An intelligent optimization system for the peanut oil production control process

Abstract

The present invention relates to the technical field of peanut oil production control, and specifically to an intelligent optimization system for the peanut oil production control process. The system includes: a process parameter modeling module that collects peanut oil production parameters, analyzes the correlation between peanut oil production parameters and quality indicators by performing linear combinations on the peanut oil production parameters, and obtains a process parameter mapping matrix. In the present invention, through in-depth correlation analysis of multiple parameters during the production process, a mapping relationship between process parameters and oil product quality indicators is established, improving the accuracy and reliability of quality control. In process control, through standardization and linear combination analysis of parameters such as pressing temperature, pressure, time, and stirring speed, the specific impacts of each production link on quality indicators are accurately reflected. By predicting the quality indicators under current production conditions, the reaction speed to quality changes is increased, enabling rapid analysis and evaluation of quality indicator deviations during real-time data monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of peanut oil production control, and particularly to an intelligent optimization system for the peanut oil production control process. Background Art

[0002] Peanut oil production control technology involves the management and optimization of various production links from raw material processing, pressing and extraction, refining to packaging and storage. By controlling key production parameters such as temperature, pressure, humidity and time, etc., the purity and nutritional components of the oil product are ensured, and impurities and harmful substances in the processing are reduced. By means of data collection and real-time monitoring, the effects of precise regulation and reduction of resource waste are achieved, thus realizing an efficient and environmentally friendly production process.

[0003] Among them, the intelligent optimization system for the peanut oil production control process conducts real-time monitoring and automatic adjustment of each link in peanut oil production through intelligent algorithms and data analysis means, helping production enterprises to ensure the quality of the oil product.

[0004] The existing technology is difficult to achieve in-depth correlation analysis of different process parameters in peanut oil production control, resulting in the dependence of oil product quality control on the qualitative judgment of a small number of parameters, unable to fully reflect the overall impact of each production link on the oil product quality, and affecting the comprehensiveness of quality control. In the quality control process, when facing real-time production data, it is difficult to quickly predict quality indicators and analyze deviations, making the response to abnormal situations relatively lagging, and easily leading to product quality fluctuations or non-compliance. In terms of abnormal parameter processing, when some parameters deviate from the standard values, the production process is difficult to adjust adaptively, easily leading to problems such as increased abnormal load of equipment, increased energy consumption, and equipment failures. At the same time, the existing technology fails to effectively regulate the multi-parameter dynamic balance in the load state, resulting in the interference of secondary factors on the optimization of production parameters under complex production conditions, making the overall production efficiency difficult to reach the expected level. Summary of the Invention

[0005] The purpose of the present invention is to solve the drawbacks existing in the prior art, and to propose an intelligent optimization system for the peanut oil production control process.

[0006] In order to achieve the above purpose, the present invention adopts the following technical solution: An intelligent optimization system for the peanut oil production control process includes:

[0007] The process parameter modeling module collects peanut oil production parameters, analyzes the correlation between peanut oil production parameters and quality indicators through linear combination of peanut oil production parameters, and obtains a process parameter mapping matrix;

[0008] The real-time data acquisition and prediction module maps the data of the process parameter mapping matrix collected in real time, obtains the predicted value of the oil quality index under the current production conditions by solving the mapping relationship, and compares it with the expected quality standard to obtain the deviation evaluation result;

[0009] The dynamic parameter smoothing module compares the current value of the peanut oil production parameter with the preset threshold range, smooths the parameters outside the range to obtain the smoothed parameter setting value. If the parameter is within the normal range, combined with the deviation evaluation result, the stable parameter setting value is obtained for the parameter within the normal range. Combining the current peanut oil production status, it is judged whether load balancing is required. If so, load balancing calculation is performed on the production parameters to generate load balancing parameters;

[0010] The process optimization and adjustment module based on the smoothed parameter setting value or the stable parameter setting value, refines and adjusts the peanut oil production parameters to obtain the optimized process parameter setting value, and integrates the optimized process parameter setting value and the load balancing parameters to obtain the global parameter data processing result of peanut oil production control.

[0011] As a further solution of the present invention, the specific steps for obtaining the linear combination of peanut oil production parameters are as follows:

[0012] Based on the collected peanut oil production parameters, including pressing temperature, pressing pressure, pressing time and stirring speed, the parameters are standardized and linearly combined with inconsistent weights to generate a process parameter combination value;

[0013] Based on the process parameter combination value, the formula is used:

[0014]

[0015] Calculate the correlation coefficient , and obtain the correlation coefficient between the process parameter and the oil quality;

[0016] Among them, is The average value of, representing the average process parameter combination value in multiple batches of production, is the oil quality index value, is The average value of, representing the average oil quality index value in multiple batches of production.

[0017] As a further solution of the present invention, the specific steps for obtaining the process parameter mapping matrix are as follows:

[0018] Based on the correlation coefficient between the process parameters and the oil quality, judge the linear relationship between the combination of process parameters and the oil quality indicators. By analyzing the value of the correlation coefficient, judge the influence of parameter adjustment on the quality indicators, and obtain the analysis result of the relationship between the combination of process parameters and the oil quality indicators;

[0019] Based on the analysis result of the relationship between the combination of process parameters and the oil quality indicators, set the process parameters as row items and the quality indicators as column items, and fill the correlation coefficient of each quality indicator into the corresponding cell of the matrix to obtain the process parameter mapping matrix.

[0020] As a further solution of the present invention, the steps for obtaining the predicted value of the oil quality indicator under the current production conditions are specifically as follows:

[0021] Based on the data in the process parameter mapping matrix, associate the standardized value of each parameter with the corresponding correlation coefficient and perform mapping processing to obtain the mapping value of the peanut oil production parameters;

[0022] According to the mapping value of the peanut oil production parameters, use the formula:

[0023]

[0024] Calculate the predicted value of the oil quality indicator under the current production conditions , and obtain the prediction result of the oil quality indicator;

[0025] Among them, is the constant term in the regression equation and is the reference level of the predicted value, is the regression coefficient, which is used to measure the influence intensity of each process parameter on the quality indicator, is the mapping value of the standardized process parameter.

[0026] As a further solution of the present invention, the steps for obtaining the deviation evaluation result are specifically as follows:

[0027] Based on the prediction result of the oil quality indicator, compare the predicted value of the oil quality indicator under the current production conditions with the expected quality standard, analyze the deviation between the quality indicators including acid value, peroxide value and purity, and obtain the deviation value of each indicator;

[0028] Based on the deviation value of each indicator, compare the deviation value with the specified standard range, judge whether it is necessary to adjust the process parameters, analyze the direction that needs to be optimized, and generate the deviation evaluation result.

[0029] As a further solution of the present invention, the steps for obtaining the smoothing parameter setting value and the stability parameter setting value are specifically as follows:

[0030] Based on the peanut oil production parameter values collected in real time, the current value of the parameter is compared one by one with the preset threshold range to determine whether the parameter exceeds the maximum or minimum allowable value, and a list of parameters outside the range is obtained;

[0031] Based on the list of parameters outside the range, the formula is used:

[0032]

[0033] Calculate the smoothed process parameter value , and obtain the smoothed parameter setting value;

[0034] Among them, is the current real-time collected process parameter value, is the smoothing factor, is the number of data points collected in the past, is the th process parameter value in the data set collected in the past;

[0035] Based on the parameters within the threshold range, according to the deviation evaluation result, analyze the deviation situation of the parameters and judge their stability. If the deviation of the parameter is within the allowable range, directly use its current value as the stable setting value to obtain the stable parameter setting value.

[0036] As a further solution of the present invention, the steps for obtaining the load balancing parameter are specifically as follows:

[0037] Based on the current peanut oil production status, check the key production parameters collected in real time, compare the current value of the parameter with the preset threshold range, judge whether load balancing processing is required, and if the parameter exceeds the preset range, mark it as the load status to obtain the determination result of the load balancing demand;

[0038] According to the determination result of the load balancing demand, the formula is used:

[0039]

[0040] Calculate the balanced load adjustment value , and generate the load balancing parameter;

[0041] Among them, is the currently collected production parameter value, is the weight coefficient of the production parameter , is the production parameter benchmark value, is the production parameter adjustment coefficient.

[0042] As a further solution of the present invention, the steps for obtaining the processing result of the global parameters for peanut oil production control are specifically as follows:

[0043] Based on the set value of the smoothing parameter or the set value of the stability parameter, combined with the predicted value of the oil quality index under the current production conditions, evaluate the influence of each production parameter on the oil quality, and perform iterative optimization to obtain the set value of the optimized process parameter;

[0044] According to the set value of the optimized process parameter, compare the adaptability of the load balancing parameter and the set value of the process parameter under the load condition, and perform adaptive adjustment to obtain the processing result of the global parameters for peanut oil production control.

[0045] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0046] In the present invention, through the in-depth correlation analysis of multiple parameters in the production process, a mapping relationship between process parameters and oil quality indexes is established, improving the accuracy and reliability of quality control. In process control, through the standardization and linear combination analysis of parameters such as pressing temperature, pressure, time, and stirring speed, the specific influence of each production link on the quality index is accurately reflected. By predicting the quality index under the current production conditions, the reaction speed to quality changes is improved, enabling rapid analysis and evaluation of quality index deviations in real-time data monitoring, and reducing the risk of product quality fluctuations caused by lagged reactions. In terms of abnormal parameter processing, smoothing processing is performed on parameters exceeding the preset threshold, ensuring the stability of production parameters and avoiding problems such as increased equipment load and energy consumption caused by parameter deviation from the standard value, which helps to extend the stable operation cycle of the equipment. In addition, under the load condition, the load balancing operation of production parameters enables effective isolation of the interference of secondary factors on production parameters under complex production conditions, improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is the system flow chart of the present invention;

[0048] Figure 2 is the flow chart of the linear combination of peanut oil production parameters of the present invention;

[0049] Figure 3 is the flow chart of obtaining the process parameter mapping matrix of the present invention;

[0050] Figure 4 is the flow chart of obtaining the predicted value of the oil quality index under the current production conditions of the present invention;

[0051] Figure 5 is the flow chart of obtaining the deviation evaluation result of the present invention;

[0052] Figure 6 Flow chart for obtaining the smoothing parameter setting value and the stability parameter setting value of the present invention;

[0053] Figure 7 Flow chart for obtaining the load balancing parameter of the present invention;

[0054] Figure 8 Flow chart for obtaining the processing result of the global parameter of peanut oil production control of the present invention. Specific embodiments

[0055] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0056] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, in the description of the present invention, "a plurality of" means two or more unless otherwise specifically defined.

[0057] Please refer to Figure 1 , an intelligent optimization system for the peanut oil production control process includes:

[0058] The process parameter modeling module collects the peanut oil production parameters such as pressing temperature, pressing pressure, pressing time and stirring speed, and performs standardization processing to make the parameters have the same scale. Using the partial least squares regression algorithm, a linear combination of the peanut oil production parameters is performed, and the correlation between the peanut oil production parameters and the oil quality indexes such as acid value, peroxide value and purity is analyzed to obtain the process parameter mapping matrix;

[0059] The real-time data collection and prediction module maps the data of the process parameter mapping matrix collected in real time through multi-dimensional vector operations, constructs a regression equation and solves the mapping relationship to obtain the predicted value of the oil quality index under the current production conditions, compares it with the expected quality standard, analyzes the deviation of the quality index, and obtains the deviation evaluation result;

[0060] The dynamic parameter smoothing module compares the current value of the peanut oil production parameters with the preset threshold range, determines whether the current peanut oil production parameters exceed the preset threshold. The preset threshold is the maximum and minimum allowable values of the pressing temperature, pressing pressure, pressing time, and stirring speed. The Laplace smoothing algorithm is used to smooth the parameters that exceed the range to obtain the smoothed parameter setting value. If the parameters are within the normal range, combined with the deviation evaluation results, the stable parameter setting value is obtained for the parameters within the normal range. Combining the current peanut oil production status, it is determined whether load balancing is required. If so, the multiple interpolation algorithm is used to calculate the load balancing of the production parameters to generate the load balancing parameters;

[0061] Based on the smoothed parameter setting value or the stable parameter setting value, combined with the predicted value of the oil quality index under the current production conditions, the process optimization and adjustment module makes a refined adjustment to the peanut oil production parameters. By adding or removing independent variables, it evaluates the influence degree of the parameters on the oil quality, retains the production parameters that affect the oil quality, and obtains the optimized process parameter setting value. Integrating the optimized process parameter setting value and the load balancing parameters, the global parameter data processing result of peanut oil production control is obtained;

[0062] The process parameter mapping matrix includes the linear combination parameters of the pressing temperature, pressing pressure, pressing time, and stirring speed, as well as the influence weight distribution on the acid value, peroxide value, and purity. The deviation evaluation results include the acid value deviation value, peroxide value deviation value, and purity deviation value, and are refined into the deviation range and trend analysis of each index. The load balancing parameters include the load distribution adjustment values of the pressing temperature, pressing pressure, pressing time, and stirring speed, as well as the balance coefficient applicable to the load state. The global parameter data processing result of peanut oil production control includes the optimized pressing temperature setting value, pressing pressure setting value, pressing time setting value, and stirring speed setting value. In addition, it also includes the parameter selection that has a significant impact on the key quality indicators.

[0063] Please refer to Figure 2 , the specific steps for obtaining the linear combination of the peanut oil production parameters are as follows:

[0064] Based on the collected peanut oil production parameters, including the pressing temperature, pressing pressure, pressing time, and stirring speed, the parameters are standardized and given inconsistent weights for linear combination to generate the process parameter combination value;

[0065] The collected peanut oil production parameters such as pressing temperature, pressing pressure, pressing time, and stirring speed are read by the collection equipment in sequence and transmitted into the system. To make the data have a unified dimension, the standardized processing method is used to unify the collected parameter data, removing the differential influence brought by different dimensions of each parameter. During the standardization process, for example, the pressing temperature is standardized to the interval [0,1], that is, the original temperature value and correspond to 0 and 1 respectively. They are converted into standardized values through the formula . The pressing pressure is also divided into the range of [0, 1] using a similar formula, while the pressing time is standardized to the range of [0, 10], and the stirring speed is standardized to the range of [1, 1]. After standardization, the parameters are integrated through linear combination. For example, in the specific combination process, the pressing temperature (T), pressing pressure (P), pressing time (t), and stirring speed (S) are respectively assigned weight coefficients a, b, c, and d for linear weighted combination. The weight coefficients are adjusted by analyzing the impact of production data on the oil quality. For example, by setting multiple groups of different weights through experiments and observing the impact of different weight combinations on the acid value to determine the appropriate weight configuration, the combination formula is obtained: combined value . The combination process is to sequentially take the standardized values of each parameter, multiply them by the corresponding weight coefficients and add them up to finally obtain the combined process parameter value .

[0066] Based on the combined value of the process parameters, the formula:

[0067]

[0068] is used to calculate the correlation coefficient , and the correlation coefficient between the process parameters and the oil quality is obtained;

[0069] Among them, represents the linear correlation strength between the combined value of the process parameters and the oil quality index, and is used to judge the overall combination effect of the process parameters, is 's average value, representing the average combined value of the process parameters in multiple batches of production, is the oil quality index value, obtained through actual detection, including parameters such as acid value, peroxide value, and purity. The oil quality detection can be carried out through standard experimental methods (such as titration method, chromatography method). For example, the acid value is measured using the standard titration method, and the acid value data of the oil products in multiple batches of production are recorded, is 's average value, representing the average oil quality index value in multiple batches of production, used to compare the deviation between single - batch production and the overall quality level, is 's sum of the accumulated products of the deviations from , used to measure the linear deviation degree between the process parameter value and the quality index, is the sum of the squared deviations of the combined value of the process parameters, representing the fluctuation range of the process parameters, is the sum of the squared deviations of the oil quality index, used to evaluate the fluctuation range of the production quality.

[0070] If the combined value of process parameters is 54.75, and the average value of the combined values for multiple batches is 50. The actually measured value of the oil quality index is 55, and the average value of the quality indices for multiple batches is 52.

[0071] Calculate the correlation coefficient:

[0072]

[0073] The result shows that the correlation coefficient is 1.

[0074] Please refer to Figure 3 , the steps for obtaining the process parameter mapping matrix are specifically as follows:

[0075] Based on the correlation coefficient between process parameters and oil quality, judge the linear relationship between the process parameter combination and the oil quality index. Analyze the impact of parameter adjustment on the quality index by examining the value of the correlation coefficient to obtain the analysis result of the relationship between the process parameter combination and the oil quality index;

[0076] A correlation coefficient of 1 indicates a perfect linear relationship between the combined value of process parameters and the oil quality index. When , it means there is a perfect positive linear relationship between variables, that is, an increase in one variable will cause an increase in the other variable at a constant ratio. This relationship implies that the data points fall exactly on a straight line with a positive slope. When , it indicates a perfect negative linear relationship, that is, an increase in one variable will cause a decrease in the other variable at a constant ratio, and the data points fall on a straight line with a negative slope. When , it means there is no linear relationship, and there is no constant positive or negative linear trend between the two variables. Therefore, a correlation coefficient of 1 means that the linear fitting effect of the variables reaches the optimal, and all data points perfectly match a straight line with a positive slope without any deviation. This value shows that under the current process combination, the relationship between the production parameters of peanut oil (such as pressing temperature, pressure, time, etc.) and the oil quality indices (such as acid value, peroxide value, purity) is completely linear, that is, the adjustment of parameters directly leads to a proportional change in the quality index without non - linear fluctuations or randomness. Therefore, obtaining a correlation coefficient of 1 indicates that the current process parameter combination is stable and completely predictable, which helps to precisely control the oil quality index in production.

[0077] Based on the analysis result of the relationship between the process parameter combination and the oil quality index, set the process parameters as row items and the quality indices as column items, and fill the correlation coefficient of each quality index into the corresponding cell of the matrix to obtain the process parameter mapping matrix;

[0078] In peanut oil production, the process parameters can include pressing temperature, pressing pressure, pressing time, and stirring speed, while the quality indicators usually include acid value, peroxide value, and purity. The purpose of the mapping matrix is to detail the contribution ratio or correlation coefficient of each process parameter to each quality indicator. After determining the process parameters and quality indicators, set the process parameters as the row items of the matrix. For example, pressing temperature, pressing pressure, pressing time, and stirring speed are used as the row items of the matrix in sequence, while the quality indicators of acid value, peroxide value, and purity are used as the column items. In this way, each cell of the matrix represents the correlation or contribution value between a process parameter and a quality indicator. When filling the matrix, it is necessary to calculate the correlation coefficient of each process parameter to each quality indicator one by one. For example, after calculation, the correlation coefficient between pressing temperature and acid value is 0.85, which indicates that pressing temperature has a relatively high influence on acid value. Therefore, 0.85 is filled into the intersection position of pressing temperature and acid value in the matrix as a specific value. Similarly, the correlation coefficient between pressing pressure and acid value is 0.75, and this value is also filled into the corresponding position of pressing pressure and acid value in the matrix. According to this process, continue to fill the combined relationships of other process parameters and quality indicators. For example, the correlation coefficient between pressing temperature and peroxide value is 0.6, and the correlation coefficient between stirring speed and purity is 0.9. These values are filled into the corresponding matrix cells one by one. After completing the correlation filling of all parameters, the mapping matrix is a structural diagram that comprehensively shows the influence of process parameters on quality indicators. This matrix not only provides an analysis of the contribution to each quality indicator (such as acid value, peroxide value, and purity), but also provides a basis for production adjustment, enabling producers to clearly identify the production parameters that affect different quality indicators and precisely adjust the parameters in subsequent production processes. The process parameter mapping matrix constructed in this way can support production control, enabling the oil quality to reach a stable standard.

[0079] Please refer to Figure 4 , the specific steps for obtaining the predicted values of the oil quality indicators under the current production conditions are as follows:

[0080] Based on the data in the process parameter mapping matrix, associate the standardized value of each parameter with the corresponding correlation coefficient and perform mapping processing to obtain the mapping values of peanut oil production parameters;

[0081] For the real-time collected data of the process parameter mapping matrix, including the standardized production parameters of pressing temperature, pressing pressure, pressing time, and stirring speed, and the correlation coefficients of these parameters to the oil quality indicators (such as acid value, peroxide value, and purity), perform mapping processing. The specific mapping process is to multiply each real-time collected standardized parameter value by the corresponding correlation coefficient to obtain the mapping value of this parameter to the target quality indicator. For example, assume that the standardized pressing temperature value is 0.8 and the correlation coefficient is 0.85, then its mapping value is . Similarly, assuming the standardized pressing pressure is 0.9 and the correlation coefficient is 0.75, the mapped value is obtained as . According to this method, the standardized values of all process parameters are multiplied by their respective correlation coefficients one by one to generate the mapped value of each parameter. Finally, these mapped values will be used as input variables in the regression equation for the next step of predicting the oil quality index.

[0082] Based on the mapped values of the peanut oil production parameters, using the formula:

[0083]

[0084] Calculate the predicted value of the oil quality index under the current production conditions , and obtain the prediction result of the oil quality index;

[0085] Among them, is used to estimate the quality index situation under the current process conditions. A regression model is constructed based on the production data collected in the past and their corresponding quality inspection results, and the process parameters are combined into predicted values , which is convenient for quality control, is the constant term in the regression equation, which is the reference level of the predicted value and reflects the basic quality index without other process parameters. It is obtained through the process of regression analysis and usually depends on the data collected in multiple batches in the past. It is determined based on multiple experimental or actual production data. For example, through 10 batches of production data, when the standardized values of all other parameters are 0, this constant term is obtained as the basic predicted value. is the regression coefficient, which is used to measure the influence intensity of each process parameter on the quality index. Each regression coefficient is obtained by fitting the data collected in the past for each process parameter and the quality index, and reflects the weight of each parameter. The process of determining these coefficients usually uses methods such as partial least squares regression (PLS). For example, multiple batches of data are used to analyze the linear relationship between the pressing temperature and the acid value, so as to obtain the value of, and the other regression coefficients are calculated in a similar way. are the mapped values of the standardized process parameters, corresponding to the pressing temperature, pressing pressure, pressing time, and stirring speed respectively. They have been standardized according to the actual collected data and the mapped values are obtained through correlation analysis.

[0086] For example, if the following standardized mapped values are obtained during the mapping process: (mapped value of pressing temperature), (mapped value of pressing pressure), (mapped value of pressing time), (mapped value of stirring speed), and the regression coefficients are assumed to be , , , , , substitute into the formula:

[0087]

[0088]

[0089] The result shows that the predicted acid value under the current process conditions is 3.5065.

[0090] Please refer to Figure 5 , and the specific steps for obtaining the deviation evaluation result are as follows:

[0091] Based on the predicted results of the oil quality indicators, compare the predicted values of the oil quality indicators under the current production conditions with the expected quality standards, analyze the deviations among the quality indicators including acid value, peroxide value, and purity, and obtain the deviation values for each indicator;

[0092] Under the current production conditions, the predicted value of the oil quality indicator calculated by the regression equation , compare it with the expected quality standard to evaluate the effectiveness of the current process settings. Assume that the quality standard for the expected acid value is 3.5, and this standard value is a benchmark determined based on previously collected data or industry requirements to ensure product quality consistency and safety. Compare the predicted value with the target value of 3.5, and calculate the deviation value as . The deviation value is 0.0065, indicating that the production parameters under the current process are close to the target value and the standard deviation is within a reasonable range. To further verify the rationality of the process settings, the predicted values of other quality indicators can be referred to. For example, if the predicted peroxide value is 1.02 and the expected standard is 1.0, through a similar deviation calculation , the deviation of the peroxide value can be obtained as 0.02. Similarly, assume that the predicted purity value is 99.8% and the target standard is 99.9%, then the deviation of the purity is . Through this comparison, the deviation degree of the process parameters from each quality indicator can be evaluated item by item, so as to understand the overall quality performance under the current production conditions. The calculation results of the deviation values provide a quantitative basis for subsequent deviation evaluations.

[0093] Based on the deviation value of each indicator, compare the deviation value with the specified standard range, judge whether the process parameters need to be adjusted, analyze the direction that needs to be optimized, and generate the deviation evaluation result.

[0094] Based on the calculated deviation results, analyze the deviation magnitudes of each quality indicator to obtain the final deviation assessment result. The process of deviation assessment is to compare the deviation value of each indicator with the specified allowable range to determine whether the current process needs to be adjusted. For example, assuming the allowable deviation range is ±0.01, for the acid value deviation it is concerned, the deviation value is less than 0.01, indicating that the predicted value of the acid value is close enough to the standard value and no adjustment is required. Similarly, the deviation of the peroxide value is 0.02, exceeding the allowable range of 0.01, meaning that the predicted value of this indicator deviates significantly from the target value and relevant process parameters need to be further adjusted, such as reducing the pressing temperature or adjusting the stirring speed to improve the peroxide value. In addition, if the deviation of the purity is 0.1%, which also exceeds the allowable range, it should be pointed out in the assessment result that the process parameters need to be optimized, such as extending the pressing time or controlling the stirring speed to increase the purity of the product. By analyzing the deviation magnitudes item by item in this way, the specific impact of each process parameter on the quality indicator can be identified, and the direction of optimization can be obtained. The deviation assessment result provides a basis for adjusting the production process to ensure the stability of the oil quality and compliance with the set quality standards. The final assessment process clarifies the priority and refinement measures for process adjustment, which helps to continuously optimize the production conditions to meet the quality control requirements.

[0095] Please refer to Figure 6 , the specific steps for obtaining the smoothing parameter setting value and the stability parameter setting value are as follows:

[0096] Based on the real-time collected peanut oil production parameter values, compare the current values of the parameters with the preset threshold ranges one by one to determine whether the parameters exceed the maximum or minimum allowable values, and obtain a list of parameters that exceed the ranges;

[0097] If during the pressing process of the currently produced peanut oil, the following real-time process parameters are collected: Pressing temperature: The current value is 145°C (the preset threshold range is 120 - 140°C); Pressing pressure: The current value is 85 MPa (the preset threshold range is 80 - 90 MPa); Pressing time: The current value is 35 minutes (the preset threshold range is 30 - 40 minutes); Stirring speed: The current value is 75 rpm (the preset threshold range is 50 - 80 rpm). By comparing each real-time collected parameter value with the preset threshold range one by one, it is judged whether each parameter is within the allowable range: For the pressing temperature: The current value is 145°C, exceeding the preset upper limit of 140°C, so this parameter is outside the threshold range and needs to be smoothed. For the pressing pressure: The current value is 85 MPa, within the threshold range (80 - 90 MPa), indicating that this parameter is within the normal range and no further processing is required. For the pressing time: The current value is 35 minutes, also within the range of 30 - 40 minutes, no adjustment is needed. For the stirring speed: The current value is 75 rpm, also within the threshold range of 50 - 80 rpm, no further processing is required. Through this process, it is determined which parameters are within the allowable range and the out-of-range parameters (i.e., the pressing temperature) that need to be smoothed.

[0098] Based on the list of out-of-range parameters, use the formula:

[0099]

[0100] Calculate the smoothed process parameter value , and obtain the smoothed parameter setting value;

[0101] Where, is the result after smoothing the original parameter value, which is used to replace the initial parameter value that deviates from the threshold to ensure that the parameter value returns to the allowable range, is the current real-time collected process parameter value, obtained in real time through sensors, is the smoothing factor, which controls the strength of smoothing and is usually obtained through the analysis of data collected in the past. For example, if there are deviations exceeding the threshold multiple times during the production process, and it is found through analysis that a smoothing factor of 0.5 can effectively adjust the out-of-range value to the allowable range, then 0.5 is used as the setting value, generally set according to the stability of the fluctuations in the data collected in the past, is the number of data points collected in the past, indicating the number of data collected in the past for smoothing calculation. The appropriate amount of batch data collected in the past can be selected through system settings to ensure that the smoothing calculation conforms to the current production situation, is the th process parameter value in the data set collected in the past, indicating the corresponding parameter value collected in the past batches.

[0102] For example, if the pressing temperature collected in real time is 145°C, which exceeds the threshold range, so it needs to be smoothed. Take the smoothing factor and use the temperature values collected in the past five times (140°C, 138°C, 136°C, 135°C, and 137°C) as , and substitute them into the formula for calculation:

[0103] Calculate the sum of the differences of the data collected in the past:

[0104]

[0105] Find the average difference:

[0106]

[0107] Calculate the smoothed value:

[0108]

[0109] The results show that the temperature value obtained after smoothing is 141.1°C, which has been adjusted back to the threshold range compared with 145°C that exceeds the threshold.

[0110] Based on the parameters that meet the threshold range, according to the deviation evaluation results, analyze the deviation of the parameters and judge their stability. If the deviation of the parameters is within the allowable range, directly use its current value as the stable set value to obtain the stable parameter set value;

[0111] For other parameters that meet the threshold range (pressing pressure, pressing time, and stirring speed), no smoothing is required, but the set value is further optimized in combination with the deviation evaluation results. For example, for the pressing pressure: the deviation evaluation results show that the deviation of the pressure is less than 0.01, indicating that this parameter matches the quality standard. 85 MPa can be directly set as the stable production set value. For the pressing time: the deviation evaluation shows that the acid value fluctuation of the current pressing time is small and the acid value is within the standard range. Therefore, the current 35 minutes can be used as the stable set value of the pressing time. For the stirring speed: the deviation evaluation results show that the deviation is 0.02. Although there is a slight fluctuation, it is still within the allowable range. Therefore, a stirring speed of 75 rpm is suitable as the stable production set value. Through this process, the following stable process parameter settings are obtained: Pressing temperature: adjusted to 141.1°C after smoothing, meeting the threshold range. Pressing pressure: 85 MPa (stable set value) Pressing time: 35 minutes (stable set value) Stirring speed: 75 rpm (stable set value). The results show that through real-time monitoring, smoothing, and deviation evaluation, each parameter can be kept within a reasonable range to ensure the stability of the production process and the qualification of the oil quality.

[0112] Please refer toFigure 7 , the steps for obtaining the load balancing parameters are specifically as follows:

[0113] Based on the current peanut oil production status, check the key production parameters collected in real time, compare the current values of the parameters with the preset threshold range, determine whether load balancing processing is required. If the parameter exceeds the preset range, it is marked as the load status to obtain the determination result of the load balancing requirement;

[0114] Combined with the current peanut oil production status, check each key production parameter (such as pressing temperature, pressing pressure, pressing time, and stirring speed) collected in real time one by one, compare its current value with the preset threshold range, and judge whether to trigger the load status balancing processing according to the load status conditions. The specific judgment process is as follows: If the current value of a certain parameter exceeds the upper limit of its preset threshold range, it is marked as "out of range"; if all parameters are within the normal range, the production is in a stable state and there is no need to trigger load balancing; if a certain production parameter (such as pressing temperature) exceeds the set threshold range, it is judged that the production status has reached the load status and subsequent load balancing operations need to be performed. For example, in a detection, the collected pressing temperature is 150 °C (exceeding the set upper limit of 140 °C), the pressing pressure is 85 MPa (within the preset range of 80 - 90 MPa), the pressing time is 32 minutes (within the preset range of 30 - 40 minutes), and the stirring speed is 77 rpm (also within the preset range of 50 - 80 rpm). Although the pressing pressure, time, and stirring speed all meet the standard range, since the pressing temperature exceeds the preset upper limit, it is determined that the production load has reached the peak and the load balancing processing flow needs to be entered. On the contrary, if all the collected parameters meet the preset threshold range, the current production status is maintained and there is no need to perform load balancing operations.

[0115] According to the determination result of the load balancing requirement, use the formula:

[0116]

[0117] Calculate the load adjustment value after balancing , and generate the load balancing parameters;

[0118] Among them, is the target value of the production parameter after equilibrium calculation under the load state, which is used to guide the actual adjustment of this parameter to ensure that this parameter is close to its reference value, is the currently collected production parameter value, representing the real-time data of this production parameter (such as pressing temperature, pressing pressure, pressing time, or stirring speed) measured currently under the load state, which is obtained by real-time collection through sensors or monitoring devices, is the production parameter The weight coefficient reflects the degree of influence of this parameter on the overall load balance and is usually set through the analysis of production data collected in the past. If a certain parameter has a greater impact on the equipment operation load, a higher weight will be set to ensure that this parameter receives a more significant balance adjustment. is the production parameter The reference value, that is, the set value under the ideal or standard load state, reflects the target value of this parameter in production and is usually determined through data collected in the past or equipment recommended values. For example, if the data collected in the past shows that the pressing temperature is stable at 140°C, then 140°C can be set as the reference value of this parameter. , is the production parameter The adjustment coefficient is used to control the amplitude of the balance adjustment. This coefficient reflects the smoothness of the parameter during the adjustment process and avoids drastic adjustments for parameters with large deviations. The adjustment coefficient is usually set according to the parameter volatility. For example, when the pressing temperature deviates greatly, a higher value can be set to reduce its adjustment amplitude and avoid load instability that may be caused by rapid changes.

[0119] For example, if the production parameters of the current load state are: pressing temperature 150°C, pressing pressure 88 MPa, pressing time 32 minutes, and stirring speed 77 rpm. The reference values are set as: pressing temperature 140°C, pressing pressure 85 MPa, pressing time 35 minutes, and stirring speed 75 rpm. The weights and adjustment coefficients of each parameter are as follows: the temperature weight is 0.4 and the adjustment coefficient is 0.5; the pressure weight is 0.3 and the adjustment coefficient is 0.3; the time weight is 0.2 and the adjustment coefficient is 0.2; the stirring speed weight is 0.1 and the adjustment coefficient is 0.1. Substitute into the formula for calculation:

[0120] The load balance value of the temperature:

[0121]

[0122] The load balance value of the pressure:

[0123]

[0124] The load balance value of the time:

[0125]

[0126] The load balance value of the stirring speed:

[0127]

[0128] The calculated load balance adjustment value is the target adjustment value for each production parameter. For example, the temperature is adjusted to 147.33°C, the pressure is adjusted to 87.31 MPa, the time is adjusted to 32.5 minutes, and the stirring speed is adjusted to 76.82 rpm. Through this balance adjustment, each production parameter gradually approaches its reference value, thereby reducing fluctuations under the load condition, enabling the production system to maintain stability under the load condition, and ensuring smooth operation of the equipment.

[0129] Please refer to Figure 8 , and the steps for obtaining the processing result of the global parameters for peanut oil production control are specifically as follows:

[0130] Based on the smoothing parameter setting value or the stable parameter setting value, combined with the predicted value of the oil quality index under the current production conditions, evaluate the impact of each production parameter on the oil quality, and perform iterative optimization to obtain the optimized process parameter setting value;

[0131] First, evaluate the degree of influence of each production parameter on the oil quality. During the evaluation process, by gradually analyzing each parameter, examine the sensitivity of its fluctuations to quality indicators such as acid value and peroxide value, and judge whether the influence is significant through deviation evaluation. Specifically, when the change range of the acid value or peroxide value caused by the fluctuation of a certain parameter exceeds the allowable range (for example, when the acid value change exceeds 0.1 or the peroxide value change exceeds 0.5), it can be considered that the parameter has a significant impact on the oil quality; if the improvement range of a certain parameter on the acid value is less than 0.05 or the improvement range on the peroxide value is less than 0.2, and the quality indicators all meet the standard requirements, it can be considered that the parameter has a small improvement effect on the oil quality, and it can be considered to be excluded or the optimization priority can be reduced. During the optimization process, dynamically adjust in combination with the deviation between the predicted value and the actual result. First, monitor the difference between the actual collected value and the model predicted value of the parameters during the production process in real time. For example, when it is predicted that the acid value should be 3.50 at a pressing temperature of 140°C, but the actual production result shows that the acid value is 3.65 and the deviation reaches 0.15, it is necessary to dynamically adjust the temperature optimization direction and further refine the control range (such as 135–145°C) to reduce the deviation. At the same time, conduct a stability evaluation on the parameters with small deviations. For example, if the deviation of the actual stirring speed is within the allowable range (±2 rpm), and the change range of the acid value or peroxide value is not sufficient to significantly improve the oil quality, its current value can be directly set as the stable value to reduce further intervention on it during the optimization process. By continuously analyzing the deviation between the predicted value and the actual result and its change trend, dynamically adjust the optimization direction and parameter combination to ensure that the optimization of production parameters can significantly improve the quality indicators, and finally determine a set of optimized process parameter setting values to achieve the stability of oil quality and the high efficiency of process control.

[0132] According to the optimized process parameter set values, compare the adaptability of the load balancing parameters and the process parameter set values under the load condition, and perform adaptive adjustment to obtain the processing result of the global parameters for peanut oil production control;

[0133] After completing the optimization and adjustment of each process parameter, integrate the optimized process parameter set values with the load balancing parameters according to the process requirements of the equipment under different load states. First, compare the load balancing parameters with the optimized process parameter set values to evaluate their adaptability under the load state. This process mainly includes the following steps: Based on the smoothed and optimized process parameters (such as pressing temperature, pressing pressure, stirring speed, etc.), clarify the ideal set value of each parameter. For example, under normal production conditions, the reference value of the pressing temperature is 125 °C, the pressure is 85 MPa, and the stirring speed is 75 rpm. These reference values will be used as the control standards for the adaptability evaluation under the load state. Under the production load state, collect the real-time data of each parameter. For example, the current value of the temperature rises to 130 °C, the pressure rises to 88 MPa, etc. Based on these load state data, calculate the equilibrium value of each parameter through the load balancing formula to measure the actual load level of each production parameter. Compare the load balancing parameters with the set values of each process parameter to check whether each parameter is within the allowable deviation range. For example, if the equilibrium value of the pressing temperature is 128 °C, which is 3 °C different from the set value of 125 °C and within the allowable deviation range (±5 °C) of the equipment, it is considered that the temperature parameter is well adapted under the load state; if the equilibrium value of the pressing pressure is 90 MPa, exceeding the allowable upper limit, it is necessary to further adjust the set value or add a pressure reduction measure in the equipment. By comparing the deviations between each process parameter and the load balancing parameter, generate an adaptability evaluation report to reflect the overall adaptability under the load state. If the deviation of a certain production parameter is too large and not within the allowable range, it is recorded as non-adapted, and this parameter is marked as needing further optimization. For the non-adapted parameter, further adjust its set value and incorporate the adjusted new set value into the global control scheme. For example, lower the pressing pressure to 87 MPa suitable for the load state, and keep the temperature at 128 °C, etc.

[0134] The above is only a preferred embodiment of the present invention and does not limit the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent optimization system for the peanut oil production control process, characterized in that, The system includes: The process parameter modeling module collects peanut oil production parameters, including pressing temperature, pressing pressure, pressing time, and stirring speed. By performing a linear combination of the peanut oil production parameters, analyzing the correlation of the peanut oil production parameters with quality indicators, a process parameter mapping matrix is obtained; The real-time data collection and prediction module maps the data of the process parameter mapping matrix collected in real time. By solving the mapping relationship, a predicted value of the oil quality indicator under the current production conditions is obtained, and a deviation evaluation result is obtained by comparing it with the expected quality standard; The dynamic parameter smoothing module compares the current value of the peanut oil production parameter with the preset threshold range, performs smoothing processing on the parameter outside the range to obtain a smoothed parameter setting value. If the parameter is within the normal range, combined with the deviation evaluation result, a stable parameter setting value is obtained for the parameter within the normal range. Combining the current peanut oil production status, it is judged whether load balancing is required. If so, load balancing calculation is performed on the production parameters to generate load balancing parameters; The process optimization and adjustment module performs refined adjustment on the peanut oil production parameters based on the smoothed parameter setting value or the stable parameter setting value to obtain an optimized process parameter setting value, and integrates the optimized process parameter setting value and the load balancing parameters to obtain the data processing result of the global parameters for peanut oil production control; The specific steps for obtaining the data processing result of the global parameters for peanut oil production control are as follows: Based on the smoothed parameter setting value or the stable parameter setting value, combined with the predicted value of the oil quality indicator under the current production conditions, the influence of each production parameter on the oil quality is evaluated and iteratively optimized to obtain an optimized process parameter setting value; According to the optimized process parameter setting value, the adaptability of the load balancing parameters and the process parameter setting value under the load condition is compared and adaptively adjusted to obtain the data processing result of the global parameters for peanut oil production control.

2. The intelligent optimization system for the peanut oil production control process according to claim 1, characterized in that, The specific steps for obtaining the linear combination of the peanut oil production parameters are as follows: Based on the collected peanut oil production parameters, including pressing temperature, pressing pressure, pressing time, and stirring speed, the parameters are standardized and inconsistent weights are assigned for linear combination to generate a process parameter combination value; Based on the process parameter combination value, the formula: Calculate the correlation coefficient , and obtain the correlation coefficient between the process parameters and the oil quality; Among them, is the average value, representing the average process parameter combination value in multi-batch production, is the oil quality index value, is the average value, representing the average oil quality index value in multi-batch production.

3. The intelligent optimization system for the peanut oil production control process according to claim 2, characterized in that, The specific steps for obtaining the process parameter mapping matrix are as follows: According to the correlation coefficient between the process parameter and the oil quality, the linear relationship between the process parameter combination and the oil quality indicator is judged. By analyzing the value of the correlation coefficient, the influence of parameter adjustment on the quality indicator is judged to obtain the relationship analysis result between the process parameter combination and the oil quality indicator; According to the relationship analysis result between the process parameter combination and the oil quality indicator, the process parameter is set as the row item and the quality indicator is set as the column item, and the correlation coefficient of each quality indicator is filled into the corresponding cell of the matrix to obtain the process parameter mapping matrix.

4. The intelligent optimization system for the peanut oil production control process according to claim 3, wherein The specific steps for obtaining the predicted value of the oil quality indicator under the current production conditions are as follows: Based on the data in the process parameter mapping matrix, the standardized value of each parameter is associated with the corresponding correlation coefficient and mapped to obtain the mapped value of the peanut oil production parameter; According to the mapped values of the peanut oil production parameters, use the formula: Calculate the predicted value of the oil product quality index under the current production conditions to obtain the prediction result of the oil product quality index; Among them, is the constant term in the regression equation and is the baseline level of the predicted value. is the regression coefficient, which is used to measure the influence intensity of each process parameter on the quality index. is the mapped value of the standardized process parameter.

5. The intelligent optimization system for the peanut oil production control process according to claim 4, characterized in that, The specific steps for obtaining the deviation evaluation result are as follows: Based on the predicted result of the oil product quality index, compare the predicted value of the oil product quality index under the current production conditions with the expected quality standard, analyze the deviation among the quality indexes including acid value, peroxide value and purity, and obtain the deviation value of each index; Based on the deviation value of each index, compare the deviation value with the specified standard range, judge whether it is necessary to adjust the process parameters, analyze the direction that needs to be optimized, and generate a deviation evaluation result.

6. The intelligent optimization system for the peanut oil production control process according to claim 5, wherein The specific steps for obtaining the smoothing parameter setting value and the stability parameter setting value are as follows: Based on the peanut oil production parameter values collected in real time, compare the current value of the parameter with the preset threshold range one by one, judge whether the parameter exceeds the maximum or minimum allowable value, and obtain a list of parameters that exceed the range; Based on the list of parameters that exceed the range, use the formula: Calculate the smoothed process parameter value to obtain the smoothed parameter setting value; Among them, is the process parameter value collected in real time currently, is the smoothing factor, is the number of data points collected previously, is the th process parameter value in the dataset collected previously; Based on the parameters that meet the threshold range, according to the deviation evaluation result, analyze the deviation situation of the parameters and judge their stability. If the deviation of the parameters is within the allowable range, directly use its current value as the stable setting value to obtain the stability parameter setting value.

7. The intelligent optimization system for the peanut oil production control process according to claim 1, characterized in that The specific steps for obtaining the load balancing parameter are as follows: Based on the current peanut oil production status, check the key production parameters collected in real time, compare the current value of the parameter with the preset threshold range, judge whether it is necessary to perform load balancing processing, and if the parameter exceeds the preset range, mark it as the load status to obtain the determination result of the load balancing requirement; According to the determination result of the load balancing requirement, use the formula: Calculate the adjusted load value after balancing , and generate load balancing parameters; Among them, is the value of the currently collected production parameter . is the weight coefficient of the production parameter . is the reference value of the production parameter . is the adjustment coefficient of the production parameter .

Images