Grease production control method and system based on intelligent digitization

Abstract

The invention relates to the technical field of grease production, in particular to a grease production control method and system based on intelligent digitization. The method comprises the following steps: acquiring grease material data, and performing processing demand analysis according to the grease material data so as to obtain oil processing demand data; acquiring a hydraulic press model; inputting the oil treatment demand data into the hydraulic press model, carrying out squeezing simulation, and carrying out low-grease extraction rate statistics on a squeezing simulation result to obtain a low-grease extraction rate; performing oil impurity analysis on the oil material according to the low oil extraction rate to generate oil impurity data; performing filter grease accumulation analysis on the hydraulic press model according to the oil impurity data to generate filter grease accumulation data; squeezing data of the spiral oil press are obtained, oil residue content analysis is carried out, and therefore high oil residue content data are obtained. Based on the grease production technology, the grease extraction rate and the production efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of oil production, and in particular to an oil production control method and system based on intelligent digitalization. Background Art

[0002] Traditional methods rely on manual operation and empirical judgment, lacking intelligent real-time data feedback and automated adjustments, resulting in the inability of temperature, pressure and other control parameters in the production process to accurately match the processing requirements of oil materials, thus affecting oil extraction rate and production efficiency. Due to the lack of intelligent oil production scheduling, energy and materials are often wasted in the production process, especially in the oil processing and pressing process, and various parameters are not optimized according to real-time data, resulting in high production costs. In the traditional oil production process, the control of temperature and pressure relies on preset rules or experience, and fails to make personalized adjustments according to the actual needs of different batches of oil materials, which can easily lead to unstable oil quality and affect the quality of the final product. In the oil production process, the problem of oil accumulation in the filter is often unable to be monitored and controlled in time, resulting in equipment blockage, affecting the continuity and efficiency of production. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide an oil production control method and system based on intelligent digitalization to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a method for controlling oil production based on intelligent digitalization comprises the following steps:

[0005] Step S1: Obtaining oil material data, and performing processing demand analysis based on the oil material data, thereby obtaining oil processing demand data;

[0006] Step S2: obtaining a hydraulic press model; inputting the oil processing demand data into the hydraulic press model, performing a pressing simulation, and performing low oil extraction rate statistics on the pressing simulation results to obtain a low oil extraction rate; performing an oil impurity analysis on the oil material according to the low oil extraction rate to generate oil impurity data; performing a filter oil accumulation analysis on the hydraulic press model according to the oil impurity data to generate filter oil accumulation data;

[0007] Step S3: Acquire the pressing data of the screw oil press and perform oil residue content analysis to obtain high oil residue content data; perform intelligent pressing temperature control according to the high oil residue content data to obtain intelligent pressing temperature control data;

[0008] Step S4: Perform intelligent production scheduling according to the oil processing demand data and the filter grease accumulation data to obtain intelligent production data; upload the intelligent production data and the pressing intelligent temperature control data to the intelligent control system to execute the grease production control task.

[0009] The present invention can realize accurate characteristic identification of oil materials by acquiring oil material data and performing processing demand analysis, provide data basis for subsequent optimization of process parameters, help formulate more reasonable processing plans according to material characteristics, and reduce unnecessary waste of resources. By using a hydraulic press model for pressing simulation, the problem of low oil extraction rate can be quickly discovered by statistically analyzing the oil extraction rate under different pressing conditions, and oil impurity data can be generated by detailed analysis of oil impurities, providing targeted improvement directions for further optimization of the pressing process. Combined with the filter oil accumulation analysis, the oil accumulation inside the filter can be accurately monitored, so that maintenance and cleaning can be carried out in time to avoid equipment blockage caused by accumulation, and ensure the continuity and efficiency of the production process. Obtaining the pressing data of the screw oil press and analyzing the oil residue content can effectively evaluate the changes in the residue content during the oil extraction process, dynamically adjust the intelligent temperature control of the pressing process according to the analysis results, further improve the oil extraction efficiency and reduce energy consumption. At the same time, by realizing intelligent production scheduling, combining oil processing demand data with filter grease accumulation data, it is possible to optimize the allocation of production tasks and resource utilization, avoid equipment overload or idle problems, and significantly improve overall production efficiency. In addition, uploading intelligent production data and pressing intelligent temperature control data to the intelligent control system ensures the efficiency and accuracy of the production process through the system's automated control, further improving the quality of oil products and the economic efficiency of production.

[0010] Optionally, step S1 specifically includes:

[0011] Step S11: Obtaining oil material data and performing spectral analysis to obtain oil spectrum data;

[0012] Step S12: evaluating the oil content according to the oil spectrum data, thereby obtaining oil content data;

[0013] Step S13: measuring the moisture content of the oil content data to obtain moisture content data;

[0014] Step S14: performing impurity content analysis according to the moisture content data, thereby obtaining impurity content data;

[0015] Step S15: Perform oil processing demand analysis based on the impurity content data to obtain oil processing demand data.

[0016] The present invention obtains spectral data of oil materials through spectral analysis, can accurately judge the composition and quality characteristics of oils, avoids the shortcomings of relying on artificial experience judgment in traditional methods, and provides more accurate raw material information. This process provides a scientific basis for subsequent oil content evaluation, can monitor the true content of oils in real time, ensures that the use of raw materials in the production process is more efficient, and avoids waste or shortage caused by inaccurate oil content. By measuring the moisture content of the oil content data, the moisture state of the oil material can be further judged, which provides an important reference for the subsequent impurity content analysis, helps to accurately identify the moisture content in the material, and avoids the influence of too much or too little water on the pressing process. On this basis, the impurity content analysis based on the moisture content data can effectively evaluate the impurity content of the oil material, thereby providing a basis for the demand analysis of oil processing. It avoids the neglect of impurity content in traditional methods, makes the oil processing demand more accurate, and reduces the phenomenon of reduced oil extraction rate or reduced production efficiency due to impurity problems. Through intelligent analysis, processing parameters can be adjusted in a timely manner according to the actual needs of the oil, effectively improving the oil extraction rate and production efficiency, and reducing energy and material waste, ensuring the efficiency, stability and sustainability of the production process.

[0017] Optionally, step S11 specifically includes:

[0018] Step S111: Obtaining oil material data and performing near infrared spectrum sampling to obtain oil near infrared spectrum data;

[0019] Step S112: performing baseline correction on the oil near-infrared spectrum data to obtain oil near-infrared spectrum correction data;

[0020] Step S113: obtaining oil absorption peak data;

[0021] Step S114: performing position identification on the oil near-infrared spectrum correction data according to the oil absorption peak data, thereby obtaining the oil absorption peak position data;

[0022] Step S115: performing intensity statistics on the oil absorption peak position data, thereby obtaining oil absorption peak intensity data;

[0023] Step S116: constructing a fat content prediction model according to the fat absorption peak intensity data, thereby obtaining a fat content prediction model;

[0024] Step S117: predicting the fat content of the fat material data according to the fat content prediction model, thereby obtaining fat content data;

[0025] Step S118: Perform spectral measurement on the oil content data to obtain oil spectrum data.

[0026] The present invention can accurately capture the chemical characteristics of oils and fats by acquiring oil material data based on near-infrared spectroscopy sampling, avoid the limitations of relying on manual experience in traditional methods, and ensure the high accuracy of data acquisition. Baseline correction processes the near-infrared spectral data of oils and fats, thereby eliminating interference caused by equipment or environmental changes, improving the reliability and accuracy of spectral data, and providing a clearer basis for subsequent analysis. By acquiring oil absorption peak data and identifying its position, the key component characteristic peaks in oils and fats can be accurately located, further improving the accuracy and pertinence of oil analysis. The statistics of absorption peak intensity provide important data support for establishing an accurate oil content prediction model, so that the model can be optimized based on actual measurement results, thereby improving the accuracy of oil content prediction. By applying the oil content prediction model, the actual content of oil materials can be accurately predicted, the error in manual measurement is reduced, and a scientific basis is provided for the subsequent processing of oils and fats. At the same time, based on the accurate results of the oil content prediction model, spectral measurement can further verify the accuracy of the prediction and ensure that the oil spectrum data finally obtained has high efficiency and stability. Through intelligent analysis and real-time data feedback, various operations in the production process are optimized, effectively avoiding the shortcomings of traditional methods that cannot accurately adjust parameters, improving oil extraction rate and production efficiency, and reducing energy and material waste.

[0027] Optionally, step S112 is specifically:

[0028] Identify the non-absorption peak region of the oil near-infrared spectrum data to obtain the non-absorption peak region data;

[0029] Baseline point selection is performed according to the data of the region without absorption peak, thereby obtaining baseline point data;

[0030] Get the cubic polynomial fitting model;

[0031] Performing polynomial baseline fitting on the baseline point data according to a cubic polynomial fitting model to generate polynomial fitting baseline data;

[0032] The near-infrared spectrum data of oil and fat are baseline corrected according to the polynomial fitting baseline data, so as to obtain the near-infrared spectrum correction data of oil and fat.

[0033] The present invention can effectively eliminate unnecessary data caused by noise or interference factors in the spectral data by identifying the non-absorption peak area of ​​the near-infrared spectrum data of oils and fats, and improve the accuracy of data analysis. The acquisition of the non-absorption peak area data provides a scientific basis for further baseline point selection, avoids the fuzzy judgment relying on artificial experience in the traditional method, and ensures that the selection of the baseline point is more accurate. Through the application of the cubic polynomial fitting model, the baseline point data can be accurately fitted with a polynomial baseline, thereby avoiding the error caused by simple linear fitting and improving the accuracy and stability of baseline correction. Based on this accurate polynomial fitting baseline data, the baseline correction of the near-infrared spectrum data of oils and fats is further performed, so that the final oil spectrum data is more accurate after removing the baseline drift and other interference factors, and provides a reliable data basis for the subsequent oil component analysis. Not only does it optimize the data processing process in the traditional method, avoid human operation errors, but it can also automatically adjust according to real-time data, improve the processing efficiency of oil materials in the production process, avoid the defects that the control parameters such as temperature and pressure in the traditional method cannot be accurately matched, and thus improve the oil extraction rate, production efficiency and the quality of the final product.

[0034] Optionally, step S2 specifically includes:

[0035] Step S21: obtaining a hydraulic press model;

[0036] Step S22: input the oil processing demand data into the hydraulic press model, perform a pressing simulation, and perform low oil extraction rate statistics on the pressing simulation results to obtain the low oil extraction rate;

[0037] Step S23: screening the oil material according to the low oil extraction rate to obtain the low oil material;

[0038] Step S24: performing impurity mass spectrometry analysis on the low-fat material to generate an impurity mass spectrum;

[0039] Step S25: identifying high-impurity oil material from low-oil material according to the impurity mass spectrum, thereby obtaining high-impurity oil material;

[0040] Step S26: Analyze the filter grease accumulation on the hydraulic press model according to the high-impurity grease material to generate filter grease accumulation data.

[0041] The present invention can accurately simulate the processing process of oil materials by obtaining a hydraulic press model and inputting the oil processing demand data into the model for pressing simulation, thereby ensuring the optimization of oil extraction rate and production efficiency during the pressing process. The low oil extraction rate statistics of the pressing simulation results are helpful to quickly identify low-oil materials in the early stage of production and remove them, avoid inefficient materials from participating in subsequent processing, and improve the overall oil extraction effect. Screening low-oil materials further improves the selectivity of oil materials and ensures the high quality of materials in subsequent processing. Impurity mass spectrometry analysis can accurately detect the impurity components in oil materials, generate detailed impurity mass spectra, provide more accurate data support, and help achieve effective identification of high-impurity oil materials. This process can timely discover and screen out high-impurity oil materials, thereby avoiding production interruptions or equipment damage caused by impurity problems. By identifying high-impurity oil materials and combining filter oil accumulation analysis, it is possible to predict and deal with the accumulation of oil in the filter in advance, avoid equipment blockage, and maintain smooth operation of the production line. Ultimately, these steps optimize the oil production process through intelligent analysis and processing, reduce human intervention, significantly improve production efficiency, reduce production costs, and ensure the stability and quality of the oil.

[0042] Optionally, step S24 is specifically:

[0043] Step S241: performing direct mass spectrometry on the low-fat material using a mass spectrometer to obtain mass spectrum data of the low-fat material;

[0044] Step S242: performing parent ion identification on the mass spectrum data of the low-fat material to obtain parent ion data;

[0045] Step S243: obtaining a parent ion spectrum library;

[0046] Step S244: performing a comparison of the parent ion data with the parent ion of the emulsion residue according to the parent ion spectral library to obtain the emulsion residue data;

[0047] Step S245: performing mass-to-charge ratio identification on the low-fat material mass spectrum data according to the emulsion residue data, thereby obtaining mass-to-charge ratio data;

[0048] Step S246: performing intensity peak recognition on the emulsion residue data according to the emulsion residue data, thereby obtaining intensity peak data;

[0049] Step S247: Draw an impurity mass spectrum according to the mass-to-charge ratio data and the intensity peak data to obtain an impurity mass spectrum.

[0050] The present invention can accurately obtain the mass spectrum data of the material by using a mass spectrometer to perform direct mass spectrometry analysis on the low-fat material, and further provide detailed information for subsequent analysis. The parent ion identification of the mass spectrum data helps to quickly determine the main components in the material, laying the foundation for the next step of component analysis. By obtaining the parent ion spectral library and comparing it with the data, the emulsion residue can be accurately identified, so as to have a deep understanding of the impurity components in the oil material. The acquisition of the emulsion residue data can identify potential problems in the oil material in a targeted manner and provide a strong basis for optimizing the production process. On this basis, the mass-to-charge ratio identification of the mass spectrum data of the low-fat material can help extract the mass and charge information of the substance, so as to further analyze the component distribution and structural characteristics in the material. The identification of the intensity peak helps to quantify the distribution and concentration of impurities, and provides specific data support for subsequent impurity processing. Finally, by combining the mass-to-charge ratio data with the intensity peak data to draw the impurity mass spectrum, the impurity components in the material can be fully displayed, and accurate visual data can be provided for oil purification and quality control in the production process, ensuring the stability and high-quality output of the oil material during the processing process. It effectively reduces manual intervention, improves analysis accuracy, ensures efficient, accurate and low-cost operation of the production process, and ensures the stability of oil quality.

[0051] Optionally, step S26 is specifically:

[0052] Step S261: placing the high-impurity grease material into the hydraulic press model and performing filtration simulation to generate hydraulic press filtration data;

[0053] Step S262: performing efficiency statistics on the hydraulic press filtering data, thereby obtaining low-efficiency hydraulic press filtering data;

[0054] Step S263: Obtain filter data and filter clogging threshold;

[0055] Step S264: performing real-time monitoring of the surface accumulation of the filter data according to the filtering data of the low-efficiency hydraulic press, thereby obtaining the surface accumulation data of the filter;

[0056] Step S265: Calculating the accumulation rate of the filter surface accumulation data to obtain the filter accumulation rate;

[0057] Step S266: dividing the filter surface accumulation data into blockage groups according to the filter blockage threshold, thereby obtaining the filter surface blockage data;

[0058] Step S267: performing rate statistics on the filter accumulation rate to obtain high-rate filter accumulation data;

[0059] Step S268: Counting the blockage degree of the filter surface blockage data, thereby obtaining the filter surface serious blockage data;

[0060] Step S269: Perform grease accumulation intersection operation based on the high-rate filter accumulation data and the filter surface severe blockage data to generate filter grease accumulation data.

[0061] The present invention can obtain accurate hydraulic press filtering data by placing high-impurity grease materials into a hydraulic press model and performing filtering simulation, thereby providing a scientific basis for subsequent operation and optimization. By performing efficiency statistics on these data, low-efficiency filtering situations can be identified, thereby further optimizing the production process and reducing resource waste. By obtaining filter data and setting a filter blocking threshold, early warning can be provided for blocking problems that occur in actual production. Real-time monitoring of surface accumulation of low-efficiency hydraulic press filtering data helps to track the grease accumulation of the filter in real time and provide dynamic feedback for problems in the filtering process. Rate calculation of accumulation data can accurately evaluate the speed of grease accumulation, thereby helping to predict in advance and take preventive measures to avoid the occurrence of blocking problems. Blockage division of accumulation data based on filter blocking thresholds enables accurate identification of areas that cause equipment blocking in actual operation, providing effective guidance for equipment maintenance. Statistical analysis of high-rate filter accumulation data can timely discover filters that accumulate too quickly, and take effective measures to reduce equipment loss. At the same time, by performing blockage degree statistics on filter surface blocking data, the operating status of the equipment can be accurately evaluated, thereby helping to arrange cleaning and maintenance in a timely manner and ensuring the stability of the production process. Finally, through the intersection operation of oil accumulation, the overall accumulation of the filter can be comprehensively evaluated, providing scientific decisions to improve filtration efficiency and equipment life, ensuring efficient and stable operation of equipment in the oil production process, reducing production costs, and improving oil extraction efficiency and product quality. By making full use of data analysis and real-time monitoring, the oil processing and pressing process is optimized, intelligent and automated management is achieved, manual intervention is reduced, and the continuity and stability of production are improved.

[0062] Optionally, step S3 specifically includes:

[0063] Step S31: acquiring the pressing data of the screw oil press, and collecting the oil sample of the screw oil press according to the pressing data of the screw oil press to obtain the oil sample of the screw oil press;

[0064] Step S32: extracting the oil residue of the screw oil press oil sample using a Soxhlet extractor to obtain an oil residue sample;

[0065] Step S33: performing oil residue content statistics according to the oil residue sample, thereby obtaining high oil residue content data;

[0066] Step S34: Perform intelligent pressing temperature control according to the high oil residue content data, thereby obtaining intelligent pressing temperature control data.

[0067] The present invention can accurately obtain representative samples by obtaining the squeezing data of the screw oil press and collecting oil samples according to these data, thereby providing a basis for subsequent oil quality analysis. Using a Soxhlet extractor to extract oil residue from oil samples can effectively separate oil and oil residue, ensure that the extracted oil is purer, and further improve the extraction rate and quality of oil. The oil residue content of the oil residue sample is statistically analyzed to accurately understand the situation of the oil residue content, thereby providing data support for subsequent process optimization and avoiding excessive oil residue affecting the quality of oil. By implementing intelligent temperature control of squeezing according to high oil residue content data, the temperature control in the squeezing process can be dynamically adjusted according to the actual oil residue content, ensuring that the temperature matches the actual needs of the oil material, thereby improving the extraction efficiency of the oil and the quality of the final product. By introducing an intelligent temperature control system, various parameters in production can be adjusted in real time, avoiding energy waste and oil quality fluctuations caused by inaccurate temperature control, reducing dependence on manual operation, and improving production stability and efficiency. Effectively combining real-time data feedback and automatic adjustment, not only optimizes the production process, reduces production costs, but also improves the overall extraction efficiency of oil, ensuring the high efficiency, energy saving and sustainability of the production process.

[0068] Optionally, step S34 is specifically:

[0069] Step S341: analyzing the material pressing conditions according to the high oil residue content data, thereby obtaining pressing condition data;

[0070] Step S342: evaluating the temperature adjustment requirement of the pressing condition data, thereby obtaining temperature adjustment requirement data;

[0071] Step S343: Designing an intelligent temperature control algorithm based on the temperature adjustment requirement data to generate temperature control algorithm data;

[0072] Step S344: Perform intelligent pressing temperature control simulation according to the temperature control algorithm data to obtain intelligent pressing temperature control data.

[0073] The present invention can accurately understand the processing requirements of different materials by analyzing the material pressing conditions according to the high oil residue content data, and then obtain the optimal conditions required in the pressing process, which provides a scientific basis for the subsequent optimization of the pressing process. The temperature adjustment demand evaluation of the pressing condition data can quantify the processing requirements of various materials at different temperatures, provide data support for the formulation of accurate temperature control schemes, and effectively avoid the problem of inaccurate temperature control caused by manual operation. Based on these demand data, an intelligent temperature control algorithm is designed, which can automatically generate the most suitable temperature control scheme according to the real-time temperature adjustment requirements, thereby ensuring that the temperature matches the oil material more accurately, improving the oil extraction rate and reducing production costs. By simulating the temperature control algorithm, its effect can be verified and further optimized, and finally a reliable temperature control scheme is generated to ensure that in actual production, temperature control can always meet the processing requirements of different oil materials, avoid unstable oil quality caused by temperature fluctuations, and at the same time improve production efficiency and reduce energy and material waste, thereby realizing an intelligent, energy-saving and efficient production process.

[0074] Optionally, the present specification also provides an intelligent digital-based grease production control system for executing the intelligent digital-based grease production control method as described above, the intelligent digital-based grease production control system comprising:

[0075] The processing demand analysis module is used to obtain oil material data and perform processing demand analysis based on the oil material data, thereby obtaining oil processing demand data;

[0076] The oil impurity analysis module is used to obtain the hydraulic press model; input the oil processing demand data into the hydraulic press model, perform pressing simulation, and perform low oil extraction rate statistics on the pressing simulation results to obtain the low oil extraction rate; perform oil impurity analysis on the oil material according to the low oil extraction rate to generate oil impurity data; perform filter oil accumulation analysis on the hydraulic press model according to the oil impurity data to generate filter oil accumulation data;

[0077] The intelligent pressing temperature control module is used to obtain the pressing data of the screw oil press and perform oil residue content analysis to obtain high oil residue content data; the intelligent pressing temperature control is performed according to the high oil residue content data to obtain the intelligent pressing temperature control data;

[0078] The intelligent production scheduling module is used to perform intelligent production scheduling according to the oil processing demand data and the filter grease accumulation data to obtain intelligent production data; the intelligent production data and the pressing intelligent temperature control data are uploaded to the intelligent control system to execute the grease production control task.

[0079] The present invention discloses an oil production control system based on intelligent digitization, which can realize any oil production control method based on intelligent digitization of the present invention, and is used to combine the operation and signal transmission medium between various modules to complete the oil production control method based on intelligent digitization. The internal modules of the system cooperate with each other, thereby improving the oil extraction rate and production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0081] Figure 1 This is a schematic diagram of the steps of the oil production control method based on intelligent digitalization of the present invention;

[0082] Figure 2 Detailed step flow diagram of step S1 in the present invention;

[0083] Figure 3 Detailed step flow diagram of step S2 in the present invention;

[0084] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0085] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0086] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0087] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0088] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for controlling oil production based on intelligent digitalization, the method comprising the following steps:

[0089] Step S1: Obtaining oil material data, and performing processing demand analysis based on the oil material data, thereby obtaining oil processing demand data;

[0090] In this embodiment, oil material data is obtained from the oil production line system, including but not limited to information such as the type, weight, oil content, moisture content and impurity content of the oil material. The obtained raw data is collected by instruments such as spectrometers and near-infrared spectrometers, especially near-infrared spectral data, which is used to analyze the oil content. The oil content is analyzed by the absorption peak position and intensity of the spectral data. The specific calculation requires identifying the characteristic wavelength and the corresponding absorption intensity value in the spectral data. According to the oil content data, the oil processing demand analysis is performed through the established linear regression model to obtain the temperature, time and pressure parameters required for oil processing. These demand data need to be expressed in specific numerical form. For example, if the oil content is higher than 85%, the processing temperature can be set to 55°C, and if the content is lower than 15%, the processing temperature can be set to 70°C.

[0091] Step S2: obtaining a hydraulic press model; inputting the oil processing demand data into the hydraulic press model, performing a pressing simulation, and performing low oil extraction rate statistics on the pressing simulation results to obtain a low oil extraction rate; performing an oil impurity analysis on the oil material according to the low oil extraction rate to generate oil impurity data; performing a filter oil accumulation analysis on the hydraulic press model according to the oil impurity data to generate filter oil accumulation data;

[0092] In this embodiment, the physical model of the hydraulic press is first obtained, and the oil processing demand data is input into the model. The input parameters of the model include oil type, oil content, impurity content, processing temperature and pressure, etc. These input data will be used to simulate the pressing process. During the simulation process, the hydraulic press model calculates the oil extraction rate according to the given pressure and temperature conditions. For the calculation of the extraction rate, a threshold standard needs to be set. For example, when the extraction rate is lower than 70%, it is considered that the oil extraction efficiency of this batch is unqualified. According to the results of the pressing simulation, the low oil extraction rate statistics are performed. When the specific statistics are performed, the extraction rate of each processed batch needs to be statistically analyzed to obtain the average value and compare it with the standard value. The impurity analysis of the oil material is performed using the low oil extraction rate results. During the analysis process, based on mass spectrometry technology, the impurity components in the oil material are quantitatively analyzed to generate oil impurity data. In the specific operation, the mass spectrum of the sample is obtained by a mass spectrometer, the main impurity substances therein are identified, and their content is calculated. If the content of a certain impurity exceeds the set critical value (such as the impurity content exceeds 5%), further processing or screening is performed. Based on the oil impurity data, the filter grease accumulation analysis of the hydraulic press model is continued. This analysis requires simulating the accumulation process of grease in the filter to obtain the rate and degree of grease accumulation. During the simulation process, physical parameters such as grease viscosity, flow rate, filter pore size, etc. are used to simulate the deposition process of grease on the filter surface. Finally, filter grease accumulation data is generated, which is used for subsequent production scheduling decisions.

[0093] Step S3: Acquire the pressing data of the screw oil press and perform oil residue content analysis to obtain high oil residue content data; perform intelligent pressing temperature control according to the high oil residue content data to obtain intelligent pressing temperature control data;

[0094] In this embodiment, real-time pressing data of the screw oil press are obtained, which include the oil residue content, oil extraction rate and other parameters related to pressing efficiency during each pressing process. By using equipment such as weighing sensors and oil flow meters, the oil residue content of the output material of the oil press is monitored in real time. By analyzing the oil residue samples, data with high oil residue content are obtained. During the analysis, the oil residue content is confirmed by a laboratory sample test method. Usually, the Soxhlet extraction method is used to extract the oil in the oil residue to determine its oil residue content. Based on the high oil residue content data, the temperature control is adjusted according to the characteristics of different oil materials to determine the optimal temperature range of the pressing process. Usually, this range is set to 50°C to 80°C. Through this data analysis, the temperature control data that needs to be adjusted is obtained, and the intelligent temperature control process for pressing is entered.

[0095] Step S4: Perform intelligent production scheduling according to the oil processing demand data and the filter grease accumulation data to obtain intelligent production data; upload the intelligent production data and the pressing intelligent temperature control data to the intelligent control system to execute the grease production control task.

[0096] In this embodiment, the obtained oil processing demand data (including oil type, quantity, material quality parameters and processing time requirements) are parsed to generate a quantifiable production task description. Based on the oil type, combined with the accumulation rate and blockage degree data provided in the filter grease accumulation data, the linear programming optimization algorithm is used to calculate the task allocation and processing priority of each device. The filter grease accumulation data should include the accumulation thickness, the percentage of filtration efficiency reduction and the deviation from the blockage threshold. With the accumulation thickness reaching 1.5 mm and the filtration efficiency decreasing by 20% as the limit, the equipment with serious accumulation will be excluded or the task load will be reduced. The intelligent scheduling module uses the industrial control computing platform to call historical operation data and real-time monitoring data, and comprehensively considers the equipment operation status, energy consumption level, current task urgency and filter status. The generated intelligent production data includes specific data files such as equipment number, processing task allocation table, temperature, pressure and time parameters required for processing, and processing schedule, in the format of XML or CSV for subsequent steps. To ensure data integrity and scheduling efficiency, the data recording frequency is set to once per minute. The aforementioned generated intelligent production data is formatted and integrated with the pressing intelligent temperature control data. The intelligent temperature control data for pressing includes a list of temperature control points, time control parameters, real-time temperature change records and adjustment thresholds. The list of temperature control points should specifically list temperature control schemes such as "75℃±1℃ for 15 minutes" or "85℃±2℃ for 10 minutes"; the time parameters must clearly specify the moment of control strategy switching to ensure that adjustments are made immediately when the temperature fluctuation exceeds ±5℃. The integrated data is uploaded to the intelligent control system via an industrial Ethernet protocol (such as Modbus TCP / IP). The system needs to have real-time monitoring and feedback functions and support the OPC UA protocol to ensure seamless connection of cross-platform data exchange. The system will generate operating instructions based on the uploaded data analysis, including equipment start and stop instructions, temperature control equipment adjustment instructions, and alarm triggering logic under abnormal conditions. For example, if the uploaded accumulation data indicates that the filter blockage rate reaches more than 50%, the system will trigger the spare filter activation instruction and prompt the replacement requirement on the display terminal. During the operation of the system, real-time status feedback is provided through sensors (temperature sensors, pressure sensors, filter accumulation sensors, etc.) installed at key parts of the equipment. The sensor data acquisition frequency is 100Hz to ensure real-time response capability in production. The uploaded data should have complete timestamp information for system logging and subsequent analysis.

[0097] Optionally, step S1 specifically includes:

[0098] Step S11: Obtaining oil material data and performing spectral analysis to obtain oil spectrum data;

[0099] In this embodiment, it is necessary to obtain the spectral data of the oil material by a near-infrared spectrometer. When using a near-infrared spectrometer, set the wavelength range of the spectrum acquisition to 1100nm to 2500nm, and adjust the light source intensity and sampling time of the instrument to ensure that the spectral data of each sample has sufficient accuracy. The processing of the oil sample needs to be carried out in a uniform state to avoid the spectral data being affected by the inhomogeneity of the material. Each sample needs to be measured at least three times independently, and the average value is taken as the final spectral data. The data reflects the spectral characteristics of the molecular absorption in the oil, and the absorption peak of the specific wavelength reflects the main components of the oil, such as fatty acids, triglycerides, etc. The measured spectral data is processed by software to obtain the specific spectral value of each oil sample as the basic data for subsequent analysis.

[0100] Step S12: evaluating the oil content according to the oil spectrum data, thereby obtaining oil content data;

[0101] In this embodiment, the oil content is evaluated based on the oil spectral data using a regression analysis method. Based on previous experimental data, a quantitative analysis model between the oil spectral data and the oil content is established. The model is usually established by the partial least squares regression (PLSR) method, in which the spectral characteristics of a specific wavelength are selected as input parameters. For each sample, the collected spectral data is compared with the existing calibration model, and the estimated value of the oil content is obtained using a regression formula. It is necessary to set an error tolerance range during the evaluation, and usually an error of less than ±0.5% is considered qualified. The obtained oil content data is usually presented in percentage form. For example, if the oil content of a certain oil sample is 78%, it means that the sample contains 78% oil components.

[0102] Step S13: measuring the moisture content of the oil content data to obtain moisture content data;

[0103] In this embodiment, a sample solution is prepared, and solvents and reagents are configured according to standard operating procedures. 50 grams of oil are used for each sample for the experiment. A known concentration of Karl Fischer reagent is added to the oil sample, and the reaction is titrated until the water is completely reacted, and the volume of the reagent consumed is recorded. The moisture content is calculated based on the ratio of the volume consumed by the reagent to the sample. At this time, the moisture content data is expressed as a percentage. If the result is 8%, it means that the sample contains 8% moisture. The determination of moisture content needs to be carried out at room temperature, and there must be no interference from other volatile substances during the experiment to ensure measurement accuracy.

[0104] Step S14: performing impurity content analysis according to the moisture content data, thereby obtaining impurity content data;

[0105] In this embodiment, the impurity content analysis of the oil material is performed based on the moisture content data. The impurity content analysis is usually performed by chemical precipitation or solvent extraction. In this step, it is first necessary to remove the moisture content in the sample to ensure the dry state of the sample. Next, add an appropriate solvent (such as n-hexane or an alcohol solvent) to extract the oil, and remove insoluble substances such as fine plant fibers and impurities by filtering after dissolution. The solvent is evaporated from the filtered solution to obtain residues of oil and impurities. Finally, the mass of the residual impurities is obtained by weighing with a precision balance, and its proportion of the total weight of the sample is calculated. This ratio is the impurity content, usually expressed as a percentage. If the impurity content exceeds the set standard value (such as 5%), the batch of oil is deemed unqualified.

[0106] Step S15: Perform oil processing demand analysis based on the impurity content data to obtain oil processing demand data.

[0107] In this embodiment, the focus is on determining the optimal oil processing process conditions based on the type and content of impurities. First, the oil processing standards under different impurity contents are set. For example, if the impurity content is less than 3%, the oil can be directly squeezed; if the impurity content is higher than 5%, pretreatment is required, such as using a separator to remove large particles of impurities, or further removal through a sedimentation tank. In this process, the optimal pretreatment time, temperature and equipment parameters are calculated through empirical formulas and experimental data. The processing demand data includes control parameters such as pressure, temperature, time, etc. at each stage, which will be used for subsequent production scheduling and oil processing procedures.

[0108] Optionally, step S11 specifically includes:

[0109] Step S111: Obtaining oil material data and performing near infrared spectrum sampling to obtain oil near infrared spectrum data;

[0110] In the present embodiment, during sampling, a near-infrared spectrometer (such as FOSS XDS series) is used to scan the grease sample. First, an appropriate wavelength range is selected, usually 1100nm to 2500nm, to capture the characteristic absorption peaks in the grease. The light source of the instrument should be set to a tungsten halogen lamp to ensure that the light source is stable and there is no fluctuation during use. Each grease sample is scanned independently at least three times by the instrument to ensure the accuracy and repeatability of the data. The scanning time during the acquisition process should be set to 5 seconds / time to ensure the accuracy of the measurement. All spectral data are recorded and stored by data acquisition software to form near-infrared spectral data of the grease material.

[0111] Step S112: performing baseline correction on the oil near-infrared spectrum data to obtain oil near-infrared spectrum correction data;

[0112] In this embodiment, the collected oil near-infrared spectrum data is baseline corrected to eliminate the influence of instrument errors and external environment on the spectrum. The baseline offset correction method is adopted, and each wavelength point is linearly regressed by software to adjust the baseline level of the original spectrum data to zero. In the specific operation, a characteristic flat interval of the wavelength range (for example, the section between 1100nm and 1300nm) is selected, and the baseline offset in the interval is calculated. Then, the offset is subtracted from each wavelength point of the entire spectrum data to obtain the baseline-corrected oil near-infrared spectrum correction data. The corrected data should have no obvious offset or fluctuation to ensure the accuracy of subsequent analysis.

[0113] Step S113: obtaining oil absorption peak data;

[0114] In this embodiment, the absorption peak data in the oil sample is extracted by analyzing the oil near-infrared spectrum calibration data. Using the spectral peak detection algorithm, the second derivative method is usually selected to highlight the peaks and troughs. The second derivative of the spectral data is calculated to identify the locations where mutations occur in the data. These mutation points are the absorption peaks. According to the known characteristics of the oil components, the absorption peaks near 3000cm-1 (such as CH vibration) and the C=O stretching vibration peak around 1700cm-1 are extracted. At each wavelength, the position of the absorption peak and its intensity data are recorded to form the oil absorption peak data as the basis for subsequent analysis.

[0115] Step S114: performing position identification on the oil near-infrared spectrum correction data according to the oil absorption peak data, thereby obtaining the oil absorption peak position data;

[0116] In this embodiment, based on the wavelength information of the absorption peak, the position of each absorption peak is marked in the original spectrum data. In specific operation, the wavelength position where the maximum absorption value of the absorption peak is located is selected as the accurate position of the absorption peak. Using the wavelength comparison function in the data processing software, the extracted absorption peak position is compared with the known standard absorption peak position, and its accurate coordinate position is determined. In this process, the threshold value set should ensure that the absorption peak error is less than 2nm, so as to obtain accurate oil absorption peak position data.

[0117] Step S115: performing intensity statistics on the oil absorption peak position data, thereby obtaining oil absorption peak intensity data;

[0118] In this embodiment, the intensity of each absorption peak is calculated, that is, the absorbance value of the absorption peak wavelength in the spectral data. When performing intensity statistics, the absorbance value at each absorption peak is first calculated, and these absorbance values ​​are statistically analyzed to obtain the intensity average value and standard deviation of each absorption peak. For example, for the absorption peak of 3000cm-1, its absorbance value is measured, and the average absorbance value is calculated in multiple samples. Through intensity statistical analysis, the relative intensity of each absorption peak can be obtained, and the stability of the absorbance can be further judged based on the standard deviation, thereby obtaining the oil absorption peak intensity data.

[0119] Step S116: constructing a fat content prediction model according to the fat absorption peak intensity data, thereby obtaining a fat content prediction model;

[0120] In this embodiment, a suitable modeling method is selected, such as partial least squares regression (PLSR). First, sample data with known oil content (i.e., experimentally determined oil content values) are used as training sets. The oil absorption peak intensity data is used as input variables, and a prediction model is established through a regression algorithm. During the modeling process, key absorption peaks (such as peaks at positions such as 3000cm-1, 1730cm-1, and 1450cm-1) are selected as feature inputs to ensure that the regression model contributes the most to these peaks. During the model training process, the regression parameters are adjusted using the cross-validation method, and the error tolerance threshold is set to ±0.5%. Ultimately, the constructed oil content prediction model will be able to accurately predict the oil content based on the oil absorption peak intensity data.

[0121] Step S117: predicting the fat content of the fat material data according to the fat content prediction model, thereby obtaining fat content data;

[0122] In this embodiment, the absorbance value of the oil material (i.e., the absorbance in the spectral data) is used as input, and the trained regression model is used for prediction. In the specific steps, the key absorption peaks in the spectral data of the oil material are extracted, the corresponding absorbance intensity is calculated, and these values ​​are input into the oil content prediction model for prediction. Through the prediction formula, the content data of the oil material is obtained, usually expressed in percentage form. The prediction process should ensure that the error of each sample is controlled within ±1% to ensure the accuracy and reliability of the prediction results.

[0123] Step S118: Perform spectral measurement on the oil content data to obtain oil spectrum data.

[0124] In this embodiment, the grease content data is verified by spectral measurement, the purpose is to ensure that the predicted grease content results have sufficient accuracy and reliability. The process first ensures that the measurement is performed using a near-infrared spectrometer that is exactly the same as step S111, which requires that the equipment model, light source, detector, scanning range and measurement settings are completely consistent. In order to maintain the consistency and comparability of the spectral data, the calibration status of the instrument needs to be checked and ensure that it has undergone correct zero point calibration and light source stability verification. When performing spectral measurement, the sample preparation method should be consistent with step S111, that is, each grease sample should be evenly mixed and maintained at appropriate temperature and humidity conditions. The grease sample should be placed in a standard sample pool, and the light beam should be scanned through the sample, and the wavelength range should be from 1100nm to 2500nm. In this process, ensure that the resolution of the spectrometer is set to high precision, such as 1nm, and ensure that the scanning speed is not less than 5 seconds each time to improve the quality of the data. Each sample is subjected to at least three independent spectral measurements to ensure the repeatability and stability of the data. After each scan, the measured spectral data is recorded in real time and stored in a digital data format for subsequent analysis. After the measurement is completed, the key absorption peaks of each spectrum are extracted, especially the bands closely related to the oil content (such as 3000cm-1, 1730cm-1, etc.) are analyzed. The data of these absorption peaks will be compared with the oil content data predicted in step S117, and the accuracy of the model will be further evaluated by calculating the error between the predicted value and the actual value. For the calculation of the error, the actual measured spectral data is first matched one by one with the predicted data in step S117, the absolute error between each pair of data is calculated, and the average error of each sample is obtained. According to these error data, check whether the predetermined error standard is met, that is, the error is less than ±1%. If the error range in this process exceeds ±1%, the model needs to be adjusted to check whether there are deviations in the data acquisition process, baseline correction, absorption peak identification and other steps, or whether the model needs to be retrained. Through comparison and analysis, the reliability of oil content prediction can be ensured, thereby providing accurate data support for industrial applications.

[0125] Optionally, step S112 is specifically:

[0126] Identify the non-absorption peak region of the oil near-infrared spectrum data to obtain the non-absorption peak region data;

[0127] In this embodiment, the near-infrared spectrum data of oils and fats is used to identify the region without absorption peaks. First, the absorption characteristics of the near-infrared spectrum of oils and fats need to be analyzed to identify the region without obvious absorption peaks in the spectrum. In the specific operation, by determining the wavelength range in the spectral data, select the wavelength segments with relatively stable absorbance values ​​and no obvious absorption peaks. Use spectral data processing tools, such as the findpeaks function in MATLAB, to analyze the spectral curve and identify the area near the peak. If the absorbance change in a certain wavelength region is less than a set threshold (such as 0.01), the region is regarded as a region without absorption peaks. The identification data of the region without absorption peaks will include the starting and ending wavelengths of each segment without absorption peaks, as well as the absorbance range of the segment.

[0128] Baseline point selection is performed according to the data of the region without absorption peak, thereby obtaining baseline point data;

[0129] In this embodiment, the selection of baseline points should be based on the spectral data in the region without absorption peaks. First, the mean or median of the absorbance values ​​in the region without absorption peaks is calculated and regarded as the baseline value. During the specific operation, for each region without absorption peaks, several wavelength points whose absorbance values ​​are closest to the mean or median in the interval are selected as baseline points. The selection criteria of the baseline points can be set to an absorbance value fluctuation range of less than ± 0.005, ensuring that these points have high stability and reliability when used as fitting baselines. The selected baseline point data includes wavelength coordinates and corresponding absorbance values.

[0130] Get the cubic polynomial fitting model;

[0131] In this embodiment, a cubic polynomial fitting model is obtained, and the model is used to fit the baseline point. Use existing spectral analysis software or programming tools (such as MATLAB, Python, etc.) to fit the baseline point data with a cubic polynomial. During the fitting process, the least squares method can be used to estimate parameters to ensure that the fitting result has the smallest error for the baseline point data. The fitted cubic polynomial equation is in the form of:

[0132] y=ax 3 +bx 2 +cx+d;

[0133] Where a, b, c, d are fitting parameters determined by minimizing the sum of squared errors. The cubic polynomial fitting model provides a smooth fitting curve within the baseline point data range to represent the baseline trend of the spectrum.

[0134] Performing polynomial baseline fitting on the baseline point data according to a cubic polynomial fitting model to generate polynomial fitting baseline data;

[0135] In this embodiment, the cubic polynomial model is applied to the baseline point data, and the fitting value of each baseline point is obtained by fitting calculation. The specific process is: for the wavelength of each baseline point, the wavelength is substituted into the cubic polynomial equation to obtain the corresponding absorbance value, and compared with the original baseline point data. If the error between the fitting value and the original data is less than a set threshold (such as 0.001), the fitting result is considered valid.

[0136] The near-infrared spectrum data of oil and fat are baseline corrected according to the polynomial fitting baseline data, so as to obtain the near-infrared spectrum correction data of oil and fat.

[0137] In this embodiment, the baseline correction of the oil near-infrared spectrum data is performed based on the polynomial fitting baseline data, the purpose of which is to eliminate the baseline drift in the spectrum. The corrected absorbance value is obtained by subtracting the corresponding polynomial fitting baseline value from the absorbance value of each wavelength point in the oil near-infrared spectrum data. In specific implementation, for each wavelength point, the polynomial fitting baseline value obtained in step S4 is used to perform the following operations:

[0138] A calibrated =A original -A fitted ;

[0139] Among them, A calibrated is the corrected absorbance, A original is the original absorbance, A fitted is the baseline absorbance obtained by polynomial fitting. Through this correction process, the low-frequency noise and baseline drift in the spectrum are eliminated, and the correction data of the near-infrared spectrum of oils and fats is obtained. These correction data will more accurately reflect the true spectral characteristics of the oil samples and provide more reliable basic data for subsequent analysis and prediction.

[0140] Optionally, step S2 specifically includes:

[0141] Step S21: obtaining a hydraulic press model;

[0142] In this embodiment, the physical and structural model of the hydraulic press is obtained. The model includes the working principle of the hydraulic press, the structural parameters of each component (such as filter pore size, oil extraction pressure, volume, etc.) and the mathematical expression of the oil processing process. The hydraulic press model should be modeled using the finite element analysis (FEA) method. Based on the actual working environment of the hydraulic press, appropriate parameters are selected, such as the pressing force is set to 5000N, the working temperature is maintained at 50°C, and the oil input is 5kg / h. The structure of the hydraulic press is dynamically analyzed by simulation software (such as ANSYS or ABAQUS) to simulate the flow characteristics and pressure distribution of the internal oil during the working process. Finally, according to the output data of the model, important parameters such as the efficiency of pressing and the oil extraction rate are obtained.

[0143] Step S22: input the oil processing demand data into the hydraulic press model, perform a pressing simulation, and perform low oil extraction rate statistics on the pressing simulation results to obtain the low oil extraction rate;

[0144] In this embodiment, the processing requirement data of the oil is input into the hydraulic press model. The processing requirement data includes the initial oil content of the oil (such as the initial oil content of the oil is 30%) and the operating parameters of the hydraulic press (such as pressurization time, pressure, temperature, etc.). After simulating the input data, a pressing simulation is performed, and the finite element analysis software is used to numerically simulate the pressing process of the oil in the hydraulic press. During the simulation process, the pressing time is set to 30 minutes and the pressure is set to 3500Pa. According to the simulation results, the low oil extraction rate during the pressing process is statistically analyzed. The low oil extraction rate can be calculated by measuring the difference between the actual oil extraction amount and the theoretical maximum extraction amount. If the oil extraction rate is lower than the set threshold (such as lower than 20%), it is marked as a low oil extraction rate.

[0145] Step S23: screening the oil material according to the low oil extraction rate to obtain the low oil material;

[0146] In this embodiment, oils with oil extraction rates lower than 20% are set as low-oil materials. First, the oil extraction rates of all oil materials are compared with the set threshold. Oils with oil extraction rates lower than 20% are classified as low-oil materials. During the screening process, an oil content measuring instrument (such as an oil analyzer) can be used to measure the oil content of each oil sample and compare it with the preset low oil extraction rate threshold. The low-oil materials after screening will enter the subsequent impurity mass spectrometry analysis step.

[0147] Step S24: performing impurity mass spectrometry analysis on the low-fat material to generate an impurity mass spectrum;

[0148] In this embodiment, a low-fat material sample is first prepared and dissolved by an appropriate solvent to ensure that the impurity components can be completely dissolved. The dissolved oil sample is subjected to mass spectrometry analysis using a gas chromatograph-mass spectrometer (GC-MS) or a liquid chromatograph-mass spectrometer (LC-MS). The operating conditions of the instrument are set as follows: the injection volume is 1 μL, the separation column temperature is set to 70°C, the mass spectrometer scanning range is 50-500m / z, and the acquisition time is 3 minutes. Through the mass spectrogram, various impurity components (such as fatty acids, heavy metals, etc.) in the oil can be identified. The impurity mass spectrum will show the mass and relative abundance of the impurity components, providing a basis for the subsequent identification of high-impurity oil materials.

[0149] Step S25: identifying high-impurity oil material from low-oil material according to the impurity mass spectrum, thereby obtaining high-impurity oil material;

[0150] In this embodiment, the standard of impurity components is set, such as the content of fatty acids exceeding 5% or the content of heavy metals exceeding a certain set value (such as the lead content is greater than 0.05 mg / kg). Each impurity component in the mass spectrum is quantitatively analyzed and its relative abundance is calculated. If the abundance of certain components exceeds the set threshold, the oil material is determined to be a high-impurity oil material. Use a standard mass spectrometry database (such as NIST or Wiley) to compare the detected components to further confirm the type and concentration of the impurity components. For high-impurity oil materials, they need to be marked and recorded for subsequent processing.

[0151] Step S26: Analyze the filter grease accumulation on the hydraulic press model according to the high-impurity grease material to generate filter grease accumulation data.

[0152] In this embodiment, the hydraulic press model is used to simulate the flow of high-impurity grease materials during the pressing process, especially the accumulation in the filter part. According to the structural parameters of the filter (such as pore size, filtration speed, etc.) and the rheological properties of the grease material (such as viscosity, fluidity, etc.), the accumulation of grease in the filter is simulated. The filter pore size is set to 50μm and the viscosity of the grease is set to 0.35Pa·s to simulate the accumulation rate of grease in the filter. The simulation results will show the amount of grease accumulated in the filter and the accumulation trend over time. Through this analysis, filter grease accumulation data is generated, including relevant parameters such as accumulation amount and accumulation time.

[0153] Optionally, step S24 is specifically:

[0154] Step S241: performing direct mass spectrometry on the low-fat material using a mass spectrometer to obtain mass spectrum data of the low-fat material;

[0155] In the present embodiment, a low-fat material sample is prepared and dissolved by an appropriate solvent to ensure that the components of grease and impurities are completely dissolved. Then, the sample is injected into a mass spectrometer for direct mass spectrometry analysis. The setting parameters of the mass spectrometer should include: electrospray ion source (ESI) or atmospheric pressure chemical ionization (APCI) mode, the analysis mode is positive ion mode, and the scanning range is set to 50 to 1000m / z. The mass spectrum data of the low-fat material is obtained by a mass spectrometer, and the data include ion peaks in all samples, their relative abundance and mass-to-charge ratio (m / z) information. This data provides molecular information of each component in the low-fat material, and provides basic data for subsequent analysis steps.

[0156] Step S242: performing parent ion identification on the mass spectrum data of the low-fat material to obtain parent ion data;

[0157] In this embodiment, parent ion identification is performed by ion peaks detected by a mass spectrometer, and the specific method is to extract all base peaks from the mass spectrum and identify their parent ions. Usually, when selecting parent ions, it is necessary to identify ion peaks with high relative abundance and stability (such as greater than 10%). In specific implementation, parent ion analysis is performed on each ion peak through software analysis tools (such as MassLynx or Xcalibur). If the parent ion molecular weight of a certain ion peak is high and stable, its data is recorded, and parent ion data is generated, including the m / z value and intensity of the parent ion.

[0158] Step S243: obtaining a parent ion spectrum library;

[0159] In the present embodiment, the parent ion spectral library is constructed by database or manually, comprising the m / z value, structural information and corresponding chemical composition of known parent ions. The method for obtaining the spectral library includes downloading relevant parent ion spectrum data from public databases (such as NIST, HMDB), or obtaining parent ion data of standard chemical substances by experiment. In order to ensure the accuracy of data, the spectral library should include parent ion information of various common oil components and impurity components thereof, such as fatty acids, triglycerides and other impurity substances. The effect of this spectral library is to provide accurate reference data for subsequent parent ion comparative analysis.

[0160] Step S244: performing a comparison of the parent ion data with the parent ion of the emulsion residue according to the parent ion spectral library to obtain the emulsion residue data;

[0161] In this embodiment, the parent ion data is compared with the parent ion spectral library. This comparison process uses standardized spectral library data to match each parent ion. If the m / z value of the parent ion matches the parent ion data related to the emulsion residue in the spectral library, it is confirmed that the parent ion belongs to the component of the emulsion residue. During the implementation process, the parent ions related to the emulsion residue are screened out through the automated comparison function of the mass spectrometry software. For example, the parent ion m / z values ​​of common phospholipids or surfactants in the emulsion will match the data in the spectral library. Finally, the relevant data of the emulsion residue are obtained, including the matching parent ion type, concentration and relative abundance.

[0162] Step S245: performing mass-to-charge ratio identification on the low-fat material mass spectrum data according to the emulsion residue data, thereby obtaining mass-to-charge ratio data;

[0163] In this embodiment, the mass-to-charge ratio (m / z) is analyzed by analyzing the ion peaks in the mass spectrum. The identification process focuses on the specific ion peaks in the emulsion residue, and its mass-to-charge ratio value is usually closely related to the chemical composition of the emulsion. The mass-to-charge ratio data related to the emulsion are automatically extracted using software (such as OpenMS or MZmine), and data filtering is performed to remove noise and irrelevant peaks. According to the data of the emulsion residue, the corresponding mass-to-charge ratio (m / z) value and its intensity are recorded.

[0164] Step S246: performing intensity peak recognition on the emulsion residue data according to the emulsion residue data, thereby obtaining intensity peak data;

[0165] In the present embodiment, the ion peaks related to the emulsion residue are screened out from the mass spectrum data of the emulsion residue. These ion peaks usually represent the chemical composition in the emulsion. The core goal of intensity peak identification is to determine the ion peaks with higher signal intensity in the mass spectrum, and the intensity of these peaks is usually related to the relative abundance of the emulsion. By using mass spectrum data analysis software (such as MassHunter, SpectraSchool, MZmine, etc.), firstly, the entire mass spectrum is subjected to signal processing, background noise is filtered out and ion peaks are identified. Next, each peak is further analyzed to determine its mass-to-charge ratio (m / z) and intensity value. For each peak that meets the conditions, its m / z value is recorded, and its relative intensity is calculated, usually expressed as the percentage of the maximum signal intensity of the peak relative to the total signal intensity. The identification of the intensity peak also needs to be filtered according to the threshold value set by the standard, and the threshold value is usually at least greater than 5% of the relative abundance. For each intensity peak identified, its mass-to-charge ratio value (m / z) and signal intensity data are recorded in detail, and these data will provide basic information for the subsequent impurity mass spectrum drawing.

[0166] Step S247: Draw an impurity mass spectrum according to the mass-to-charge ratio data and the intensity peak data to obtain an impurity mass spectrum.

[0167] In the present embodiment, the impurity mass spectrogram of the low-fat material is drawn in combination with the mass-to-charge ratio data and the intensity peak data. Specifically, first, the mass-to-charge ratio data obtained in step S245 is combined with the intensity peak data identified in step S246 to establish a complete two-dimensional mass spectrogram data set. Using mass spectrum data processing software (such as ProteoWizard, OpenMS or other related software), all valid mass-to-charge ratio values ​​(m / z) and corresponding intensity data are imported into the software, and data processing is performed. The software will first sort these data to ensure that the mass-to-charge ratio is arranged from small to large. Then, using the data visualization function, a two-dimensional chart with mass-to-charge ratio (m / z) as the X-axis and signal intensity as the Y-axis is drawn. In the chart, each point represents an intensity peak corresponding to a mass-to-charge ratio, and these points are presented by curves or bar graphs. This figure will show the distribution of impurities in the low-fat material, and different mass-to-charge ratios correspond to different impurity components. Through the impurity mass spectrogram, the relative abundance of each component can be clearly observed, and its content in the sample and its influence can be analyzed. This chart not only provides a basis for the screening of oil materials, but also provides visual data support for subsequent quality analysis.

[0168] Optionally, step S26 is specifically:

[0169] Step S261: placing the high-impurity grease material into the hydraulic press model and performing filtration simulation to generate hydraulic press filtration data;

[0170] In this embodiment, the high-impurity grease material needs to be placed in a hydraulic press model for simulation. To this end, a numerical simulation tool for the hydraulic press model is required, such as fluid dynamics simulation software (such as ANSYS Fluent or COMSOL Multiphysics). The simulation tool can accurately reproduce the physical behavior of the grease material during the filtration process under specific working conditions.

[0171] Input the relevant parameters of the high-impurity grease material into the simulation system, including data such as the viscosity, flow rate and particle size of the material. The parameters of the grease material can be obtained through laboratory analysis, for example, the viscosity of the grease material is measured by a viscometer, and the particle size is measured by a particle size analyzer. Next, define the filtration conditions of the hydraulic press, such as pressure, flow rate and pore size of the filter. During the simulation process, a mathematical model is used to calculate the flow and filtration process of the grease material in the filter. According to the characteristics of the material and the resistance of the filter, the data generated during the filtration process are simulated, including filtration efficiency, pressure loss, flow rate change, etc. Finally, generate complete hydraulic press filtration data, including various physical quantity data and performance data during the filtration process.

[0172] Step S262: performing efficiency statistics on the hydraulic press filtering data, thereby obtaining low-efficiency hydraulic press filtering data;

[0173] In this embodiment, a special analysis tool, such as MATLAB or Excel, is required to analyze the various data obtained during the hydraulic press filtering process. First, the filtering efficiency of the hydraulic press is calculated. The filtering efficiency can be obtained by calculating the change in the total amount of grease material before and after filtering. For example, the total amount of grease material before filtration minus the amount of grease flowing through the filter after filtration, and then the ratio is calculated with the amount of grease before filtration to obtain the percentage of filtering efficiency. According to the simulation data obtained in step S261, select the low-efficiency filtering conditions, which usually correspond to higher pressure loss or lower filtering effect. Set a low-efficiency filtering efficiency threshold, such as when it is less than 80%, it is considered to be low-efficiency filtering. By comparing all the filtering data, the data that meets the low-efficiency filtering standard is screened out, and finally the low-efficiency hydraulic press filtering data is obtained.

[0174] Step S263: Obtain filter data and filter clogging threshold;

[0175] In this embodiment, it is necessary to obtain relevant data of the filter and set a clogging threshold. The filter data generally includes the filter pore size, filter element material, working pressure range, etc., which can be obtained through the filter's technical manual or laboratory test. The setting of the clogging threshold depends on the design standard of the filter, and is usually defined as clogging when the surface resistance of the filter element reaches a certain level. For example, it is set that when the pressure loss of the filter exceeds a predetermined value (such as 20%), the filter is considered to be clogged. The threshold can be obtained through experiments, or set according to the design regulations of the filter.

[0176] Step S264: performing real-time monitoring of the surface accumulation of the filter data according to the filtering data of the low-efficiency hydraulic press, thereby obtaining the surface accumulation data of the filter;

[0177] In this embodiment, according to the filtering data of the low-efficiency hydraulic press, it is necessary to monitor the grease accumulation on the filter surface in real time. Use a pressure sensor, a flow meter and a surface sensor (such as a laser scanner or an infrared sensor) to monitor the surface state of the filter in real time. By combining with the low-efficiency data obtained by the hydraulic press simulation, the degree of grease material accumulated on the filter surface is analyzed. The data recorder and sensor will detect the grease accumulation on the filter surface in real time and transmit the data to the data processing platform. At this time, the monitoring data will be recorded and counted according to the real-time accumulation amount, and the filter surface accumulation data will be output.

[0178] Step S265: Calculating the accumulation rate of the filter surface accumulation data to obtain the filter accumulation rate;

[0179] In this embodiment, the calculation of the filter accumulation rate is based on the rate of change of the amount of grease accumulation on the filter surface. The real-time filter surface accumulation data is calculated hour by hour using a time series analysis method. The accumulation rate can be obtained by recording the accumulation amount at each time point and calculating the difference between the accumulation amount at the previous time point. The calculation formula for the accumulation rate is:

[0180]

[0181] This step requires periodic statistics of the accumulation rate, setting a time interval (for example, every 10 minutes), and calculating the accumulation rate in each time period. The final result will show the grease accumulation rate of the filter.

[0182] Step S266: dividing the filter surface accumulation data into blockage groups according to the filter blockage threshold, thereby obtaining the filter surface blockage data;

[0183] In this embodiment, the filter clogging threshold needs to be set first. The setting of the clogging threshold is based on the design standard and experimental data of the filter, and is usually defined by the standard value of the accumulation rate or the accumulation amount. For example, the accumulation rate is set to exceed a certain value (such as 10g / min) or the cumulative accumulation exceeds a certain limit (such as 5g / cm 2 ), the filter is considered to be in a blocked state. At the same time, the setting of the blocking threshold can also be adjusted according to the working environment of the filter, such as pressure loss and flow rate change. For example, when the pressure loss of the filter exceeds 15%, the filter can also be considered to be seriously blocked. Next, real-time monitoring equipment (such as pressure sensors, flow meters, and surface sensors, etc.) is required to obtain the accumulation data on the filter surface. These data record the changes in the amount of grease accumulation on the filter surface, including the accumulation rate or accumulation amount at each time point. These data are obtained through sensors and calculation algorithms. The measurement method of the accumulation amount can be based on physical sensors and fluid mechanics models, and the accumulation rate is the change in the accumulation amount per unit time. After obtaining the real-time accumulation data, these data are compared with the set blocking threshold. When the accumulation rate or cumulative accumulation amount in the real-time data exceeds the preset threshold, the moment is marked as the moment of filter blockage. At this time, the accumulation data of the filter is considered to be blocked data, and will include information such as the accumulation rate, accumulation amount, pressure change, and flow rate change at that moment. Finally, all the moments and related data that meet the clogging criteria will be recorded in the database and a clogging report will be generated, which lists in detail the clogging time, clogging degree, accumulation rate, pressure loss, etc. of each filter. These data can not only help identify the current clogging status of the filter, but also serve as the basis for subsequent maintenance and optimization decisions, predict the clogging trend of the filter, and optimize the use and replacement cycle of the filter.

[0184] Step S267: performing rate statistics on the filter accumulation rate to obtain high-rate filter accumulation data;

[0185] In this embodiment, the filter accumulation rate is analyzed in detail and which filters are in a high-rate accumulation state are identified. First, a high-rate threshold is set based on the existing filter accumulation rate data. Usually, the threshold is set to a rate exceeding 10g / min, which is considered a high-rate accumulation. The setting of this threshold is based on the design specifications, working conditions and common accumulation rates of the filter in actual operation. Next, all filter accumulation rate data are screened to find all records with rates exceeding 10g / min. These records represent that the accumulation rate of the filter is relatively high at a certain moment and is in a high-rate accumulation state. A high-rate filter accumulation data set is generated by summarizing and counting the data that meets the conditions. The data set contains each filter that meets the conditions, its accumulation rate and the corresponding time information. These data can help identify filters that are in an abnormal accumulation state and provide a basis for subsequent optimization and maintenance decisions.

[0186] Step S268: Counting the blockage degree of the filter surface blockage data, thereby obtaining the filter surface serious blockage data;

[0187] In this embodiment, it is necessary to define a standard for the degree of blockage, which is usually measured by the amount of accumulated grease or the pressure increment caused by the blockage. For grease accumulation, the degree of blockage can be calculated by the amount of accumulated grease. If the amount of accumulated grease exceeds a certain standard value (such as 5g / cm 2 ), the degree of blockage is considered to be high; for pressure increment, if the pressure loss of the filter reaches a certain proportion (such as more than 80%), it is considered to be seriously blocked. In the statistical process, the cumulative statistical method is used to record the blockage status of the filter in each time period. For each monitoring time point, the degree of blockage at that moment is calculated. If the blockage degree exceeds the set severe blockage standard (for example, the blockage degree exceeds 90%), the blockage data at that moment is classified as severe blockage data. Finally, the filter surface severe blockage data is generated, recording the blockage degree of each filter during the monitoring period and the time when severe blockage occurs, as reference data for subsequent analysis and maintenance.

[0188] Step S269: Perform grease accumulation intersection operation based on the high-rate filter accumulation data and the filter surface severe blockage data to generate filter grease accumulation data.

[0189] In this embodiment, it is first necessary to perform an intersection operation on the two sets of data obtained in step S267 and step S268. The first set of data is the high-rate filter accumulation data, which records the filters and related data whose accumulation rate exceeds the set threshold (such as 10g / min); the second set of data is the filter surface severe blockage data, which records the filters whose blockage degree exceeds the severe standard. The purpose of the intersection operation is to find those filters that have both high-rate accumulation and severe blockage. The specific operation is to compare the two sets of data and filter out the records that meet both conditions (i.e., high-rate accumulation and severe blockage). These records represent filters with a high grease accumulation rate and an accumulation amount sufficient to cause blockage. Through set operations (such as intersection operations), the filter grease accumulation data is finally obtained. This data set not only records the basic information of the high-rate accumulation filter, but also includes its blockage status, providing important data support for subsequent analysis of grease accumulation trends, optimization of filter design, and prediction of maintenance cycles.

[0190] Optionally, step S3 specifically includes:

[0191] Step S31: acquiring the pressing data of the screw oil press, and collecting the oil sample of the screw oil press according to the pressing data of the screw oil press to obtain the oil sample of the screw oil press;

[0192] In this embodiment, it is first necessary to obtain the operating data of the screw oil press through the data acquisition system, including parameters such as pressing pressure, rotation speed, material temperature and oil yield. The data can be obtained in real time through sensors installed on the oil press, such as pressure sensors, temperature sensors, rotation speed sensors, etc. After obtaining the real-time pressing data of the screw oil press, the oil sample is collected. When collecting oil samples, it is necessary to set the collection time interval and collection amount. The collected samples need to be judged based on the outflow of oil during the operation of the press. For example, it is set to collect oil samples every 100 minutes to ensure the representativeness and accuracy of the samples. The quality of the oil sample can be monitored by regular weighing to ensure the effectiveness of the sample. Finally, the collected oil sample is the oil sample of the screw oil press, which provides basic data for subsequent extraction and analysis.

[0193] Step S32: extracting the oil residue of the screw oil press oil sample using a Soxhlet extractor to obtain an oil residue sample;

[0194] In the present embodiment, the oil sample collected in step S31 is placed in a Soxhlet extractor for processing. The Soxhlet extractor is an experimental device commonly used for oil extraction, and the oil components in the oil sample are extracted by continuous solvent reflux and osmosis. The specific operation is to mix the oil sample with an appropriate solvent (such as petroleum ether or ether), heat the solvent to boiling and evaporate it, condense it into a liquid by reflux in a condenser and flow it back into the extractor, and the oil components are dissolved in the solvent and extracted. This process usually lasts about 6-8 hours to ensure that the oil is completely extracted. After the extraction is completed, a separating funnel is used to separate the oil residue and the oil, and the obtained oil residue sample is a solid residue sample after the oil component is removed from the oil. The quality of the oil residue sample can be measured by weighing to ensure the efficiency of the extraction process.

[0195] Step S33: performing oil residue content statistics according to the oil residue sample, thereby obtaining high oil residue content data;

[0196] In this embodiment, the oil residue sample needs to be dried to ensure that there is no moisture in the sample. Drying is usually carried out at 105°C until the mass of the oil residue sample no longer changes. Next, the mass of the oil residue sample is recorded using a weighing method to calculate the content of the oil residue. The oil residue content refers to the proportion of the mass of the solid residue in the oil residue sample to the mass of the oil sample, usually expressed as a percentage. A threshold value for the oil residue content is set. For example, when the oil residue content exceeds 30%, the oil residue content is considered to be high. By taking statistics on multiple oil residue samples, high oil residue content data can be obtained. These data can be used to evaluate the oil residue situation under different raw materials or different operating conditions, and provide a basis for subsequent oil pressing control.

[0197] Step S34: Perform intelligent pressing temperature control according to the high oil residue content data, thereby obtaining intelligent pressing temperature control data.

[0198] In this embodiment, it is necessary to analyze the high oil residue content data to identify the oil samples with high oil residue content. Based on the high oil residue content data, the pressing condition analysis is carried out to determine how to adjust the temperature conditions of the press under high oil residue conditions. The analysis includes evaluating the effects of different oil residue contents on the oil pressing effect, especially the oil recovery rate and oil quality. According to the analysis results, an adaptive temperature range is set. When the oil residue content reaches or exceeds the preset standard, the temperature of the press will be adjusted to this range to optimize the oil pressing effect and the oil residue removal efficiency. Further, the temperature adjustment demand assessment is carried out to determine the specific temperature adjustment range. For example, when the oil residue content exceeds 35%, the temperature needs to be increased to 80°C to increase the fluidity of the oil and improve the pressing effect. According to the temperature adjustment demand data, a temperature control algorithm is designed, which automatically controls the heating system of the press according to the real-time oil residue data and the temperature adjustment demand. The temperature control algorithm data will be used to simulate the pressing process under different temperature conditions to optimize the pressing efficiency and reduce the pressure problem caused by excessive oil residue content, ensuring the intelligent control and efficiency of oil pressing.

[0199] Optionally, step S34 is specifically:

[0200] Step S341: analyzing the material pressing conditions according to the high oil residue content data, thereby obtaining pressing condition data;

[0201] In this embodiment, it is first necessary to analyze samples with different oil residue contents according to the high oil residue content data. First, a standard interval of oil residue content is set, for example, the oil residue content is divided into three levels: low (below 20%), medium (20%-30%), and high (above 30%). Then, the material pressing conditions are analyzed according to the oil residue content level. This analysis includes setting appropriate pressing pressure, rotation speed, heating temperature and other factors. The specific operation is: for low oil residue content samples, the pressing pressure can be set to 10MPa and the rotation speed is set to 30 rpm; for medium oil residue content samples, the pressing pressure can be set to 15MPa and the rotation speed is set to 40 rpm; for high oil residue content samples, the pressing pressure can be set to 20MPa and the rotation speed is set to 50 rpm. On this basis, by adjusting the temperature and pressure to conduct experiments, the oil yield and oil residue residue remaining under different pressing conditions are analyzed, so as to obtain the pressing condition data suitable for different oil residue content data.

[0202] Step S342: evaluating the temperature adjustment requirement of the pressing condition data, thereby obtaining temperature adjustment requirement data;

[0203] In this embodiment, the temperature requirements under different oil residue content conditions are analyzed. For example, in the case of high oil residue content (more than 30%), the oil is more viscous, so the temperature needs to be increased to enhance the fluidity of the oil. At this time, the temperature is set to 80°C; for samples with medium oil residue content (20%-30%), the temperature is set to 70°C; for samples with low oil residue content, the temperature is set to 60°C. Through the oil pressing experiment on samples with different oil residue content, the fluidity and pressure changes of the oil during the pressing process are measured, and the relationship between the fluidity of the oil and temperature is further analyzed, and finally the temperature adjustment demand data is determined. These data will provide parameter support for the subsequent design of intelligent temperature control algorithms.

[0204] Step S343: Designing an intelligent temperature control algorithm based on the temperature adjustment requirement data to generate temperature control algorithm data;

[0205] In this embodiment, during the design process, it is necessary to first consider the correlation between different oil residue contents and temperatures, and establish the functional relationship between oil residue content and temperature control through a mathematical model. For example, when the oil residue content reaches 30%, by adjusting the temperature to 80°C, if the oil residue content drops to 20%, the temperature can be adjusted to 70°C. The relationship between temperature change and oil residue content change can be established through a formula and further optimized through a data fitting algorithm. The system response time also needs to be considered during the design of the temperature control algorithm to ensure that the temperature adjustment can be achieved in a short time to avoid affecting the pressing efficiency due to temperature lag. According to the temperature adjustment demand data, the control algorithm design is used to generate temperature control algorithm data corresponding to each oil residue content to ensure that the temperature can be accurately adjusted in actual operation.

[0206] Step S344: Perform intelligent pressing temperature control simulation according to the temperature control algorithm data to obtain intelligent pressing temperature control data.

[0207] In this embodiment, during the simulation process, the real pressing data is input into the temperature control algorithm system, including parameters such as pressing pressure, rotation speed and oil residue content. Then, according to the designed temperature control algorithm, the heating temperature is adjusted according to the real-time oil residue content data. For example, in actual operation, when the oil residue content is monitored to be 28% in real time, the system automatically adjusts the heating temperature to 75°C according to the temperature control algorithm data, and feeds back the temperature change in the press in real time. The simulation system should record the pressing effect at different temperatures, including the oil collection rate and the oil residue residual rate, to evaluate the accuracy of temperature control and its impact on pressing efficiency. Through multiple simulations and adjustment of algorithm parameters, a stable temperature control strategy is finally determined to obtain intelligent temperature control data for pressing, which can be used to implement the temperature control system in the actual production process.

[0208] Optionally, the present specification also provides an intelligent digital-based grease production control system for executing the intelligent digital-based grease production control method as described above, the intelligent digital-based grease production control system comprising:

[0209] The processing demand analysis module is used to obtain oil material data and perform processing demand analysis based on the oil material data, thereby obtaining oil processing demand data;

[0210] The oil impurity analysis module is used to obtain the hydraulic press model; input the oil processing demand data into the hydraulic press model, perform pressing simulation, and perform low oil extraction rate statistics on the pressing simulation results to obtain the low oil extraction rate; perform oil impurity analysis on the oil material according to the low oil extraction rate to generate oil impurity data; perform filter oil accumulation analysis on the hydraulic press model according to the oil impurity data to generate filter oil accumulation data;

[0211] The intelligent pressing temperature control module is used to obtain the pressing data of the screw oil press and perform oil residue content analysis to obtain high oil residue content data; the intelligent pressing temperature control is performed according to the high oil residue content data to obtain the intelligent pressing temperature control data;

[0212] The intelligent production scheduling module is used to perform intelligent production scheduling according to the oil processing demand data and the filter grease accumulation data to obtain intelligent production data; the intelligent production data and the pressing intelligent temperature control data are uploaded to the intelligent control system to execute the grease production control task.

[0213] The present invention discloses an oil production control system based on intelligent digitization, which can realize any oil production control method based on intelligent digitization of the present invention, and is used to combine the operation and signal transmission medium between various modules to complete the oil production control method based on intelligent digitization. The internal modules of the system cooperate with each other, thereby improving the oil extraction rate and production efficiency.

[0214] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0215] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for controlling oil production based on intelligent digitalization, characterized in that: The following steps are involved: Step S1: Obtaining oil material data, and performing processing demand analysis based on the oil material data, thereby obtaining oil processing demand data; Step S2: obtaining a hydraulic press model; inputting the oil processing demand data into the hydraulic press model, performing a pressing simulation, and performing low oil extraction rate statistics on the pressing simulation results to obtain a low oil extraction rate; performing an oil impurity analysis on the oil material according to the low oil extraction rate to generate oil impurity data; performing a filter oil accumulation analysis on the hydraulic press model according to the oil impurity data to generate filter oil accumulation data; Step S3: Acquire the pressing data of the screw oil press and perform oil residue content analysis to obtain high oil residue content data; perform intelligent pressing temperature control according to the high oil residue content data to obtain intelligent pressing temperature control data; Step S4: Perform intelligent production scheduling according to the oil processing demand data and the filter grease accumulation data to obtain intelligent production data; upload the intelligent production data and the pressing intelligent temperature control data to the intelligent control system to execute the grease production control task.

2. The oil production control method based on intelligent digitalization according to claim 1 is characterized in that: Step S1 is specifically as follows: Step S11: Obtaining oil material data and performing spectral analysis to obtain oil spectrum data; Step S12: evaluating the oil content according to the oil spectrum data, thereby obtaining oil content data; Step S13: measuring the moisture content of the oil content data to obtain moisture content data; Step S14: performing impurity content analysis according to the moisture content data, thereby obtaining impurity content data; Step S15: Perform oil processing demand analysis based on the impurity content data to obtain oil processing demand data.

3. The oil production control method based on intelligent digitalization according to claim 2 is characterized in that: Step S11 is specifically as follows: Step S111: Obtaining oil material data and performing near infrared spectrum sampling to obtain oil near infrared spectrum data; Step S112: performing baseline correction on the oil near-infrared spectrum data, thereby obtaining oil near-infrared spectrum correction data; Step S113: obtaining oil absorption peak data; Step S114: performing position identification on the oil near-infrared spectrum correction data according to the oil absorption peak data, thereby obtaining the oil absorption peak position data; Step S115: performing intensity statistics on the oil absorption peak position data, thereby obtaining oil absorption peak intensity data; Step S116: constructing a fat content prediction model according to the fat absorption peak intensity data, thereby obtaining a fat content prediction model; Step S117: predicting the fat content of the fat material data according to the fat content prediction model, thereby obtaining fat content data; Step S118: Perform spectral measurement on the oil content data to obtain oil spectrum data.

4. The oil production control method based on intelligent digitalization according to claim 3 is characterized in that: Step S112 is specifically as follows: Identify the non-absorption peak region of the oil near-infrared spectrum data to obtain the non-absorption peak region data; Baseline point selection is performed according to the data of the region without absorption peak, thereby obtaining baseline point data; Get the cubic polynomial fitting model; Performing polynomial baseline fitting on the baseline point data according to a cubic polynomial fitting model to generate polynomial fitting baseline data; The near-infrared spectrum data of oil and fat are baseline corrected according to the polynomial fitting baseline data, so as to obtain the near-infrared spectrum correction data of oil and fat.

5. The oil production control method based on intelligent digitalization according to claim 1 is characterized in that: Step S2 is specifically as follows: Step S21: obtaining a hydraulic press model; Step S22: input the oil processing demand data into the hydraulic press model, perform a pressing simulation, and perform low oil extraction rate statistics on the pressing simulation results to obtain the low oil extraction rate; Step S23: screening the oil material according to the low oil extraction rate to obtain the low oil material; Step S24: performing impurity mass spectrometry analysis on the low-fat material to generate an impurity mass spectrum; Step S25: identifying high-impurity oil material from low-oil material according to the impurity mass spectrum, thereby obtaining high-impurity oil material; Step S26: Analyze the filter grease accumulation on the hydraulic press model according to the high-impurity grease material to generate filter grease accumulation data.

6. The intelligent digital oil production control method according to claim 5 is characterized in that: Step S24 is specifically as follows: Step S241: performing direct mass spectrometry on the low-fat material using a mass spectrometer to obtain mass spectrum data of the low-fat material; Step S242: performing parent ion identification on the mass spectrum data of the low-fat material to obtain parent ion data; Step S243: obtaining a parent ion spectrum library; Step S244: performing a comparison of the parent ion data with the parent ion of the emulsion residue according to the parent ion spectral library to obtain the emulsion residue data; Step S245: performing mass-to-charge ratio identification on the low-fat material mass spectrum data according to the emulsion residue data, thereby obtaining mass-to-charge ratio data; Step S246: performing intensity peak recognition on the emulsion residue data according to the emulsion residue data, thereby obtaining intensity peak data; Step S247: Draw an impurity mass spectrum according to the mass-to-charge ratio data and the intensity peak data to obtain an impurity mass spectrum.

7. The oil production control method based on intelligent digitalization according to claim 5 is characterized in that: Step S26 is specifically as follows: Step S261: placing the high-impurity grease material into the hydraulic press model and performing filtration simulation to generate hydraulic press filtration data; Step S262: performing efficiency statistics on the hydraulic press filtering data, thereby obtaining low-efficiency hydraulic press filtering data; Step S263: Obtain filter data and filter clogging threshold; Step S264: performing real-time monitoring of the surface accumulation of the filter data according to the filtering data of the low-efficiency hydraulic press, thereby obtaining the surface accumulation data of the filter; Step S265: Calculating the accumulation rate of the filter surface accumulation data to obtain the filter accumulation rate; Step S266: dividing the filter surface accumulation data into blockage groups according to the filter blockage threshold, thereby obtaining the filter surface blockage data; Step S267: performing rate statistics on the filter accumulation rate to obtain high-rate filter accumulation data; Step S268: Counting the blockage degree of the filter surface blockage data, thereby obtaining the filter surface serious blockage data; Step S269: Perform grease accumulation intersection operation based on the high-rate filter accumulation data and the filter surface severe blockage data to generate filter grease accumulation data.

8. The oil production control method based on intelligent digitalization according to claim 1 is characterized in that: Step S3 is specifically as follows: Step S31: acquiring the pressing data of the screw oil press, and collecting the oil sample of the screw oil press according to the pressing data of the screw oil press to obtain the oil sample of the screw oil press; Step S32: extracting the oil residue of the screw oil press oil sample using a Soxhlet extractor to obtain an oil residue sample; Step S33: performing oil residue content statistics according to the oil residue sample, thereby obtaining high oil residue content data; Step S34: Perform intelligent pressing temperature control according to the high oil residue content data, thereby obtaining intelligent pressing temperature control data.

9. The intelligent digital oil production control method according to claim 8 is characterized in that: Step S34 is specifically as follows: Step S341: analyzing the material pressing conditions according to the high oil residue content data, thereby obtaining pressing condition data; Step S342: evaluating the temperature adjustment requirement of the pressing condition data, thereby obtaining temperature adjustment requirement data; Step S343: Designing an intelligent temperature control algorithm based on the temperature adjustment requirement data to generate temperature control algorithm data; Step S344: Perform intelligent pressing temperature control simulation according to the temperature control algorithm data to obtain intelligent pressing temperature control data.

10. An intelligent digital-based oil production control system, characterized in that: Used to execute the intelligent digitalization-based grease production control method as claimed in claim 1, the intelligent digitalization-based grease production control system comprises: The processing demand analysis module is used to obtain oil material data and perform processing demand analysis based on the oil material data, thereby obtaining oil processing demand data; The oil impurity analysis module is used to obtain the hydraulic press model; input the oil processing demand data into the hydraulic press model, perform pressing simulation, and perform low oil extraction rate statistics on the pressing simulation results to obtain the low oil extraction rate; perform oil impurity analysis on the oil material according to the low oil extraction rate to generate oil impurity data; perform filter oil accumulation analysis on the hydraulic press model according to the oil impurity data to generate filter oil accumulation data; The intelligent pressing temperature control module is used to obtain the pressing data of the screw oil press and perform oil residue content analysis to obtain high oil residue content data; the intelligent pressing temperature control is performed according to the high oil residue content data to obtain the intelligent pressing temperature control data; The intelligent production scheduling module is used to perform intelligent production scheduling according to the oil processing demand data and the filter grease accumulation data to obtain intelligent production data; the intelligent production data and the pressing intelligent temperature control data are uploaded to the intelligent control system to execute the grease production control task.

Images