Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides an intelligent optimization system for a peanut oil production control process.
In order to achieve the purpose, the invention adopts the following technical scheme that the intelligent optimization system for the peanut oil production control process comprises the following components:
the technological parameter modeling module collects peanut oil production parameters, and analyzes the correlation of the peanut oil production parameters to quality indexes by linearly combining the peanut oil production parameters to obtain a technological parameter mapping matrix;
the real-time data acquisition and prediction module maps the data of the process parameter mapping matrix acquired in real time, obtains a predicted value of an oil quality index under the current production condition by solving a mapping relation, and compares the predicted value with an expected quality standard to obtain a deviation evaluation result;
The dynamic parameter smoothing module compares the current value of the peanut oil production parameter with a preset threshold range, performs smoothing treatment on the parameter exceeding the range to obtain a smoothed parameter set value, if the parameter is in a normal range, combines the deviation evaluation result, obtains a stable parameter set value for the parameter in the normal range, combines the current peanut oil production state, judges whether load balancing is needed, and if so, performs load balancing calculation on the production parameter to generate a load balancing parameter;
And the process optimization adjustment module refines and adjusts the peanut oil production parameters based on the smooth parameter set value or the stable parameter set value, obtains an optimized process parameter set value, integrates the optimized process parameter set value and the load balancing parameter, and obtains a global parameter data processing result of peanut oil production control.
As a further scheme of the invention, the obtaining step for carrying out linear combination on peanut oil production parameters comprises the following steps:
based on the collected peanut oil production parameters including pressing temperature, pressing pressure, pressing time and stirring speed, carrying out standardized treatment on the parameters and endowing inconsistent weights to carry out linear combination so as to generate a technological parameter combination value;
Based on the combined values of the process parameters, the formula is adopted:
Calculating a correlation coefficientObtaining a correlation coefficient of the technological parameter and the oil quality;
Wherein, theIs thatRepresents the average process parameter combination value in the multi-batch production,Is an index value of the quality of oil products,Is thatAnd the average value of (2) represents the average oil quality index value in multi-batch production.
As a further aspect of the present invention, the step of obtaining the process parameter mapping matrix specifically includes:
judging the linear relation between the process parameter combination and the oil quality index according to the correlation coefficient of the process parameter and the oil quality, and analyzing the influence of the parameter adjustment on the quality index by analyzing the numerical value of the correlation coefficient to obtain a relation analysis result of the process parameter combination and the oil quality index;
and according to the analysis result of the relation between the technological parameter combination and the oil quality index, setting technological parameters as row items and quality indexes as column items, and filling the correlation coefficient of each quality index into a cell corresponding to the matrix to obtain a technological parameter mapping matrix.
As a further scheme of the invention, the method for obtaining the predicted value of the oil quality index under the current production condition comprises the following steps:
based on the data in the technological parameter mapping matrix, associating the standardized value of each parameter with the corresponding correlation coefficient, and carrying out mapping treatment to obtain the mapping value of the peanut oil production parameter;
According to the mapping value of the peanut oil production parameter, the formula is adopted:
Calculating the predicted value of the oil quality index under the current production conditionObtaining an oil quality index prediction result;
Wherein, theIs a constant term in the regression equation, is a reference level for the predicted value,Is a regression coefficient used for measuring the influence intensity of each technological parameter on the quality index,Is the mapping value of the standardized process parameters.
As a further aspect of the present invention, the step of obtaining the deviation evaluation result specifically includes:
Comparing the predicted value of the oil quality index under the current production condition with an expected quality standard based on the oil quality index prediction result, and analyzing the deviation among the quality indexes including the acid value, the peroxide value and the purity to obtain a deviation value of each index;
And comparing the deviation value with a specified standard range based on the deviation value of each index, judging whether the process parameters need to be adjusted, analyzing the direction needing to be optimized, and generating a deviation evaluation result.
As a further aspect of the present invention, the step of obtaining the smoothing parameter set value and the stability parameter set value specifically includes:
Based on the peanut oil production parameter values acquired in real time, comparing the current value of the parameter with a preset threshold range one by one, and judging whether the parameter exceeds a maximum or minimum allowable value or not to obtain an out-of-range parameter list;
Based on the out-of-range parameter list, the formula is adopted:
Calculating smoothed process parameter valuesObtaining a smooth parameter set value;
Wherein, theIs the current process parameter value acquired in real time,Is a smoothing factor which is used to smooth the image,Is the number of data points collected in the past,Is the first data set collected in the pastProcess parameter values;
And analyzing the deviation condition of the parameters and judging the stability of the parameters based on the parameters meeting the threshold range according to the deviation evaluation result, and if the deviation of the parameters is within the allowable range, directly taking the current value of the parameters as a stable set value to obtain a stable parameter set value.
As a further aspect of the present invention, the step of obtaining the load balancing parameter specifically includes:
Based on the current peanut oil production state, checking key production parameters acquired in real time, comparing the current value of the parameters with a preset threshold range, judging whether load balancing treatment is needed, and marking the load state if the parameters exceed the preset range to obtain a judging result of the load balancing requirement;
According to the judging result of the load balancing requirement, adopting the formula:
calculating a balanced load adjustment valueGenerating a load balancing parameter;
Wherein, theIs the current production parameter collectedIs used as a reference to the value of (a),Is a production parameterIs used for the weight coefficient of the (c),Is a production parameterIs used for the reference value of (a),Is a production parameterIs used for the adjustment of the coefficient of (c).
As a further scheme of the invention, the overall parameter data processing result of peanut oil production control is obtained by the following steps:
Based on the smooth parameter set value or the stable parameter set value, evaluating the influence of each production parameter on the oil quality by combining with the predicted value of the oil quality index under the current production condition, and performing iterative optimization to obtain an optimized process parameter set value;
and comparing the load balance parameter with the suitability of the process parameter set value under the load condition according to the optimized process parameter set value, and carrying out adaptive adjustment to obtain a peanut oil production control global parameter data processing result.
Compared with the prior art, the invention has the advantages and positive effects that:
In the invention, the mapping relation between the technological parameters and the oil quality index is established by deep level association analysis of multiple parameters in the production process, thereby improving the precision and reliability of quality control. In process control, the specific influence of each production link on the quality index is accurately reflected through standardized and linear combination analysis of parameters such as the squeezing temperature, the pressure, the time, the stirring speed and the like. By predicting the quality index under the current production condition, the reaction speed to the quality change is improved, so that the quality index deviation can be rapidly analyzed and evaluated in real-time data monitoring, and the product quality fluctuation risk caused by hysteresis reaction is reduced. In the aspect of abnormal parameter processing, the parameters exceeding the preset threshold value are subjected to smoothing processing, so that the stability of production parameters is ensured, the problems of equipment load increase and energy consumption rise caused by deviation of the parameters from the standard values are avoided, and the stable operation period of equipment is prolonged. In addition, under the condition of a load state, the load balancing operation on the production parameters is performed, so that the interference of secondary factors on the production parameters can be effectively isolated under the complex production condition, and the production efficiency is improved.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In the description of the present invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate describing the present invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention. Furthermore, in the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Referring to fig. 1, an intelligent optimization system for peanut oil production control process includes:
The technological parameter modeling module collects the peanut oil production parameters of the pressing temperature, the pressing pressure, the pressing time and the stirring speed, performs standardized treatment to enable the parameters to have the same scale, adopts a partial least squares regression algorithm to linearly combine the peanut oil production parameters, analyzes the correlation of the peanut oil production parameters on acid value, peroxide value and purity oil quality index, and obtains a technological parameter mapping matrix;
The real-time data acquisition and prediction module maps the data of the process parameter mapping matrix acquired in real time through multidimensional vector operation, obtains a predicted value of an oil quality index under the current production condition by constructing a regression equation and solving a mapping relation, compares the predicted value with an expected quality standard, analyzes the deviation of the quality index, and obtains a deviation evaluation result;
The dynamic parameter smoothing module compares the current value of the peanut oil production parameter with a preset threshold range, judges whether the current peanut oil production parameter exceeds the preset threshold, wherein the preset threshold is the maximum allowable value and the minimum allowable value of the squeezing temperature, the squeezing pressure, the squeezing time and the stirring speed, adopts a Laplacian smoothing algorithm to carry out smoothing treatment on the parameters exceeding the range to obtain a smoothed parameter set value, if the parameters are in a normal range, combines a deviation evaluation result, obtains a stable parameter set value for the parameters in the normal range, combines the current peanut oil production state, judges whether load balancing is needed, and if so, adopts a multiple interpolation algorithm to carry out load balancing calculation on the production parameters to generate a load balancing parameter;
The process optimization adjustment module performs refinement adjustment on peanut oil production parameters based on a smooth parameter set value or a stable parameter set value and combined with a predicted value of an oil quality index under the current production condition, retains production parameters affecting the oil quality by adding or removing the influence degree of independent variable evaluation parameters on the oil quality, acquires an optimized process parameter set value, integrates the optimized process parameter set value and a load balancing parameter, and acquires a peanut oil production control global parameter data processing result;
The process parameter mapping matrix comprises linear combination parameters of a pressing temperature, a pressing pressure, a pressing time and a stirring speed, influence weight distribution of the linear combination parameters on an acid value, a peroxide value and purity, deviation evaluation results comprise an acid value deviation value, a peroxide value deviation value and a purity deviation value, deviation ranges and trend analysis of each index are thinned, load balancing parameters comprise a load distribution adjustment value of the pressing temperature, the pressing pressure, the pressing time and the stirring speed, balance coefficients suitable for load state states, and peanut oil production control global parameter data processing results comprise optimized pressing temperature set values, pressing pressure set values, pressing time set values and stirring speed set values, and further comprise parameter choices which have significant influence on key quality indexes.
Referring to fig. 2, the steps for obtaining the linear combination of peanut oil production parameters are specifically:
based on the collected peanut oil production parameters including pressing temperature, pressing pressure, pressing time and stirring speed, carrying out standardized treatment on the parameters and endowing inconsistent weights to carry out linear combination so as to generate a technological parameter combination value;
the acquired peanut oil production parameters such as the squeezing temperature, the squeezing pressure, the squeezing time and the stirring speed are sequentially read through the acquisition equipment and are transmitted into the system, so that the acquired parameter data are unified by adopting a standardized processing method to remove the differential influence caused by different dimensions of the parameters so as to ensure that each item of data has unified dimensions. In the normalization process, e.g. the pressing temperature is normalized to within the interval [0,1], i.e. the raw temperature valueAndRespectively corresponding to 0 and 1, by the formulaThe values were normalized, the pressing pressure was also divided into the [0,1] intervals using a similar formula, the pressing time was normalized to the [0,10] range, and the stirring speed was normalized to the [1,1] interval. After normalization is completed, the parameters are integrated through linear combination, for example, the pressing temperature (T), the pressing pressure (P), the pressing time (T) and the stirring speed (S) are respectively given with weight coefficients a, b, c, d for linear weighted combination, and the weight coefficients are adjusted through analysis of the influence of production data on the quality of the oil product. For example, by experimentally setting a plurality of groups of different weights, observing the influence of different weight combinations on the acid value to determine a proper weight configuration, a combination formula is obtainedThe combination process sequentially takes the normalized values of the parameters, multiplies the normalized values by the corresponding weight coefficients and adds the multiplied values to finally obtain the combined process parameter values。
Based on the combined values of the process parameters, the formula is adopted:
Calculating a correlation coefficientObtaining a correlation coefficient of the technological parameter and the oil quality;
Wherein, theThe linear correlation strength between the process parameter combination value and the oil quality index is expressed and used for judging the overall combination effect of the process parameters,Is thatRepresents the average process parameter combination value in the multi-batch production,Is an index value of the quality of the oil product, is obtained through actual detection, comprises parameters such as acid value, peroxide value, purity and the like, the quality detection of the oil product can be carried out through standard experimental methods (such as titration method and chromatography method), for example, the acid value is measured by using the standard titration method, the acid value of the oil product produced in a plurality of batches is recorded,Is thatRepresents the average oil quality index value in the multi-batch production for comparing the deviation of single production from the overall quality level,Is thatAnd (3) withThe sum of the products of the deviations is used to measure the degree of linear offset between the process parameter value and the quality index,Is the sum of squares of the deviations of the combined values of the process parameters, represents the fluctuation range of the process parameters,Is the sum of squares of deviation of oil quality indexes and is used for evaluating the fluctuation range of production quality.
If the process parameter is combined with the value54.75, A combined value average of multiple batches50. Actually measuring the oil quality index value55, A plurality of batches of quality index mean value52.
Calculating a correlation coefficient:
the results indicate a correlation coefficient1.
Referring to fig. 3, the process parameter mapping matrix is obtained by the steps of:
Judging the linear relation between the process parameter combination and the oil quality index according to the correlation coefficient of the process parameter and the oil quality, and judging the influence of parameter adjustment on the quality index by analyzing the numerical value of the correlation coefficient to obtain a relation analysis result of the process parameter combination and the oil quality index;
A correlation coefficient of 1 indicates that the combination value of the process parameters and the oil quality index have complete linear relation, whenWhen it is indicated that there is a perfectly positive linear relationship between the variables, i.e. an increase in one variable will result in an increase in the other variable in a constant proportion. This relationship means that the data points fall entirely on a straight line with a positive slope. When (when)When a completely negative linear relationship is present, i.e., an increase in one variable results in a decrease in the other variable at a constant rate, the data points fall on a straight line of negative slope. When (when)When no linear relationship is shown, there is no constant positive or negative linear trend between the two variables. Thus, a correlation coefficient of 1 means that the linear fitting effect of the variables is optimal, and that all data points match exactly one straight line of positive slope, without any deviation. This value demonstrates that under the current process combinations, the relationship between peanut oil production parameters (e.g., press temperature, pressure, time, etc.) and oil quality indices (e.g., acid value, peroxide value, purity) is perfectly linear, i.e., adjustment of the parameters directly results in a proportional change in the quality index without nonlinear fluctuations or randomness. Thus, the result with a correlation coefficient of 1 indicates that the current combination of process parameters is stable and completely predictable, which is conducive to accurate control of the quality index of the oil in production.
According to the analysis result of the relation between the technological parameter combination and the oil quality index, setting technological parameters as row items and quality indexes as column items, and filling the correlation coefficient of each quality index into a cell corresponding to the matrix to obtain a technological parameter mapping matrix;
In peanut oil production, process parameters may include press temperature, press pressure, press time, and agitation speed, while quality indicators typically include acid number, peroxide number, and purity. The purpose of the mapping matrix is to show in detail the proportion of contribution or correlation coefficient of each process parameter to each quality index. After determining the process parameters and the quality index, the process parameters are set as row items of a matrix, for example, the pressing temperature, the pressing pressure, the pressing time, the stirring speed and the like are sequentially used as row items of the matrix, and the quality index acid value, the peroxide value and the purity are used as column items. Thus, each cell of the matrix represents a correlation or contribution of a process parameter to a quality index. When the matrix is filled, the correlation coefficient of each technological parameter to each quality index is calculated one by one. For example, the correlation coefficient of the press temperature and the acid value is calculated to be 0.85, which indicates that the press temperature has a high influence on the acid value. Thus, 0.85 is filled as a specific value into the matrix at the crossing position of the pressing temperature and the acid value. Similarly, the correlation coefficient of the press pressure to the acid value was 0.75, and this value was also filled in the corresponding position of the press pressure and the acid value in the matrix. According to such a procedure, the packing of the combined relationship of the other process parameters and the quality index is continued. For example, the correlation coefficient of the pressing temperature and the peroxide value is 0.6, the correlation coefficient of the stirring speed and the purity is 0.9, and the values are filled in the corresponding matrix units one by one. After the correlation filling of all parameters is completed, the mapping matrix is a structural diagram which comprehensively displays the influence of the technological parameters on the quality index. The matrix not only provides the analysis of the contribution condition of each quality index (such as acid value, peroxide value and purity), but also provides the basis for production adjustment, so that a producer can clearly identify the production parameters affecting different quality indexes, and accurately adjust the parameters in the subsequent production process. The process parameter mapping matrix constructed in this way can support production control, so that the quality of oil products can reach a stable standard.
Referring to fig. 4, the steps for obtaining the predicted value of the oil quality index under the current production condition specifically include:
based on the data in the technological parameter mapping matrix, associating the standardized value of each parameter with the corresponding correlation coefficient, and carrying out mapping treatment to obtain the mapping value of the peanut oil production parameter;
And mapping process is carried out on the process parameter mapping matrix data acquired in real time, wherein the process parameter mapping matrix data comprises standardized production parameters of pressing temperature, pressing pressure, pressing time and stirring speed, and correlation coefficients of the parameters on oil quality indexes (such as acid value, peroxide value and purity). The specific mapping process is to multiply each real-time acquired standardized parameter value with a corresponding correlation coefficient to obtain a mapping value of the parameter to the target quality index. For example, assuming that the normalized press temperature value is 0.8 and the correlation coefficient is 0.85, the mapped value is. Similarly, assuming that the normalized press pressure is 0.9 and the correlation coefficient is 0.75, a map value of 0.75 is obtained. According to the method, the standardized values of all the process parameters are multiplied with the respective correlation coefficients one by one to generate a mapping value of each parameter. Finally, the mapping values are used as input variables in a regression equation for predicting the oil quality index in the next step.
According to the mapping value of peanut oil production parameters, the formula is adopted:
Calculating the predicted value of the oil quality index under the current production conditionObtaining an oil quality index prediction result;
Wherein, theFor estimating quality index under current process conditions, constructing regression model based on the collected production data and its corresponding quality detection result, and combining process parameters into predicted valueIs convenient for quality control,Is a constant term in a regression equation, is a reference level of a predicted value, reflects a basic quality index without other process parameters, is obtained through a regression analysis process, is generally determined based on multiple experiments or actual production data depending on multiple batches of previously collected data, for example, through 10 batches of production data, is obtained as a basic predicted value under the condition that all other parameter standardized values are 0,Is a regression coefficient for measuring the influence intensity of each process parameter on the quality index, each regression coefficient is obtained based on the fitting of the data collected in the past on each process parameter and quality index, the weights of each parameter are reflected, and the process of determining the coefficients is generally realized by a partial least squares regression (PLS) method, for example, a plurality of batch data are used for analyzing the linear relation between the squeezing temperature and the acid value, thereby obtainingOther regression coefficients are calculated in a similar manner,The mapping values of the standardized technological parameters correspond to the squeezing temperature, the squeezing pressure, the squeezing time and the stirring speed respectively, and the mapping values are obtained through standardized processing and correlation analysis according to the actually collected data.
For example, if the mapping process yields the following normalized mapping values: (press temperature map value),(Press pressure map value),(Press time map value),(Stirring speed map value), regression coefficient was assumed to be、、、、The formula is introduced:
the results show that the predicted acid number under the current process conditions is 3.5065.
Referring to fig. 5, the obtaining steps of the deviation evaluation result specifically include:
comparing the predicted value of the oil quality index under the current production condition with an expected quality standard based on the oil quality index prediction result, and analyzing the deviation among the quality indexes including the acid value, the peroxide value and the purity to obtain a deviation value of each index;
under the current production condition, calculating the predicted value of the oil quality index through a regression equationWhich is compared to expected quality standards to evaluate the effectiveness of the current process settings. Assuming that the quality standard of the expected acid value is 3.5, the standard value is a standard determined according to the data collected in the past or the industry requirements and is used for ensuring the quality consistency and the safety of the product. Will predict the valueComparing with the target value 3.5, calculating the deviation value as. The deviation value is 0.0065, which indicates that the production parameter under the current process is close to the target value and within a reasonable range from the standard deviation. To further verify the rationality of the process settings, predictions of other quality metrics may be referenced. For example, if the predicted peroxide value is 1.02 and the expected standard is 1.0, the calculation is made by a similar deviationThe deviation of the peroxide value was found to be 0.02. Similarly, assuming that the predicted value of purity is 99.8% and the target standard is 99.9%, the deviation of purity is. By means of the comparison, the deviation degree of the technological parameters on each quality index can be evaluated item by item, and therefore the overall quality performance under the current production conditions can be known. The calculation result of the deviation value provides a quantization basis for subsequent deviation evaluation.
Based on the deviation value of each index, comparing the deviation value with a specified standard range, judging whether the process parameters need to be adjusted, analyzing the direction needing to be optimized, and generating a deviation evaluation result.
And analyzing the deviation of each quality index based on the calculated deviation result to obtain a final deviation evaluation result. The deviation evaluation process is to compare the deviation value of each index with a specified tolerance range and judge whether the current process needs to be adjusted. For example, assuming that the allowable deviation range is + -0.01, for the acid value deviationThe deviation value is smaller than 0.01, which indicates that the predicted value of the acid value is close to the standard value, and adjustment is not needed. Similarly, a deviation of the peroxide value of 0.02 out of the allowable range of 0.01 means that the deviation of the predicted value from the target value of the index is large, and it is necessary to further adjust the relevant process parameters such as lowering the press temperature or adjusting the stirring speed to improve the peroxide value. In addition, if the deviation of the purity is 0.1%, which is also out of the allowable range, it is indicated in the evaluation result that it is necessary to optimize the process parameters such as extending the press time or controlling the stirring speed to increase the purity of the product. By analyzing the deviation item by item, the specific influence of each technological parameter on the quality index can be identified, and the direction required to be optimized is obtained. The deviation evaluation result provides an adjustment basis for the production process, and ensures that the oil quality is stable and meets the set quality standard. The final evaluation process defines the priority and refinement of process adjustments, helping to continuously optimize production conditions to meet quality control requirements.
Referring to fig. 6, the steps for obtaining the smoothing parameter set value and the stability parameter set value specifically include:
Based on the peanut oil production parameter values acquired in real time, comparing the current value of the parameter with a preset threshold range one by one, and judging whether the parameter exceeds a maximum or minimum allowable value or not to obtain an out-of-range parameter list;
If the peanut oil produced at present is in the squeezing process, collecting real-time technological parameters including a squeezing temperature of 145 ℃ at the current value (the preset threshold range is 120-140 ℃) and a squeezing pressure of 85MPa at the current value (the preset threshold range is 80-90 MPa) for a squeezing time of 35 minutes (the preset threshold range is 30-40 minutes) and a stirring speed of 75rpm at the current value (the preset threshold range is 50-80 rpm), judging whether each parameter is in an allowable range or not by comparing each real-time collected parameter value with the preset threshold range one by one, wherein the squeezing temperature is 145 ℃ and exceeds the preset upper limit of 140 ℃, so that the parameter exceeds the threshold range and needs to be smoothed. For a press pressure of 85MPa at the present value, which is in the threshold range (80-90 MPa), this indicates that the parameter is in the normal range and no further treatment is necessary. For a press time of 35 minutes at the present value, again in the range of 30-40 minutes, no adjustment is necessary. For stirring speeds, the current value is 75rpm, which is also in the threshold range of 50-80rpm, no further treatment is required. By this procedure it is determined which parameters are within the allowed range and the out-of-range parameters (i.e. press temperature) that require smoothing.
Based on the list of out-of-range parameters, the formula is adopted:
Calculating smoothed process parameter valuesObtaining a smooth parameter set value;
Wherein, theIs the result of smoothing the original parameter values, which is used to replace the parameter values of the initial deviation threshold, to ensure that the parameter values return to within the allowed range,Is the current process parameter value acquired in real time, is acquired in real time through a sensor,Is a smoothing factor, and the magnitude of the smoothing force is controlled, and is usually obtained through analysis of data collected in the past, for example, if deviation exceeding a threshold value occurs many times in the production process, the analysis finds that the smoothing factor of 0.5 can effectively adjust the exceeding value to be within an allowable range, and the smoothing factor is set by taking 0.5 as a set value, and is generally set according to the fluctuation stability in the data collected in the past,The number of data points collected in the past, representing the number of data collected in the past for the smooth calculation, can be selected by the system settings to an appropriate number of data collected in the past to ensure that the smooth calculation meets the current production situation,Is the first data set collected in the pastThe process parameter values represent the corresponding parameter values collected in the batch collected in the past.
For example, if the pressing temperature is collected in real timeIs 145 ℃ and is out of the threshold range, so that smooth adjustment is needed. Taking a smoothing factorAnd using the temperature values collected in the past five times (140 ℃, 138 ℃, 136 ℃, 135 ℃ and 137 ℃) as the temperature valuesCarrying out formula calculation:
calculating the sum of differences of the previously collected data:
Averaging the differences:
Calculating a smoothed value:
The result showed that the temperature value obtained after the smoothing treatment was 141.1 ℃ and was adjusted back to the threshold range compared to 145 ℃ exceeding the threshold.
Based on the parameters conforming to the threshold range, analyzing the deviation condition of the parameters according to the deviation evaluation result and judging the stability of the parameters, and if the deviation of the parameters is in the allowable range, directly taking the current value of the parameters as a stable set value to obtain a stable parameter set value;
For other parameters (press pressure, press time, and stirring speed) that meet the threshold range, smoothing is not required, and the set value is further optimized in conjunction with the deviation evaluation result. For example, for a press pressure, the deviation evaluation shows a deviation of the pressure of less than 0.01, indicating that the parameter matches the quality standard. The 85MPa can be directly set as a stable production set point. For the press time, the deviation evaluation showed that the fluctuation of the acid value of the current press time was small, and the acid value was within the standard range. Thus, the current 35 minutes can be used as a stable set point for the press time. For the stirring speed, the deviation evaluation result showed that the deviation was 0.02, which was within the allowable range despite slight fluctuation, so that the stirring speed of 75rpm was suitable as a stable production set point. Through the process, stable process parameter setting is obtained, wherein the squeezing temperature is adjusted to 141.1 ℃ after smoothing treatment, and the squeezing temperature accords with a threshold range. The results show that through real-time monitoring, smoothing and deviation evaluation, all parameters can be kept in a reasonable range so as to ensure the stability of the production process and the qualification of the oil quality.
Referring to fig. 7, the load balancing parameter obtaining steps specifically include:
Based on the current peanut oil production state, checking key production parameters acquired in real time, comparing the current value of the parameters with a preset threshold range, judging whether load balancing treatment is needed, and marking the load state if the parameters exceed the preset range to obtain a judging result of the load balancing requirement;
And (3) combining the current peanut oil production state, checking all key production parameters (such as pressing temperature, pressing pressure, pressing time and stirring speed) acquired in real time one by one, comparing the current value with a preset threshold range, and judging whether load state balance treatment needs to be triggered according to load state conditions. The specific judging flow is that if the current value of a certain parameter exceeds the upper limit of the preset threshold range, the current value is marked as an 'out-of-range', if all the parameters are in a normal range, the production is in a stable state without triggering load balancing, and if a certain production parameter (such as a squeezing temperature) exceeds the preset threshold range, the production state is judged to reach a load state, and the subsequent load balancing operation is required to be executed. For example, in one test, the collected press temperature is 150 ℃ (140 ℃ above the set upper limit), the press pressure is 85MPa (80-90 MPa in the preset range), the press time is 32 minutes (30-40 minutes in the preset range), and the stirring speed is 77rpm (50-80 rpm in the preset range), but the press pressure, time and stirring speed all meet the standard range, but the press temperature exceeds the preset upper limit, so that the production load is judged to reach the peak, and the load balancing process flow is required. Otherwise, if all the acquired parameters accord with the preset threshold range, the current production state is maintained, and load balancing operation is not needed.
According to the judging result of the load balancing requirement, adopting the formula:
calculating a balanced load adjustment valueGenerating a load balancing parameter;
Wherein, theFor production parametersThe target value after balanced calculation in the load state is used for guiding the actual adjustment of the parameter, ensuring that the parameter approaches to the reference value,Is the current production parameter collectedRepresenting the real-time data of the currently measured production parameter (such as pressing temperature, pressing pressure, pressing time or stirring speed) in a load state, acquired by a sensor or monitoring equipment in real time,Is a production parameterThe weight coefficient of the parameter is generally set by analyzing the production data collected in the past, if the influence of a certain parameter on the running load of the equipment is large, the weight coefficient is set to be higher, so as to ensure that the parameter is obviously balanced and adjusted,Is a production parameterThe reference value of (a) reflecting the target value of the parameter in production, i.e. the set value in the ideal or standard load condition, is usually determined by means of conventionally collected data or equipment recommendation values, for example, if the conventionally collected data indicate that the press temperature is stabilized at 140 ℃, 140 ℃ can be set as the reference value of the parameter,Is a production parameterFor controlling the amplitude of the balance adjustment, the coefficient reflecting the parameter of the adjustment processAvoiding drastic adjustments of the parameters of larger deviations, the adjustment coefficients being generally set according to the fluctuation of the parameters, e.g. when the press temperature deviates more than usual, higher values may be setThe value is reduced to reduce the adjustment amplitude, and the unstable load condition possibly caused by rapid change is avoided.
For example, if the current load conditions are production parameters of 150℃press temperature, 88MPa press pressure, 32 minutes press time, 77rpm stirring speed. The reference values were set at a press temperature of 140 ℃, a press pressure of 85MPa, a press time of 35 minutes, and a stirring speed of 75rpm. The weight and the adjustment coefficient of each parameter are respectively as follows, the temperature weight is 0.4, the adjustment coefficient is 0.5, the pressure weight is 0.3, the adjustment coefficient is 0.3, the time weight is 0.2, the adjustment coefficient is 0.2, the stirring speed weight is 0.1, and the adjustment coefficient is 0.1. Carrying out calculation by using a formula:
load balancing value of temperature:
Load balancing value of pressure:
Load balance value of time:
load balancing value of stirring speed:
Calculated load balancing adjustment valueFor the target adjustment values of the respective production parameters, for example, the temperature was adjusted to 147.33 ℃, the pressure was adjusted to 87.31MPa, the time was adjusted to 32.5 minutes, and the stirring speed was adjusted to 76.82rpm. Through the balance adjustment, each production parameter gradually approaches to the reference value, so that fluctuation in a load state is reduced, the production system can be kept stable under the load state condition, and stable operation of equipment is ensured.
Referring to fig. 8, the overall parameter data processing result of peanut oil production control is specifically obtained by the following steps:
based on the smooth parameter set value or the stable parameter set value, evaluating the influence of each production parameter on the oil quality by combining with the predicted value of the oil quality index under the current production condition, and performing iterative optimization to obtain an optimized process parameter set value;
Firstly, the influence degree of each production parameter on the quality of oil products is evaluated. In the evaluation process, the sensitivity of fluctuation to quality indexes such as acid value, peroxide value and the like is inspected by gradually analyzing each parameter, and whether the influence is obvious is judged by deviation evaluation. Specifically, when the fluctuation of a certain parameter causes the variation range of the acid value or the peroxide value to exceed the allowable range (for example, when the variation of the acid value exceeds 0.1 or the variation of the peroxide value exceeds 0.5), the influence of the parameter on the quality of the oil product is considered to be remarkable, and when the variation of the certain parameter causes the improvement range of the acid value to be smaller than 0.05 or the improvement range of the peroxide value to be smaller than 0.2 and the quality index meets the standard requirement, the improvement effect of the parameter on the quality of the oil product is considered to be smaller, and the elimination or the reduction of the optimization priority can be considered. In the optimization process, the deviation between the predicted value and the actual result is combined for dynamic adjustment, and the difference between the actual acquired value of the parameter and the predicted value of the model in the production process is monitored in real time. For example, when the predicted acid value should be 3.50 at a press temperature of 140 ℃, but the actual production result shows that the acid value is 3.65, and when the deviation reaches 0.15, the control range (e.g., 135-145 ℃) needs to be further refined by dynamically adjusting the temperature optimization direction to reduce the deviation. Meanwhile, stability evaluation is performed on parameters with smaller deviation, for example, if the deviation of the actual stirring speed is within an allowable range (+ -2 rpm) and the change amplitude of the acid value or the peroxide value is insufficient to remarkably improve the oil quality, the current value can be directly set as a stable value, and further intervention on the parameters in the optimization process is reduced. The deviation between the predicted value and the actual result and the variation trend thereof are continuously analyzed, the optimization direction and the parameter combination are dynamically adjusted, the optimization of the production parameters is ensured to be capable of obviously improving the quality index, and finally a group of optimized technological parameter set values are determined, so that the stability of the oil quality and the high efficiency of technological control are realized.
According to the optimized technological parameter set value, comparing the suitability of the load balancing parameter and the technological parameter set value under the load condition, and carrying out adaptive adjustment to obtain a global parameter data processing result of peanut oil production control;
After the optimization and adjustment of each process parameter are completed, the optimized process parameter set value and the load balancing parameter are integrated according to the process requirements of the equipment under different load states. Firstly, comparing the load balancing parameter with the optimized technological parameter set value to evaluate the suitability of the load balancing parameter in the load state. This process essentially comprises the steps of defining the ideal settings for each parameter based on the smoothed and optimized process parameters (e.g. press temperature, press pressure, stirring speed, etc.). For example, under normal production conditions, the reference value of the pressing temperature is 125 ℃, the pressure is 85MPa, and the stirring speed is 75rpm. These reference values will serve as a control for the adaptation assessment under load conditions. In the production load state, real-time data of various parameters are acquired, for example, the current value of the temperature rises to 130 ℃, the pressure rises to 88MPa and the like. Based on these load status data, an equalization value for each parameter is calculated by a load equalization formula to measure the actual load level of each production parameter. And comparing the load balancing parameter with the set value of each process parameter, and checking whether each parameter is within the allowable deviation range. For example, if the equilibrium value of the pressing temperature is 128 ℃, which differs from the set value of 125 ℃ by 3 ℃ and is within the allowable deviation range of the equipment (+ -5 ℃) the temperature parameter is considered to be well adapted in the load state, and if the equilibrium value of the pressing pressure is 90MPa, which exceeds the allowable upper limit, further adjustment of the set value or addition of depressurization measures in the equipment is required. And generating an adaptability evaluation report by comparing the deviation of each process parameter and the load balancing parameter so as to reflect the overall adaptation condition under the load state. If a certain production parameter deviates too much from the allowable range, it is recorded as a mismatch and marked that the parameter needs further optimization. And for the parameters which are not adapted, further adjusting the set values of the parameters, and incorporating the new adjusted set values into the global control scheme. For example, the press pressure is adjusted down to 87MPa in accordance with the load condition, the temperature is kept at 128 ℃.
The present invention is not limited to the above embodiments, and any equivalent embodiments which can be changed or modified by the technical disclosure described above can be applied to other fields, but any simple modification, equivalent changes and modification made to the above embodiments according to the technical matter of the present invention will still fall within the scope of the technical disclosure.