index acquisition unit is used to install a vibrating tube densitometer, a concentration sensor, and a micro closed cup flash point tester in several same-diameter regions of the oil mixer, and collect and obtain the octane number X i of the i-th same-diameter region, the oil density the dynamic viscosity of the oil i and the flash point

[0010] Furthermore, the index fluctuation analysis module further includes an index anomaly analysis unit. The index anomaly analysis unit is used to establish a spatial index data set to construct the comprehensive coefficient of variation of the i-th same-diameter region. The acquisition steps include: S21. Extract the spatial index data set, calculate each index of the i-th same-diameter region respectively, and obtain the average value and standard deviation of each index: S22. Calculate the coefficient of variation for each index respectively, and obtain the octane number coefficient of variation of the i-th same-diameter region, the oil density coefficient of variation the dynamic viscosity coefficient of the oil and the oil density coefficient of variation In the formula, is the average value of the octane number in the i-th same-diameter region, representing the central tendency of the octane number in this same-diameter region; is the standard deviation of the octane number in the i-th same-diameter region, indicating the fluctuation range of the octane number, that is, the degree to which the octane number at each measurement point deviates from the average value; The larger it is, the stronger the volatility of the octane number and the more uneven the mixing; is the average value of the oil density in the i-th same-diameter region, representing the central tendency of the oil density in this same-diameter region; is the standard deviation of the oil density in the i-th same-diameter region, indicating the fluctuation range of the oil density, that is, the degree to which the oil density value at each measurement point deviates from the average value; The larger it is, the stronger the fluctuation of the oil density in this same-diameter region and the more uneven the mixing; is the average value of the dynamic viscosity of the oil in the i-th same-diameter region, representing the central tendency of the dynamic viscosity of the oil in this same-diameter region; is the standard deviation of the dynamic viscosity of the oil in the i-th same-diameter region, indicating the fluctuation range of the dynamic viscosity of the oil, that is, the degree to which the dynamic viscosity value of the oil at each measurement point deviates from the average value; The larger it is, the stronger the fluctuation of the dynamic viscosity of the oil in this same-diameter region and the more uneven the mixing; is the average value of the flash point of the oil in the i-th same-diameter region, representing the central tendency of the flash point of the oil in this same-diameter region; is the standard deviation of the flash point of the oil in the i-th same-diameter region, indicating the fluctuation range of the flash point of the oil, that is, the degree to which the flash point value of the oil at each measurement point deviates from the average value; The larger it is, the stronger the fluctuation of the flash point of the oil in this same-diameter region and the more uneven the mixing; S23. Combining the coefficient of variation of the octane number in the i-th same-diameter region , the coefficient of variation of the oil density , the coefficient of variation of the dynamic viscosity of the oil and the coefficient of variation of the oil density , the comprehensive coefficient of variation of the i-th same-diameter region is obtained by calculating through the following formula : In the formula, represents the weight coefficient of the k-th index, represents the coefficient of variation of the k-th index in the i-th same-diameter region, including the coefficient of variation of the octane number in the i-th same-diameter region , the coefficient of variation of the oil density , the coefficient of variation of the dynamic viscosity of the oil and the coefficient of variation of the oil density .

[0011] Furthermore, the central control module further includes an orifice compensation prediction module; The orifice compensation prediction module is used to collect and construct an orifice compensation factor for the j-th orifice in the i-th same-diameter area based on Bernoulli's equation , which is used to characterize the degree of deviation of the actual orifice structure from the design target; The orifice compensation prediction module includes an orifice data acquisition unit; The orifice data acquisition unit is used to obtain the orifice diameter size of each orifice after actual installation, and collect the designed orifice diameter of the j-th nozzle in the i-th same-diameter area , actual injection flow rate , total pressure at the branch pipe inlet and the outlet pressure of the j-th orifice in the i-th same-diameter area , and extract the oil density of the i-th same-diameter area from the spatial index dataset , and construct a second dataset.

[0012] Furthermore, the orifice compensation prediction module further includes an orifice blockage prediction unit; The orifice blockage prediction unit is used to construct an orifice compensation factor for the j-th orifice in the i-th same-diameter area according to the second dataset, based on Bernoulli's equation and the continuity principle , and the specific steps include: S31. Calculate the theoretical orifice diameter of the j-th orifice in the i-th same-diameter area according to Bernoulli's equation and the continuity principle , and the specific steps are as follows: S311. According to the actual injection flow rate of the j-th nozzle in the i-th same-diameter area collected , pressure difference between inlet and outlet and oil density , use the orifice flow formula as: In the formula, is the actual cross-sectional area of the j-th nozzle in the i-th same-diameter area; Inverse solution to obtain the theoretical orifice cross-sectional area of the j-th nozzle in the i-th same-diameter area : S312. When the orifice is set as a standard round hole, further obtain the theoretical orifice diameter of the j-th orifice in the i-th same-diameter area : S32. Combine the designed orifice diameter of the j-th nozzle in the i-th same-diameter area and the theoretical aperture of the j-th nozzle hole in the i-th same-diameter region , the aperture compensation factor of the j-th nozzle hole in the i-th same-diameter region is calculated through the following formula : .

[0013] Furthermore, the central control module further includes an AI analysis module; The AI analysis module includes an evaluation model establishment unit, a training unit, and a classification result unit; The evaluation model establishment unit is used to construct an AI analysis model for oil product blending to classify and discriminate the uniformity of oil product injection mixing by using one or more of logistic regression, support vector machine, decision tree, random forest, or ensemble learning algorithm as the classifier basis; The training unit is used to extract the injection pressure gradient index and the comprehensive coefficient of variation of the i-th same-diameter region, as well as the aperture compensation factor of the j-th nozzle hole in the i-th same-diameter region and train the sample data set, and the sample data set includes: The injection pressure gradient index of the i-th same-diameter region , which is used to characterize the change characteristics of the pressure drop per unit length in this same-diameter region; The comprehensive coefficient of variation of the i-th same-diameter region , which is used to measure the degree of uniformity fluctuation of the nozzle hole arrangement; The aperture compensation factor of the j-th nozzle hole in the i-th same-diameter region , which is used to reflect the deviation degree of the actual nozzle hole from the target aperture and whether there is a risk of blockage; The classification result unit inputs the sample numbers into the trained AI analysis model for oil product blending to obtain the classification output result, including: A preset first threshold Z1, and the injection pressure gradient index of the i-th same-diameter region is compared with the first threshold Z1 to obtain the first classification output result, including: When , it indicates that the pressure drop distribution in this same-diameter region is qualified; When , it indicates that the pressure drop distribution in this same-diameter region is abnormal, triggering a pressure drop risk warning; A preset second threshold Z2, and the comprehensive coefficient of variation of the i-th same-diameter region is compared with the second threshold Z2 to obtain the second classification output result, including: When , it indicates that the uniformity of the nozzle hole arrangement in this same-diameter region is qualified; When It indicates that the nozzle arrangement uniformity in this same-diameter area is unqualified, there is a risk of uneven arrangement, and a risk warning for arrangement uniformity is triggered; A preset third threshold Z3, and the aperture compensation factor of the j-th nozzle in the i-th same-diameter area is compared with the third threshold Z3 to obtain a third classification output result, including: When it indicates that the aperture error of the j-th nozzle in this same-diameter area is within the acceptable range; When it indicates that there are potential risks of aperture deviation or blockage in the j-th nozzle in this same-diameter area, and a structural risk warning is triggered.

[0014] Furthermore, the AI analysis module further includes a strategy generation unit, which is used to generate corresponding strategies according to the pressure drop risk warning, arrangement uniformity risk warning, and structural risk warning, including: According to the pressure drop risk warning, a first strategy is generated, including: increasing the injection pressure in this same-diameter area by 5% - 10% to enhance the liquid propulsion force and relieve the local pressure drop accumulation phenomenon; evenly adding 1 - 2 auxiliary tear holes within the adjacent nozzle intervals, with the aperture set to 3mm - 5mm, to guide the fluid diversion and thus reduce the main path pressure difference; According to the arrangement uniformity risk warning, a second strategy is generated, including: locally adding 1 - 3 nozzles in the same-diameter area and re-planning the injection sequence, preferentially activating the nozzles at the center of injection in this same-diameter area, and activating them sequentially towards the edge, with the time interval for activating the injection through holes set to 1 - 3 seconds; According to the structural risk warning, a third strategy is generated, including: performing fine-tuning and hole-filling treatment on the nozzles in this same-diameter area. For nozzles with an aperture deviation not exceeding 5%, grinding or reaming repair treatment is carried out; for nozzles with an aperture deviation exceeding ±10%, physical replacement is implemented; and the nozzles in this same-diameter area are marked as blocked nozzles, and 1 - 2 auxiliary tear holes are set on both sides of the blocked nozzles to guide the fluid to bypass the blockage point.

[0015] A mixer for blending high-quality oil products, comprising: A tank body for containing oil product raw materials of different components; A mixer assembly is arranged at 500mm above the inner bottom of the tank body and includes: The main liquid supply pipe is a DN200 stainless steel pipe; Multiple connected branch pipes, including several DN65 stainless steel pipes and several branch pipes equipped with nozzles; A plurality of spray holes are provided on the branch pipe, and the diameter of the spray holes increases as the distance from the branch pipe increases, so as to compensate for the pressure loss and realize uniform spraying; at least one section of corrugated flexible connecting pipe is used to avoid the installation difficulties caused by the rigid connection; the pipeline of the mixer assembly is configured to realize that different components of oil products are injected from the main supply pipe in sequence, and are uniformly injected into the tank body through the spray holes, so as to realize uniform blending of the oil products; Multiple groups of control valves are respectively set at the injection inlets of different components; A PLC controller or industrial computer, used to control the opening and closing of the valve according to preset recipe parameters; The liquid level sensor is installed inside the tank to monitor the oil level in real time; The ratio algorithm module calculates the required raw material injection amount according to the real-time liquid level change and the set ratio; The central control module works in conjunction with the mixer to control the injection ratio of each component within a raw material injection height range of 10 meters, and complete the final blending within the 2-3 meter adjustment space at the top of the tank, thereby producing qualified oil products.

[0016] Compared with the prior art, the beneficial effects of the present invention are: the injection pressure data and concentration data of the nozzle holes at each stage are collected in real time through the central control module, and the injection pressure gradient index, comprehensive coefficient of variation and aperture compensation factor are calculated after the main pipeline is divided into equal diameter regions, which can not only reflect the pressure drop distribution, nozzle hole arrangement uniformity and structural deviation of the injection process in detail, but also provide quantifiable and analyzable basic data for subsequent optimization strategies. Through the AI ​​analysis model to classify and output each indicator, the system can accurately identify different types of risks and generate corresponding adjustment strategies, effectively avoid the concentration deviation caused by insufficient or excessive local injection, and improve the overall consistency and quality stability of oil blending, which is particularly suitable for production scenarios such as lubricants and special oils with high requirements for product homogeneity. When abnormal pressure drop, uneven arrangement or structural deviation occurs, the system can generate corresponding strategies respectively, including adjusting the injection pressure increase ratio (such as fine-tuning by 10%-30%), optimizing the flow velocity distribution (such as reducing or increasing the flow density in a certain area), adjusting the nozzle hole arrangement spacing or adding "auxiliary tear holes" and other structural compensation means, so as to achieve dynamic closed-loop optimization of the injection system. By introducing AI model training and automatic identification mechanisms, the system can identify risk trends at an early stage and automatically generate adjustment strategies, reducing dependence on operators, reducing the probability of human misjudgment, and avoiding fluctuations in blending quality due to failure to respond in time to problems such as nozzle blockage and loss during long-term operation. The control system combines traditional fluid mechanics theory (such as the Bernoulli equation) with AI modeling analysis to establish a closed-loop feedback mechanism from monitoring, identification to regulation, making the blending process more refined, intelligent and highly reliable, meeting the dual requirements of quality and efficiency in modern oil production. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic diagram of the control system process for blending high-quality oil products in the present invention.

[0018] Figure 2 This is a top-down sectional view schematic diagram of a mixer for blending high-quality oil products in Example 6.

[0019] Figure 3 This is a schematic diagram of the position for opening the auxiliary tear holes in Example 5.

[0020] In the figure: 001, tank body; 002, mixer assembly; 003, main liquid supply pipe; 004, branch pipe; 005, spray hole; 006, corrugated flexible connecting pipe; 007, auxiliary tear hole. Detailed implementation manners

[0021] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with specific embodiments.

[0022] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar terms used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. The terms such as "connected" or "linked" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left", "right" are only used to represent relative position relationships, and when the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0023] Example 1: Please refer to Figure 1 , the present invention provides a technical solution: A control system for blending high-quality oil products, comprising: A central control module, which monitors in real time the injection pressure data and concentration data of the spray holes at different injection stages, and equally divides the paragraphs with the same aperture in the main pipeline into several same-diameter regions to construct the injection pressure gradient index and the comprehensive coefficient of variation of the i-th same-diameter region, and based on Bernoulli's equation, constructs the aperture compensation factor of the j-th spray hole in the i-th same-diameter region, and after constructing and training the AI analysis model for oil product blending, the injection pressure gradient index of the i-th same-diameter region and the comprehensive coefficient of variation and the aperture compensation factor of the j-th injection hole in the i-th same-diameter area Input into the oil blending AI analysis model, and based on its classification output results, generate corresponding strategies for the corresponding classification output results.

[0024] In this embodiment, the central control module collects the injection pressure data and concentration data of each injection hole in real time at each stage, and after regionalizing the main pipeline into equal-diameter areas, calculates the injection pressure gradient index, the comprehensive coefficient of variation, and the aperture compensation factor. This can not only reflect in detail the pressure drop distribution, the uniformity of the injection hole arrangement, and the structural deviation situation during the injection process, but also provide quantifiable and analyzable basic data for subsequent optimization strategies. Through the AI analysis model to classify and output judgments on each index, the system can accurately identify different types of risks and generate corresponding adjustment strategies, effectively avoiding concentration deviation caused by local under-injection or over-injection, improving the overall consistency and quality stability of oil blending, and is especially suitable for production scenarios such as lubricating oil and special oil with high requirements for product homogeneity. When there are abnormal pressure drops, uneven arrangements, or structural deviations, the system can generate the first, second, and third strategies respectively, specifically including adjusting the injection pressure increase ratio (such as fine-tuning by 10%-30% amplitude), optimizing the flow velocity distribution (such as reducing or increasing the flow density in a certain area), adjusting the arrangement spacing of injection holes, or adding structural compensation means such as "auxiliary weep holes", so as to realize the dynamic closed-loop optimization of the injection system. By introducing the AI model training and automatic recognition mechanism, the system can identify risk trends in the early stage and automatically generate adjustment strategies, reducing the dependence on operators, reducing the probability of human misjudgment, and also avoiding the quality fluctuation of blending caused by problems such as injection hole blockage and loss not being responded to in time during long-term operation. This control system combines traditional fluid mechanics theories (such as Bernoulli's equation) with AI modeling analysis to establish a closed-loop feedback mechanism from monitoring, identification to regulation, making the blending process more refined, intelligent, and highly reliable, meeting the dual requirements of modern oil production for quality and efficiency.

[0025] Example 2, please refer to Figure 1 , the central control module includes: An injection monitoring module, which is used to collect and obtain the injection pressure data of each injection hole at different injection stages, collect the distance between each injection hole and the main pipe, and collect the actual aperture size data of each injection hole, establish a first data set, use neural network technology to establish a pressure response model and train it, and based on the first data set, construct the injection pressure gradient index of the i-th same-diameter area ; The injection monitoring module includes a same-diameter area dividing unit and a pressure collecting unit; The divided same-diameter region unit is used for the spray hole section with the same designed aperture of the spray holes on the main pipe, and is divided into one same-diameter section, including a same-diameter section with a plurality of spray holes with a diameter of 18 mm or 22 mm arranged continuously; By equally dividing the regions with the same spray hole aperture in the main pipeline into multiple same-diameter regions and setting a fixed number of spray holes (such as K = 5) in each region, the overall complex injection system can be decomposed into multiple controllable same-diameter regions, which is convenient for local modeling analysis and risk positioning, and improves the refinement level of spray hole arrangement and performance evaluation.

[0026] In each same-diameter section, it is divided according to the total number of same spray holes to form multiple same-diameter regions; set the length of each same-diameter section as L, there are N spray holes in this same-diameter section, and the arrangement of the spray holes in this same-diameter section is equally divided into M same-diameter regions, and the expression is ; where K is the number of spray holes included in each same-diameter region; (such as K = 5, indicating that every 5 spray holes form a same-diameter region); The pressure acquisition unit is used to set pressure sensors at several spray holes of the oil mixer to obtain the injection pressure data at different injection stages; and collect the distances between each spray hole and the main pipe and the actual aperture size data of each spray hole, and establish a first data set, and the first data set includes: Total pressure at the branch pipe inlet 、Pressure drop of the j-th spray hole in the i-th same-diameter region 、Total number of spray holes in the i-th same-diameter region 、Length of the i-th same-diameter region And the distance of the j-th spray hole relative to the starting point in this same-diameter region .

[0027] The injection monitoring module further includes a pressure model establishment unit; The pressure model establishment unit is used to utilize a convolutional neural network to construct an initial convolutional neural network model, and train and test the initial convolutional neural network model with the first data set, and use the trained initial convolutional neural network model as a pressure response model to construct the injection pressure gradient index of the i-th same-diameter region , and the acquisition steps include: S11. In each same-diameter region, obtain the axial position coordinates of all spray holes on the branch pipe, and establish a spray hole coordinate data set: , To Indicates the first spray hole to the The coordinate positions of the nozzles are obtained from CAD drawings, construction design drawings, or actual installation measurements. By collecting the precise axial positions of the nozzles on the branch pipes, digital modeling of the nozzle arrangement in physical space is achieved, providing a geometric basis for subsequent distance calculation and uniformity evaluation, and helping to detect structural deviations.

[0028] S12. Calculate the actual distances between all adjacent nozzles in the i-th same-diameter area using coordinate differences, and calculate the spacing. The expression is: ; thus, the nozzle spacing data set for the i-th same-diameter area is obtained: ; Automatically calculating the spacing data between nozzles replaces manual measurement and empirical estimation, improves the analysis efficiency and spatial distribution accuracy, and facilitates the discovery of potential abnormal nozzle arrangements. Extracting data features that reflect the overall trend and local fluctuations of the nozzle arrangement lays a statistical foundation for the judgment of the uniformity factor and enhances the sensitivity of the model to changes in structural uniformity.

[0029] S13. According to the nozzle spacing data set of the i-th same-diameter area obtained in S12, calculate the average nozzle spacing and the standard deviation : S14. Based on the average spacing and the standard deviation of the i-th same-diameter area, calculate the nozzle arrangement uniformity factor of the i-th same-diameter area through the following formula: When , it indicates that the arrangement in this same-diameter area meets the uniformity standard. When , it indicates that the arrangement in this same-diameter area does not meet the uniformity standard and there is a risk of affecting the mixing effect, triggering the first warning instruction, including: adjusting the nozzle spacing by ±3% - ±5% and reducing the overall injection flow rate by 5% - 10% until ; When , it indicates that the arrangement in this same-diameter area does not meet the uniformity standard, indicating a risk of highly uneven arrangement, triggering the second warning instruction, including: adjusting the nozzle spacing by ±10% - ±20% and reducing the overall injection flow rate by 11% - 20% until ; restoring the normal injection flow rate; setting the first and second warning instructions, and defining different levels of nozzle spacing adjustment ranges (±3% - ±5%, ±10% - ±20%) and flow rate adjustment strategies (5% - 10%, 11% - 20%), providing a rapid-response and operationally clear closed-loop control method, and improving the adaptive adjustment ability of the system.

[0030] Specific data example: The number of same-diameter regions M = 4, and each same-diameter region contains K = 5 spray holes; This example focuses on the i = 2 same-diameter region (spray holes No. 6 - 10); Total pressure at the inlet of the branch pipe is 8.5 (kPa); the length of this same-diameter region is 600 - 310 = 290 mm; Example Table 1 of the first data set (the 2nd same-diameter region): Total pressure at the inlet of the branch pipe is 8.5 (kPa); the length of this same-diameter region is 600 - 310 = 290 mm; Spacing calculation (S12 - S13): Average spacing of spray holes in the i-th same-diameter region and standard deviation : ; ; Spray hole arrangement uniformity factor in the i-th same-diameter region: ; Judgment and response, because , it indicates that the arrangement in this same-diameter region does not meet the uniform standard, indicating a risk of highly non-uniform arrangement, triggering the second warning instruction, including: adjusting the spray hole spacing by ±10% - ±20%, and reducing the overall injection flow rate by 11% - 20% until until, and then restoring the normal injection flow rate; Suggestions for adjusting the spray hole spacing (±10% - ±20%); The target spacing range should be fine-tuned by ±10% - ±20% around the ideal mean value of 72.5 mm: 72.5×(1 ± 0.1) ⇒ 65.25 mm - 79.75 mm; 72.5×(1 ± 0.2) ⇒ 58.00 mm - 87.00 mm; Select a new approximate equidistant arrangement plan as follows: Spray hole No. 6: 310 mm (fixed); The new spacing is selected to be approximately 70 mm ± reasonable deviation: The new coordinate sequence = [310, 380, 450, 520, 590] mm, and the corresponding new spacing: 70, 70, 70, 70 mm → The uniformity is ideal, and the jet hole arrangement uniformity factor of the i-th same-diameter region ≈ 0.

[0031] S15. After the first warning instruction and the second warning instruction are executed, extract the total pressure at the branch pipe inlet in the first dataset , the pressure drop of the j-th jet hole in the i-th same-diameter region , the total number of jet holes in the i-th same-diameter region , the length of the i-th same-diameter region and the distance of the j-th jet hole from the starting point in this same-diameter region , combined with the jet hole arrangement uniformity factor of the i-th same-diameter region , calculate and obtain the jet pressure gradient index of the i-th same-diameter region through the following formula : In the formula, The term is used to normalize the pressure drop to the pressure loss per unit length, which is the basic gradient definition; The term in the brackets The meaning is: the weighted average of the pressure drops of all jet holes in the region, where introduces the influence of the jet hole position on the pressure drop. The closer to the end of the region (farther from the liquid inlet), the greater the pressure drop; represents the adjustment position sensitivity weight, which is set to 1 - 2; represents the non-uniformity correction factor. If the jet holes are unevenly distributed, it will cause a sharp local pressure drop; represents the uniformity empirical weight, which is set to 0.1 - 0.5.

[0032] In this embodiment, a jet pressure gradient index that comprehensively considers the pressure drop, jet hole position, total number of jet holes, and arrangement uniformity is constructed, which can comprehensively reflect the difference in the mixing driving force in the local area; Example 3, please refer to Figure 1 , the central control module further includes: An index fluctuation analysis module, which is used to set multiple groups of oil sampling points in the tank where the mixer is located, regularly detect the oil concentration and related indexes at different spatial positions in each same-diameter region, establish a spatial index dataset, and construct the comprehensive coefficient of variation of the i-th same-diameter region to evaluate the uniformity of the oil after mixing; The index fluctuation analysis module includes an index acquisition unit, which is used to install a vibrating tube densitometer, a concentration sensor, and a micro closed cup flash point tester in several same-diameter areas of the oil mixer, and collect and obtain the octane number X of the i-th same-diameter area i , oil density , dynamic viscosity of the oil and flash point i , and construct a spatial index data set

[0033] Measure the pressure change and nozzle hole state for each area, and generate corresponding area indexes

[0034] The index fluctuation analysis module further includes an index anomaly analysis unit, which is used to establish a spatial index data set to construct the comprehensive coefficient of variation of the i-th same-diameter area , and the acquisition steps include S21. Extract the spatial index data set, calculate each index for the i-th same-diameter area respectively, and obtain the average value and standard deviation of each index S22. Calculate the coefficient of variation for each index respectively, and obtain the coefficient of variation of the octane number in the i-th same-diameter area , the coefficient of variation of the oil density , the coefficient of variation of the dynamic viscosity of the oil and the coefficient of variation of the oil density : In the formula is the average value of the octane number in the i-th same-diameter area, representing the central tendency of the octane number in this same-diameter area is the standard deviation of the octane number in the i-th same-diameter area, indicating the fluctuation range of the octane number, that is, the degree to which the octane number at each measurement point deviates from the average value The larger it is, the stronger the volatility of the octane number and the more uneven the mixing is the average value of the oil density in the i-th same-diameter area, indicating the central tendency of the oil density in this same-diameter area is the standard deviation of the oil density in the i-th same-diameter area, indicating the fluctuation range of the oil density, that is, the degree to which the oil density value at each measurement point deviates from the average value The larger it is, the stronger the fluctuation of the oil density in this same-diameter area and the more uneven the mixing is the average value of the dynamic viscosity of the oil in the i-th same-diameter area, indicating the central tendency of the dynamic viscosity of the oil in this same-diameter area is the standard deviation of the kinematic viscosity of the oil product in the i-th equal-diameter region, representing the fluctuation range of the kinematic viscosity of the oil product, that is, the degree to which the kinematic viscosity values of each measurement point deviate from the average value; The larger it is, the stronger the fluctuation of the kinematic viscosity of the oil product in this equal-diameter region, and the more uneven the mixing; is the average value of the flash point of the oil product in the i-th equal-diameter region, representing the central tendency of the flash point of the oil product in this equal-diameter region; is the standard deviation of the flash point of the oil product in the i-th equal-diameter region, representing the fluctuation range of the flash point of the oil product, that is, the degree to which the flash point values of each measurement point deviate from the average value; The larger it is, the stronger the fluctuation of the flash point of the oil product in this equal-diameter region, and the more uneven the mixing; S23. Combine the coefficient of variation of the octane number in the i-th equal-diameter region , the coefficient of variation of the oil product density , the coefficient of variation of the kinematic viscosity of the oil product and the coefficient of variation of the oil product density , and obtain the comprehensive coefficient of variation of the i-th equal-diameter region through the following formula : In the formula, represents the weight coefficient of the k-th index, represents the coefficient of variation of the k-th index in the i-th equal-diameter region, including the coefficient of variation of the octane number in the i-th equal-diameter region , the coefficient of variation of the oil product density , the coefficient of variation of the kinematic viscosity of the oil product and the coefficient of variation of the oil product density .

[0035] Please refer to Table 2 of the spatial index dataset of the i-th equal-diameter region: In this embodiment, this module can be extended from a single index (such as density or viscosity) to more representative comprehensive indexes such as octane number and flash point, improving the judgment accuracy. By collecting data at multiple spatial points to construct a "spatial index dataset", it is possible to identify the uniformity problems of oil product mixing at different positions, providing a basis for nozzle layout, flow rate control, etc. Using the comprehensive coefficient of variation as a dimensionless index to eliminate unit differences and achieve comprehensive cross-index comparison makes the mixing evaluation more universal and sensitive.

[0036] Example 4, please refer to Figure 1 , the central control module further includes an orifice diameter compensation prediction module; The orifice diameter compensation prediction module is used to collect and construct the orifice diameter compensation factor of the j-th nozzle in the i-th equal-diameter region based on the Bernoulli equation , used to characterize the degree of deviation of the actual nozzle structure from the design target; The aperture compensation prediction module includes an aperture data acquisition unit; The aperture data acquisition unit is used to obtain the aperture size of each nozzle after actual installation, and collect the designed aperture of the j-th nozzle in the i-th same-diameter area , actual injection flow rate , total pressure at the branch pipe inlet and the outlet pressure of the j-th nozzle in the i-th same-diameter area , and extract the oil density of the i-th same-diameter area in the spatial index dataset , and construct a second dataset.

[0037] The aperture compensation prediction module further includes an aperture blockage prediction unit; The aperture blockage prediction unit is used to construct the aperture compensation factor of the j-th nozzle in the i-th same-diameter area according to the second dataset, based on Bernoulli's equation and the principle of continuity , and the specific steps include: S31. According to Bernoulli's equation and the principle of continuity, calculate the theoretical aperture of the j-th nozzle in the i-th same-diameter area , and the specific steps are as follows: S311. According to the actual injection flow rate of the j-th nozzle in the i-th same-diameter area collected , pressure difference between inlet and outlet and oil density , using the nozzle flow formula: In the formula, is the actual cross-sectional area of the j-th nozzle in the i-th same-diameter area; Inverse solution to obtain the theoretical nozzle cross-sectional area of the j-th nozzle in the i-th same-diameter area : S312. When the nozzle is set as a standard round hole, further obtain the theoretical aperture of the j-th nozzle in the i-th same-diameter area : S32. Combine the designed aperture of the j-th nozzle in the i-th same-diameter area and the theoretical aperture of the j-th nozzle in the i-th same-diameter area , and calculate and obtain the aperture compensation factor of the j-th nozzle in the i-th same-diameter area through the following formula : ; In this embodiment, by calculating and adjusting the nozzle aperture compensation factor, the working parameters of the nozzle can be dynamically adjusted under different oil product conditions, thereby optimizing the fluidity and mixing effect of the oil product in the equipment, and improving the uniformity and quality of the oil product. The aperture blockage prediction unit can predict the nozzle aperture compensation factor based on Bernoulli's equation and the principle of continuity, so as to identify possible blockage situations in advance. This helps to timely adjust the working state of the nozzle and avoid equipment failures or production interruptions caused by blockages. After realizing the aperture compensation prediction, the working state of the nozzle can be monitored in real time, and dynamic adjustment can be made according to the difference between the theoretical aperture and the actual aperture, reducing the working instability caused by aperture deviation, thereby improving the operation reliability of the overall equipment. By constructing an aperture blockage prediction unit, potential problems of the nozzle (such as aperture blockage) can be detected in advance, and necessary maintenance or adjustment measures can be taken before the problems occur. This warning mechanism significantly reduces the system maintenance cost and extends the service life of the equipment.

[0038] Example 5, please refer to Figure 1 , the central control module further includes an AI analysis module; The AI analysis module includes an evaluation model establishment unit, a training unit, and a classification result unit; The evaluation model establishment unit is used to construct an AI analysis model for oil product blending to classify and discriminate the uniformity of oil product injection mixing by using one or more of logistic regression, support vector machine, decision tree, random forest, or ensemble learning algorithm as the classifier basis; The training unit is used to extract the injection pressure gradient index and the comprehensive coefficient of variation of the i-th same-diameter area, as well as the aperture compensation factor of the j-th nozzle in the i-th same-diameter area and train the sample data set, and the sample data set includes: The injection pressure gradient index of the i-th same-diameter area , which is used to describe the change characteristics of the pressure drop per unit length in this same-diameter area; The comprehensive coefficient of variation of the i-th same-diameter area , which is used to measure the degree of uniformity fluctuation of the nozzle arrangement; The aperture compensation factor of the j-th nozzle in the i-th same-diameter area , which is used to reflect the deviation degree between the actual nozzle and the target aperture, and whether there is a blockage risk; The classification result unit inputs the sample numbers into the trained AI analysis model for oil product blending to obtain a classification output result, including: A preset first threshold Z1, comparing the injection pressure gradient index of the i-th same-diameter area with the first threshold Z1 to obtain a first classification output result, including: When , it indicates that the pressure drop distribution in this equal-diameter area is qualified; When , it indicates that the pressure drop distribution in this equal-diameter area is abnormal, triggering a pressure drop risk warning; Preset a second threshold Z2, and compare the comprehensive coefficient of variation of the i-th equal-diameter area with the second threshold Z2 to obtain a second classification output result, including: When , it indicates that the uniformity of the nozzle arrangement in this equal-diameter area is qualified; When , it indicates that the uniformity of the nozzle arrangement in this equal-diameter area is unqualified, there is a risk of uneven arrangement, and a risk warning for arrangement uniformity is triggered; Preset a third threshold Z3, and compare the aperture compensation factor of the j-th nozzle in the i-th equal-diameter area with the third threshold Z3 to obtain a third classification output result, including: When , it indicates that the aperture error of the j-th nozzle in this equal-diameter area is within the acceptable range; When , it indicates that there are potential risks of aperture deviation or blockage in the j-th nozzle in this equal-diameter area, triggering a structure risk warning.

[0039] Furthermore, the AI analysis module further includes a strategy generation unit, which is used to generate corresponding strategies according to the pressure drop risk warning, the arrangement uniformity risk warning, and the structure risk warning, including: Generate a first strategy according to the pressure drop risk warning, including: increasing the injection pressure in this equal-diameter area by 5% - 10% to enhance the liquid propulsion force and relieve the local pressure drop accumulation phenomenon; evenly adding 1 - 2 auxiliary weep holes 007 within the adjacent nozzle intervals, with the aperture set to 3mm - 5mm, to guide the fluid to split, thereby reducing the main path pressure difference; Generate a second strategy according to the arrangement uniformity risk warning, including: locally adding 1 - 3 nozzles in the equal-diameter area and re-planning the injection sequence, preferentially activating the nozzles at the center of injection in this equal-diameter area, and activating them sequentially towards the edge, with the time interval for activating the injection through holes set to 1 - 3 seconds; Generate a third strategy according to the structure risk warning, including: performing fine-tuning and hole-filling treatment on the nozzles in this equal-diameter area. For nozzles with an aperture deviation not exceeding 5%, perform grinding or reaming repair treatment; for nozzles with an aperture deviation exceeding ±10%, perform physical replacement; and mark the nozzles in this equal-diameter area as blocked nozzles, and set 1 - 2 auxiliary weep holes 007 on both sides of the blocked nozzles to guide the fluid to bypass the blockage point.

[0040] Note: The angle between two adjacent opening positions is 90 degrees. Each short section is provided with 1 auxiliary weep hole with a diameter of 10 mm, and the direction is vertically downward. In this embodiment, by using multiple machine learning algorithms such as logistic regression, support vector machine, decision tree, and random forest, the AI analysis module can accurately construct an AI analysis model for oil product blending, realizing high-precision classification and discrimination of the uniformity of oil product injection and mixing. This makes the injection process of oil products more controllable and helps ensure the quality and consistency of the final product.

[0041] Pressure drop risk warning: When the injection pressure gradient is abnormal, the system will immediately issue a pressure drop risk warning to avoid fluid flow problems caused by uneven pressure drop.

[0042] Arrangement uniformity risk warning: When it is detected that the arrangement of spray holes is uneven, the system can promptly identify the problem and issue a uniformity risk warning to prevent product quality problems caused by uneven injection.

[0043] Structure risk warning: When there are deviations in the aperture of the spray holes or potential blockage hazards, the system can effectively detect and issue a structure risk warning to avoid system failure caused by spray hole failures.

[0044] Based on the risk warning, the AI analysis module can generate specific optimization strategies to optimize the oil product injection process and improve the operation stability of the equipment. These include: By increasing the injection pressure and adding auxiliary weep holes, the system can effectively alleviate the local pressure drop phenomenon, optimize the injection uniformity, and enhance the propulsion force of the fluid. By re-planning the activation sequence of the spray holes and adding local spray holes, the system can better control the injection uniformity and avoid the influence of uneven arrangement on the injection effect. By fine-tuning, grinding, or reaming the spray holes for maintenance, the system can effectively eliminate the aperture error and replace the spray holes when the aperture deviation is too large to ensure that the injection effect is not affected.

[0045] Example 6, please refer to Figure 2 and Figure 3 , a mixer for high-quality oil product blending, comprising: A tank body 001 for containing oil product raw materials of different components; A mixer assembly 002, arranged 500 mm above the inner bottom of the tank body 001, comprising: A main liquid supply pipe 003, which is a DN200 stainless steel pipe; Multiple connected branch pipes 004, including several DN65 stainless steel pipes and several branch pipes 004 provided with spray holes 005; the main liquid supply pipe 003 is connected to the multiple connected branch pipes 004; A plurality of spray holes 005 are provided on the branch pipe 004, and the diameter of the spray holes 005 increases with the increase of the branch pipe 004 and the main liquid supply pipe 003, so as to compensate for the pressure loss and realize uniform spraying; at least one section of corrugated flexible connecting pipe 006 is used to avoid the installation difficulties caused by the rigid connection; the pipeline of the mixer assembly 002 is configured to realize the injection of different components of oil products from the main liquid supply pipe 003 in sequence, and evenly inject them into the tank body 001 through the spray holes 005, so as to realize the uniform blending of the oil products; Multiple groups of control valves are respectively set at the injection inlets of different components; A PLC controller or industrial computer, used to control the opening and closing of the valve according to preset recipe parameters; The liquid level sensor is installed inside the tank to monitor the oil level in real time; The ratio algorithm module calculates the required raw material injection amount according to the real-time liquid level change and the set ratio; The central control module works in conjunction with the mixer to control the injection ratio of each component within a raw material injection height range of 10 meters, and complete the final blending within the 2-3 meter adjustment space at the top of the tank, thereby producing qualified oil products.

[0046] It should be noted that all calculation formulas in this application document use regression analysis including but not limited to machine learning algorithms to deeply analyze the relevant parameters collected and identify their natural trends and relationships. Use professional software such as Python's Scikit-learn library or R language to automatically generate mathematical models that match the data. Then, objectively evaluate the performance of the model through methods such as cross-validation, and combine continuous feedback and optimization to ensure that the created formula truly reflects the inherent laws of the data, thereby ensuring its effectiveness and accuracy, and ensuring that the calculation process complies with the constraints of natural laws rather than based on artificially set rules.

[0047] The technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of the various embodiments of the present invention.

[0048] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite ordered listing of executable instructions for implementing logical functions, and can be embodied specifically in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device or in connection with these instruction execution systems, apparatus, or devices.

[0049] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A control system for high-quality oil product blending, characterized in that Including: The central control module monitors the injection pressure data and concentration data of the injection holes in different injection stages in real time, and equally divides the paragraphs with the same aperture in the main pipeline into several same-diameter regions to construct the injection pressure gradient index of the i-th same-diameter region and the comprehensive coefficient of variation , and based on the Bernoulli equation, constructs the aperture compensation factor of the j-th injection hole in the i-th same-diameter region , and after constructing and training the oil blending AI analysis model, inputs the injection pressure gradient index and the comprehensive coefficient of variation of the i-th same-diameter region, as well as the aperture compensation factor of the j-th injection hole in the i-th same-diameter region into the oil blending AI analysis model, and generates corresponding strategies according to its classification output results and the corresponding classification output results 2. The control system for blending high-quality oil products according to claim 1, wherein: The central control module includes: An injection monitoring module is used to collect and obtain the injection pressure data of each injection hole at different injection stages, collect the distance between each injection hole and the main pipe, and collect the actual aperture size data of each injection hole, establish a first data set, establish and train a pressure response model using neural network technology, and construct an injection pressure gradient index for the i-th same-diameter region based on the first data set ; The injection monitoring module includes a same-diameter area division unit and a pressure acquisition unit; The same-diameter area division unit is used for the orifice section with the same designed orifice diameter on the main pipe, divided into one same-diameter section, including a same-diameter section with a plurality of orifices with a diameter of 18 mm or 22 mm arranged continuously; In each same-diameter segment, divide it according to the total number of same spray holes to form multiple same-diameter regions; set the length of each same-diameter segment as L. There are N spray holes in this same-diameter segment. Divide the layout of the spray holes in this same-diameter segment equally into M same-diameter regions, and the expression is ; where K is the number of spray holes contained in each same-diameter region; The pressure acquisition unit is used to set pressure sensors at several orifices of the oil mixer to obtain injection pressure data at different injection stages; and collect the distance between each orifice and the main pipe and the actual orifice diameter size data of each orifice, and establish a first data set, the first data set includes: Total pressure at the branch pipe inlet , pressure drop at the j-th orifice in the i-th same-diameter region , total number of orifices in the i-th same-diameter region , length of the i-th same-diameter region and distance of the j-th orifice from the starting point in this same-diameter region .

3. The control system for blending high-quality oil products according to claim 2, characterized in that: The injection monitoring module further includes a pressure model establishment unit; The pressure model establishment unit is used to build an initial convolutional neural network model by using a convolutional neural network, train and test the initial convolutional neural network model with a first data set, and use the trained initial convolutional neural network model as a pressure response model to build the injection pressure gradient index of the i-th same-diameter region , and the acquisition steps include: S11. In each same-diameter area, obtain the axial position coordinates of all spray holes on the branch pipe, and establish a spray hole coordinate data set: , to represent the coordinate positions of the 1st to the th spray holes in the i-th same-diameter area, which are obtained from CAD drawings, construction design drawings or actual installation measurements; S12. Calculate the actual distance between all adjacent spray holes in the \(i\)-th same-diameter region using the coordinate difference, and calculate the spacing. The expression is: ; thus, obtain the spray hole spacing data set of the \(i\)-th same-diameter region: ; S13. Obtain the data set of the nozzle pitch in the \(i\)-th same-diameter region according to S12, and calculate the average nozzle pitch and the standard deviation in the \(i\)-th same-diameter region and standard deviation : S14. According to the average spacing and the standard deviation of the i-th same-diameter region, the nozzle arrangement uniformity factor of the i-th same-diameter region is calculated by the following formula : When , it indicates that the arrangement of the same-diameter area meets the uniform standard. When , it indicates that the arrangement of the same-diameter area does not meet the uniform standard, and there is a risk of affecting the mixing effect, triggering the first warning instruction, including: adjusting the nozzle spacing by ±3% - ±5% and reducing the overall injection flow rate by 5% - 10% until ; When , it indicates that the arrangement of the same-diameter area does not meet the uniform standard, indicating a risk of uneven arrangement height, triggering a second warning instruction, including: adjusting the nozzle spacing by ±10% - ±20%, and reducing the overall injection flow rate by 11% - 20% until is reached, and then restoring the normal injection flow rate; S15. After the first warning instruction and the second warning instruction are executed, extract the total pressure at the inlet of the branch pipe in the first dataset , the pressure drop of the j-th nozzle hole in the i-th same-diameter area , the total number of nozzle holes in the i-th same-diameter area , the length of the i-th same-diameter area and the distance of the j-th nozzle hole from the starting point in this same-diameter area , combined with the nozzle hole layout uniformity factor of the i-th same-diameter area , calculate and obtain the jet pressure gradient index of the i-th same-diameter area through the following formula : In the formula represents the adjusted position-sensitive weight, set to 1 - 2; represents the uniformity empirical weight, set to 0.1 - 0.

5.

4. The control system for blending high-quality oil products according to claim 3, wherein: The central control module further includes: The index fluctuation analysis module is used to set multiple groups of oil sampling points in the tank where the mixer is located, regularly detect the oil concentration and related indicators at different spatial positions in each same-diameter area, establish a spatial index data set, and construct the comprehensive coefficient of variation of the i-th same-diameter area , which is used to evaluate the uniformity of the oil after mixing; The index fluctuation analysis module includes an index acquisition unit, which is used to install a vibrating tube densitometer, a concentration sensor, and a micro closed cup flash point tester in several isodiametric regions of the oil mixer, and collect and obtain the octane number X of the ith isodiametric region i , the oil density , the dynamic viscosity of the oil and the flash point i , and construct a spatial index data set.

5. The control system for blending high-quality oil products according to claim 4, wherein: The index fluctuation analysis module further includes an index anomaly analysis unit, which is used to establish a spatial index data set to construct the comprehensive variation coefficient of the i-th same-diameter area , and the acquisition steps include: S21. Extract the spatial index data set, calculate each index of the i-th same-diameter area respectively, and obtain the average value and standard deviation of each index: S22. Calculate the coefficient of variation for each indicator respectively to obtain the coefficient of variation of the octane number for the i-th same-diameter region , the coefficient of variation of the oil density , the coefficient of variation of the dynamic viscosity of the oil and the coefficient of variation of the oil density : In the formula, is the average value of the octane number in the i-th same-diameter region, representing the central tendency of the octane number in this same-diameter region; is the standard deviation of the octane number in the i-th same-diameter region, indicating the fluctuation range of the octane number, that is, the degree to which the octane numbers at each measurement point deviate from the average value; The larger it is, the stronger the volatility of the octane number and the more uneven the mixing; is the average value of the oil density in the i-th same-diameter region, representing the central tendency of the oil density in this same-diameter region; is the standard deviation of the oil density in the i-th same-diameter region, representing the fluctuation range of the oil density, that is, the degree to which the oil density values at each measurement point deviate from the average value; The larger it is, the stronger the fluctuation of the oil density in this same-diameter region and the more uneven the mixing; is the average value of the dynamic viscosity of the oil product in the i-th same-diameter region, representing the central tendency of the dynamic viscosity of the oil product in this same-diameter region; is the standard deviation of the dynamic viscosity of the oil product in the i-th same-diameter region, representing the fluctuation range of the dynamic viscosity of the oil product, that is, the degree to which the dynamic viscosity values of the oil product at each measurement point deviate from the average value; The larger it is, the stronger the fluctuation of the dynamic viscosity of the oil product in this same-diameter region and the more uneven the mixing; is the average flash point of the oil products in the i-th same-diameter region, representing the central tendency of the flash points of the oil products in this same-diameter region; is the standard deviation of the flash points of the oil products in the i-th same-diameter region, representing the fluctuation range of the flash points of the oil products, that is, the degree to which the flash point values of the oil products at each measurement point deviate from the average value; The larger it is, the stronger the fluctuation of the flash point of the oil products in this same-diameter region and the more uneven the mixing; S23. Combine the coefficient of variation of octane number in the \(i\)th same-diameter region , the coefficient of variation of oil density , the coefficient of variation of dynamic viscosity of oil and the coefficient of variation of oil density , and calculate the comprehensive coefficient of variation of the \(i\)th same-diameter region through the following formula : In the formula, represents the weight coefficient of the k-th index, represents the coefficient of variation of the k-th index in the i-th co-diameter region, including the coefficient of variation of the octane number in the i-th co-diameter region , the coefficient of variation of the oil density , the coefficient of variation of the dynamic viscosity of the oil and the coefficient of variation of the oil density .

6. The control system for blending high-quality oil products according to claim 5, wherein: The central control module further includes an orifice diameter compensation prediction module; The aperture compensation prediction module is used to collect and construct, based on Bernoulli's equation, the aperture compensation factor of the j-th nozzle hole in the i-th same-diameter region, which is used to characterize the degree of deviation of the actual nozzle hole structure from the design target; The orifice diameter compensation prediction module includes an orifice diameter data acquisition unit; The aperture data acquisition unit is used to obtain the aperture sizes of each injection hole after actual installation, and collect the designed aperture of the j-th nozzle in the i-th same-diameter area , the actual injection flow rate , the total pressure at the branch pipe inlet and the outlet pressure of the j-th injection hole in the i-th same-diameter area , and extract the oil density of the i-th same-diameter area in the spatial index dataset , and construct a second dataset.

7. A control system for blending high-quality oil products according to claim 6, characterized in that: The orifice diameter compensation prediction module further includes an orifice blockage prediction unit; The aperture blockage prediction unit is configured to construct an aperture compensation factor for the j-th nozzle hole in the i-th same-diameter region according to the second data set, based on Bernoulli's equation and the principle of continuity. , and the specific steps include: S31. Calculate the theoretical aperture of the j-th nozzle in the i-th same-diameter region according to Bernoulli's equation and the principle of continuity , and the specific steps are as follows: S311. According to the actual injection flow rate of the j-th nozzle in the i-th same-diameter area collected , the differential pressure between the inlet and outlet and the oil density , the orifice flow formula is used as follows: wherein, is the actual cross-sectional area of the j-th nozzle in the i-th same-diameter area; Inverse solution to obtain the theoretical orifice cross-sectional area of the j-th nozzle in the i-th same-diameter region : S312. When the spray hole is set as a standard round hole, further obtain the theoretical aperture of the j-th spray hole in the i-th same-diameter area. : S32. Combine the designed aperture of the j-th nozzle in the i-th same-diameter region and the theoretical aperture of the j-th nozzle hole in the i-th same-diameter region , and calculate the aperture compensation factor of the j-th nozzle hole in the i-th same-diameter region through the following formula : 。 8. A control system for blending high-quality oil products according to claim 7, characterized in that: The central control module further includes an AI analysis module; The AI analysis module includes an evaluation model establishment unit, a training unit and a classification result unit; The evaluation model establishment unit is used to construct an AI analysis model for oil product blending to classify and discriminate the uniformity of oil product injection mixing by using one or more of logistic regression, support vector machine, decision tree, random forest, or ensemble learning algorithm as the classifier basis; The training unit is used to extract the injection pressure gradient index of the i-th same-diameter region and the comprehensive coefficient of variation as well as the aperture compensation factor of the j-th nozzle hole in the i-th same-diameter region and train the sample data set, where the sample data set includes: The injection pressure gradient index of the i-th same-diameter region , which is used to characterize the change characteristics of the pressure drop per unit length in this same-diameter region; The comprehensive coefficient of variation of the i-th same-diameter region , which is used to measure the degree of uniformity fluctuation of the nozzle hole arrangement; The aperture compensation factor of the j-th nozzle in the i-th same-diameter region , which is used to reflect the deviation degree between the actual nozzle and the target aperture and whether there is a risk of blockage; The classification result unit inputs the aggregated sample number into the trained AI analysis model for oil product blending to obtain a classification output result, including: Preset a first threshold Z1, and compare the injection pressure gradient index of the i-th same-diameter region with the first threshold Z1 to obtain a first classification output result, including: When , it indicates that the pressure drop distribution in the same-diameter area is qualified; When , it indicates that the pressure drop distribution in this same-diameter area is abnormal, triggering a pressure drop risk warning; Preset a second threshold Z2, and compare the comprehensive coefficient of variation of the i-th same-diameter region with the second threshold Z2 to obtain a second classification output result, including: When , it indicates that the nozzle arrangement uniformity in the same-diameter area is qualified; When , it indicates that the nozzle arrangement uniformity in this same-diameter area is unqualified, there is a risk of uneven arrangement, and a risk warning for arrangement uniformity is triggered; Preset a third threshold Z3, and the aperture compensation factor of the j-th nozzle in the i-th same-diameter region Compare with the third threshold Z3 to obtain a third classification output result, including: When , it indicates that the aperture error of the j-th nozzle in this same-diameter area is within the acceptable range; When , it indicates that there is a risk of aperture deviation or blockage in the j-th spray hole of this same-diameter area, triggering a structural risk warning.

9. The control system for blending high-quality oil products according to claim 8, wherein: The AI analysis module further includes a strategy generation unit, and the strategy generation unit is used to generate corresponding strategies according to the pressure drop risk warning, layout uniformity risk warning and structure risk warning, including: According to the pressure drop risk warning, generate a first strategy, including: increasing the injection pressure in this same-diameter area by 5% - 10% to enhance the liquid propulsion force and relieve the local pressure drop accumulation phenomenon; evenly adding 1 - 2 auxiliary weep holes within the adjacent orifice intervals, with the orifice diameter set to 3 mm - 5 mm, to guide the fluid diversion, thereby reducing the main path pressure difference; According to the layout uniformity risk warning, generate a second strategy, including: locally adding 1 - 3 orifices in the same-diameter area and re-planning the injection sequence, preferentially activating the orifices at the injection center of this same-diameter area, and activating them in sequence from the center to the edge, with the activation time interval of the through holes set to 1 - 3 seconds; According to the structure risk warning, generate a third strategy, including: performing fine-tuning and hole compensation treatment on the orifices in this same-diameter area, for orifices with an orifice diameter deviation not exceeding 5%, performing grinding or reaming repair treatment; for orifices with an orifice diameter deviation exceeding ±10%, performing physical replacement; and marking the orifices in this same-diameter area as blocked orifices, and setting 1 - 2 auxiliary weep holes on both sides of the blocked orifices to guide the fluid to bypass the blockage point.

10. A mixer for blending high-quality oil products, characterized in that: A control system for high-quality oil product blending for implementing any one of claims 1 - 9, including: A tank for containing oil product raw materials of different components; The mixer assembly is located 500 mm above the bottom of the tank and includes: The main liquid supply pipe is a DN200 stainless steel pipe; Multiple interconnected branch pipes, including several DN65 stainless steel pipes and several branch pipes equipped with spray holes; A plurality of spray holes are provided on the branch pipe, and the diameter of the spray holes increases as the distance from the branch pipe increases, so as to compensate for the pressure loss and realize uniform spraying; at least one section of corrugated flexible connecting pipe is used to avoid the installation difficulties caused by the rigid connection; the pipeline of the mixer assembly is configured to realize that different components of oil products are injected from the main supply pipe in sequence, and are uniformly injected into the tank body through the spray holes, so as to realize uniform blending of the oil products; Multiple groups of control valves are respectively set at the injection inlets of different components; A PLC controller or industrial computer, used to control the opening and closing of the valve according to preset recipe parameters; The liquid level sensor is installed inside the tank to monitor the oil level in real time; The ratio algorithm module calculates the required raw material injection amount according to the real-time liquid level change and the set ratio; The central control module works in conjunction with the mixer to control the injection ratio of each component within a raw material injection height range of 10 meters, and complete the final blending within the 2-3 meter adjustment space at the top of the tank, thereby producing qualified oil products.

Images