A product temperature control method and system based on data analysis

Abstract

The present invention discloses a product temperature control method and system based on data analysis, which relates to the technical field of temperature control in rice production. The product temperature control method based on data analysis divides the rice in a drying bin into several layers of drying depth, and randomly selects several measurement points for each layer of drying depth; obtains the rice drying status data at each measurement point at each layer of drying depth in the drying bin in real time, and performs a comprehensive analysis to obtain a rice drying temperature correction value in the drying bin; and performs a judgment analysis with a preset rice drying temperature threshold; and takes temperature control measures based on the analysis results. The present invention can dynamically obtain a more spatially representative rice drying temperature correction value through stratified sampling and comprehensive analysis of status data, thereby providing a more accurate basis for subsequent adjustment, improving overall drying uniformity, reducing quality fluctuations during the drying process, and significantly improving the technical shortcomings of existing temperature control strategies.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature control in rice production, and in particular to a product temperature control method and system based on data analysis. Background Art

[0002] As one of the main grain varieties, the post-harvest drying of rice is of great significance for ensuring storage safety and stable quality. In modern rice processing and production, hot air drying equipment is generally used to dehumidify rice. Temperature control is the core link that affects drying efficiency, energy consumption level and finished product quality. At present, temperature control in the drying process mostly relies on a single point or a small number of measuring points to obtain temperature data in the warehouse, and combines empirical rules or fixed thresholds to perform heating, ventilation and other operations. The control method is relatively extensive. Since the heat and humidity distribution in the drying warehouse is affected by factors such as layer position, airflow organization, and material stacking status, uneven temperatures often occur at different depths and regions. Traditional control methods are difficult to accurately reflect the overall drying status, resulting in frequent problems of insufficient or excessive drying in some areas.

[0003] In addition, existing temperature control strategies generally lack analysis and feedback mechanisms for real-time multi-point data, making it difficult to dynamically adjust control parameters according to different drying stages, affecting the intelligence level of the drying process and the consistency of product quality. Therefore, a new temperature control method is needed that can integrate real-time data analysis, layered perception and intelligent adjustment to serve rice drying production more efficiently and accurately.

[0004] Prior art, such as the invention patent application with announcement number CN110334971A, discloses a rice quality detection method based on big data analysis, comprising: first, selecting test rice samples of at least two rice qualities, and collecting first evaluation data of the test rice samples of rice quality respectively; then, solving the first quality identification parameter corresponding to the test rice samples of each rice quality; then, collecting the second evaluation data of the rice sample to be detected; then, solving the second quality identification parameter corresponding to the rice sample to be detected; finally, comparing the second quality identification parameter with the first quality identification parameter to obtain a comparison value. The present invention uses the least squares method to identify system parameters, without the need to know the physical meaning of the system parameters themselves, and only needs to solve and compare with the first quality identification parameters under the test rice samples of various rice qualities; by combining multiple evaluation data, the objectivity of the detection result is strong, and the method is simple and effectively improves the efficiency of rice quality detection.

[0005] Based on the above scheme, it is found that the limitations of the existing technology include at least the following problems. First, traditional rice drying temperature control technology generally uses single point measurement or overall average temperature as the control basis, and lacks detailed characterization of the temperature status at different depths and positions in the drying bin. As a result, the drying control has obvious surface response characteristics, which makes it difficult to accurately reflect the true drying status of the rice as a whole in the bin. During the actual drying process, the rice often shows obvious stratified temperature differences in the vertical direction due to the influence of hot air flow distribution, moisture migration, etc. If it only relies on surface or local temperature for control, it is very easy for some areas to be over-dried or under-dried, which in turn affects the drying uniformity and quality of the finished product, and even causes energy waste or quality control failure. Summary of the Invention

[0006] In response to the shortcomings of the existing technology, the present invention provides a product temperature control method and system based on data analysis, which solves the problem in the existing technology of lack of fine perception and dynamic correction of the spatial distribution differences of temperature in the drying chamber, resulting in inaccurate temperature control and uneven drying.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a product temperature control method based on data analysis, comprising the following steps: dividing rice in a drying bin into several layers of drying depth, and randomly selecting several measurement positions for each drying depth; acquiring rice drying status data at each measurement position at each drying depth in the drying bin in real time, and performing comprehensive analysis to obtain a correction value for the rice drying temperature in the drying bin; judging and analyzing the correction value for the rice drying temperature in the drying bin and a preset rice drying temperature threshold; if the correction value for the rice drying temperature in the drying bin is lower than the preset rice drying temperature threshold, taking a preset temperature increase control measure for the rice in the drying bin; if the correction value for the rice drying temperature in the drying bin is higher than the preset rice drying temperature threshold, taking a preset temperature decrease control measure for the rice in the drying bin.

[0008] Furthermore, the rice drying state data includes rice drying temperature values ​​and rice drying humidity values ​​at several time points. The specific steps of obtaining the rice drying temperature correction value in the drying bin are as follows: based on the rice drying state data at each measurement position point at each drying depth in the drying bin, respectively analyzing the rice drying state feature set in the drying bin, including the rice drying temperature comprehensive index and the rice drying humidity comprehensive index; and performing a comprehensive analysis on the rice drying state feature set in the drying bin to obtain the rice drying temperature correction value in the drying bin.

[0009] Furthermore, the specific steps of analyzing the rice drying state feature set in the drying bin are as follows: reading the rice drying temperature value and the rice drying humidity value at each measurement position point at each drying depth in the drying bin, and performing comprehensive analysis on them respectively to obtain the rice drying temperature measurement mean and the rice drying humidity measurement mean at each drying depth in the drying bin; performing comprehensive analysis on the rice drying temperature measurement mean and the rice drying humidity measurement mean at each drying depth in the drying bin respectively to obtain the rice drying temperature comprehensive index and the rice drying humidity comprehensive index in the drying bin.

[0010] Furthermore, the specific formula for calculating the correction value of the rice drying temperature in the drying bin is as follows: ;in, is the correction value of rice drying temperature in the drying bin, is the comprehensive index of rice drying temperature in the drying bin, It is the comprehensive index of rice drying humidity in the drying bin. is the drying and humidity influence coefficient stored in the database, is the temperature-humidity interaction coefficient stored in the database, It is the drying humidity correction factor stored in the database.

[0011] Furthermore, the specific steps of taking preset temperature control measures for the rice in the drying bin are as follows: performing difference analysis on the rice drying temperature correction value in the drying bin and the preset rice drying temperature threshold value to obtain the rice drying temperature rise difference in the drying bin; obtaining current drying state data and drying state parameter data in the drying bin, the current drying state data including the current drying airflow velocity value and the drying airflow velocity parameter value, and the drying state parameter data including the current drying radiation intensity value and the drying radiation intensity parameter value; inputting the rice drying temperature rise difference in the drying bin, the current drying state data and the drying state parameter data into a preset temperature control model for comprehensive analysis to obtain the rice temperature rise control index in the drying bin; and taking a preset temperature control treatment on the rice in the drying bin based on the rice temperature rise control index in the drying bin.

[0012] Furthermore, the temperature rise regulation model is specifically as follows: ;in, is the temperature adjustment index of rice in the drying bin. is the temperature rise difference of rice drying temperature in the drying bin, is the logarithmic correction coefficient of temperature difference rise stored in the database, is the temperature difference warming weight correction coefficient stored in the database, is the comprehensive adjustment coefficient of temperature difference and heating stored in the database, is the first temperature difference rising threshold in the database, is the temperature difference heating power correction coefficient stored in the database, is the current drying air flow velocity value in the drying chamber, is the parameter value of the drying air flow velocity in the drying chamber, is the correction coefficient of the airflow difference heating index stored in the database, is the airflow difference temperature rise influence coefficient stored in the database, is the airflow difference temperature rise adjustment coefficient stored in the database, is the second temperature difference threshold in the database, is the airflow difference temperature rise correction coefficient stored in the database, is the temperature difference radiation heating influence coefficient stored in the database, is the current drying radiation intensity value in the drying chamber, is the parameter value of the drying radiation intensity in the drying chamber, is the radiation heating adjustment coefficient stored in the database, It is the temperature rise interaction adjustment coefficient stored in the database.

[0013] Furthermore, the specific steps of taking a preset temperature control treatment on the rice in the drying bin based on the rice temperature control index in the drying bin are as follows: the rice temperature control index in the drying bin is judged and analyzed with a plurality of preset temperature control intervals, and each temperature control interval corresponds to a preset temperature control measure; based on the temperature control measure corresponding to the preset temperature control interval in which the rice temperature control index is, the rice in the drying bin is temperature controlled.

[0014] Furthermore, the specific steps of taking preset cooling control measures for the rice in the drying bin are as follows: performing difference analysis on the rice drying temperature correction value in the drying bin and a preset rice drying temperature threshold value to obtain the rice drying temperature cooling difference in the drying bin; reading the current drying state data and drying state parameter data in the drying bin, and inputting them together with the rice drying temperature cooling difference in the drying bin into a preset cooling control model for comprehensive analysis to obtain a rice cooling control index in the drying bin; and taking a preset cooling control treatment on the rice in the drying bin based on the rice cooling control index in the drying bin.

[0015] Furthermore, the specific steps of taking a preset cooling control treatment on the rice in the drying bin based on the rice cooling control index in the drying bin are as follows: judging and analyzing the rice cooling control index in the drying bin and several preset cooling control intervals, and each cooling control interval corresponds to a preset cooling control measure; based on the cooling control measure corresponding to the preset cooling control interval in which the rice cooling control index is, cooling control is performed on the rice in the drying bin.

[0016] A product temperature control system based on data analysis comprises: a division unit for dividing rice in a drying bin into a plurality of drying depth layers and randomly selecting a plurality of measurement positions for each drying depth layer; a real-time acquisition unit for acquiring rice drying state data at each measurement position at each drying depth layer in the drying bin in real time, and performing comprehensive analysis to obtain a correction value of the rice drying temperature in the drying bin; a judgment unit for performing judgment and analysis between the correction value of the rice drying temperature in the drying bin and a preset rice drying temperature threshold; a temperature increase control unit for taking a preset temperature increase control measure for the rice in the drying bin if the correction value of the rice drying temperature in the drying bin is lower than a preset rice drying temperature threshold; and a temperature decrease control unit for taking a preset temperature decrease control measure for the rice in the drying bin if the correction value of the rice drying temperature in the drying bin is higher than the preset rice drying temperature threshold.

[0017] The present invention has the following beneficial effects:

[0018] (1) This product temperature control method based on data analysis divides the rice in the drying bin into multiple drying depth layers and randomly selects multiple measurement points in each layer to obtain the temperature and humidity data of each layer in real time, effectively avoiding the problem of insufficient representativeness caused by relying only on single-point or surface measurement in traditional drying temperature control. During the drying process, due to multiple factors such as hot air distribution, ventilation structure, and material density, the rice in the bin often has inconsistent drying degrees in different layers. If the average or fixed point temperature is used as the control basis, it is often difficult to reflect the local temperature control deviation, resulting in overdrying of some areas and local moisture residue, which in turn affects the drying efficiency and product quality. Through stratified sampling and comprehensive analysis of state data, a more spatially representative rice drying temperature correction value can be dynamically obtained, thereby providing a more accurate basis for subsequent adjustments, improving the overall drying uniformity, reducing quality fluctuations during the drying process, and significantly improving the technical shortcomings of existing temperature control strategies.

[0019] (2) The product temperature control method based on data analysis, through the fusion analysis of the temperature and humidity data of each layer of rice measuring point, constructs a drying state feature set including the temperature comprehensive index and the humidity comprehensive index, and on this basis, introduces the drying humidity influence coefficient, temperature and humidity interaction influence coefficient, and drying humidity correction coefficient stored in the database to correct the original temperature parameters and obtain a temperature correction value that is more in line with the actual drying state of the material. This correction mechanism effectively makes up for the defects of the traditional temperature control system that ignores humidity changes or cannot reflect the wet-wet linkage behavior. Especially in the late stage of drying, when the temperature tends to be stable and the humidity changes are still significant, relying solely on temperature judgment will result in control errors. The dynamic temperature correction mechanism in this method can not only reflect the heat and humidity coupling effect in the drying process in real time, but also make the temperature parameters closer to the actual drying physical situation through the support of the empirical coefficients in the database, thereby achieving intelligent temperature control with higher resolution and stronger perception ability, and improving the sensitivity and accuracy of the system.

[0020] (3) The product temperature control method based on data analysis constructs a regulation model containing multiple factors such as temperature difference, airflow difference, and radiation difference in the heating and cooling control strategies respectively. The heating control index or the cooling control index is obtained through comprehensive calculation, and the corresponding heating or cooling control strategy is further matched based on the segmented interval where the index is located. Different from the simple rule judgment or fixed value adjustment method used in the existing technology, this method integrates the current difference state and the control variable parameter value through the control index, and realizes accurate modeling with the help of a variety of correction and adjustment coefficients stored in the database. It can not only determine the adjustment intensity according to the size of the difference, but also dynamically control the combination and amplitude of the adjustment means, thereby effectively avoiding the problem of overshoot or under-adjustment. This control system has good scalability and flexible adjustment capabilities, and is particularly suitable for refined control in complex drying scenarios such as severe temperature fluctuations, uneven material loads, and frequent airflow disturbances.

[0021] (4) The product temperature control system based on data analysis clarifies the structural composition of the division unit, real-time acquisition unit, judgment unit, temperature rise control unit and temperature fall control unit through functional unit division, and realizes the complete process encapsulation from data acquisition, state analysis, judgment decision-making to control execution, forming a highly modular intelligent temperature control architecture. Compared with the existing problems of high coupling between temperature control logic and hardware structure, complex deployment and difficult maintenance in the existing technology, the system can be flexibly adapted to different drying equipment and different control platforms through functional partitioning design, and has good software and hardware decoupling and engineering expansion capabilities. At the same time, the modular structure facilitates the independent upgrade or algorithm replacement of each functional unit in the later stage. For example, the data acquisition strategy of the real-time acquisition unit can be independently optimized, or the judgment algorithm in the judgment unit can be replaced without affecting the operation of other modules, which significantly improves the maintainability, scalability and industrial application deployment efficiency of the system.

[0022] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of a product temperature control method based on data analysis of the present invention.

[0024] Figure 2 The present invention is a line graph of rice drying temperature at seven measurement points at three drying depths in a drying bin based on data analysis.

[0025] Figure 3 The present invention is a rice drying humidity line graph at seven measurement points at three drying depths in a drying bin based on data analysis.

[0026] Figure 4 This is a flowchart of the specific steps of taking preset temperature control measures for rice in a drying bin in a product temperature control method based on data analysis of the present invention.

[0027] Figure 5 This is a block diagram of a product temperature control system based on data analysis in the present invention. DETAILED DESCRIPTION

[0028] See also Figure 1 An embodiment of the present invention provides a technical solution: a product temperature control method based on data analysis, comprising the following steps: dividing rice in a drying bin into a plurality of drying depths, and randomly selecting a plurality of measurement points for each drying depth; acquiring rice drying status data at each measurement point at each drying depth in the drying bin in real time, and performing a comprehensive analysis to obtain a correction value of the rice drying temperature in the drying bin; performing a judgment and analysis between the correction value of the rice drying temperature in the drying bin and a preset rice drying temperature threshold; if the correction value of the rice drying temperature in the drying bin is lower than the preset rice drying temperature threshold, taking a preset temperature increase control measure for the rice in the drying bin; if the correction value of the rice drying temperature in the drying bin is higher than the preset rice drying temperature threshold, taking a preset temperature decrease control measure for the rice in the drying bin.

[0029] Specifically, the rice drying state data includes rice drying temperature values ​​and rice drying humidity values ​​at several time points. The specific steps for obtaining the rice drying temperature correction value in the drying bin are as follows: based on the rice drying state data at each measurement position point at each drying depth in the drying bin, respectively analyzing the rice drying state feature set in the drying bin, including the rice drying temperature comprehensive index and the rice drying humidity comprehensive index; and performing a comprehensive analysis on the rice drying state feature set in the drying bin to obtain the rice drying temperature correction value in the drying bin.

[0030] Among them, the rice drying temperature value can be measured and obtained by multi-point thermocouple or infrared sensor.

[0031] The humidity value of rice drying can be obtained by measuring with a capacitive humidity sensor or a near-infrared moisture meter.

[0032] The specific steps of analyzing the rice drying state feature set in the drying bin are as follows: reading the rice drying temperature value and the rice drying humidity value at each measurement position point at each drying depth in the drying bin, and performing comprehensive analysis on them respectively (i.e., performing mean analysis on several measurement positions), and obtaining the mean rice drying temperature measurement value and the mean rice drying humidity measurement value at each drying depth in the drying bin; performing comprehensive analysis on the mean rice drying temperature measurement value and the mean rice drying humidity measurement value at each drying depth in the drying bin respectively (i.e., performing mean analysis on several drying depths), and obtaining the comprehensive rice drying temperature index and the comprehensive rice drying humidity index in the drying bin.

[0033] The specific implementation example of calculating the comprehensive index of rice drying temperature and rice drying humidity in the drying bin is as follows. The existing parameters are as follows: the rice drying temperature value and rice drying humidity value at seven measurement points at three drying depths. The specific data are shown in Tables 1-3 and Figure 2-3 As shown:

[0034] Table 1 Example of rice drying temperature and humidity values ​​at seven measurement points at the first drying depth

[0035] Measurement location point 1 Measurement location point 2 Measurement location point 3 Measurement location point 4 Measurement location point 5 Measurement location point 6 Measurement location point 7 Rice drying temperature 45.820 45.277 46.454 46.163 46.409 46.342 45.897 Rice drying humidity value 0.190 0.206 0.204 0.205 0.205 0.191 0.197

[0036] Table 2 Example of rice drying temperature and humidity values ​​at seven measurement points at the second drying depth

[0037] Measurement location point 1 Measurement location point 2 Measurement location point 3 Measurement location point 4 Measurement location point 5 Measurement location point 6 Measurement location point 7 Rice drying temperature 44.133 44.294 44.068 44.488 44.583 44.407 45.243 Rice drying humidity value 0.223 0.219 0.215 0.211 0.215 0.215 0.221

[0038] Table 3 Example of rice drying temperature and humidity values ​​at seven measurement points at the third drying depth

[0039] Measurement location point 1 Measurement location point 2 Measurement location point 3 Measurement location point 4 Measurement location point 5 Measurement location point 6 Measurement location point 7 Rice drying temperature 43.421 43.814 43.211 44.203 43.112 44.480 44.158 Rice drying humidity value 0.233 0.227 0.222 0.231 0.231 0.228 0.232

[0040] Performing mean analysis on the data in Table 1-3, we obtain:

[0041] The comprehensive index of rice drying temperature in the drying bin is approximately: 44.820 (unit: ℃).

[0042] The comprehensive index of rice drying humidity in the drying chamber is approximately: 0.217 (unit: kg / kg, which is the unit of dry basis moisture content, converted based on moisture content).

[0043] The specific formula for calculating the correction value of rice drying temperature in the drying bin is as follows: ;in, is the correction value of rice drying temperature in the drying bin, is the comprehensive index of rice drying temperature in the drying bin, It is the comprehensive index of rice drying humidity in the drying bin. is the drying and humidity influence coefficient stored in the database, is the temperature-humidity interaction coefficient stored in the database, It is the drying humidity correction factor stored in the database.

[0044] It should be explained that the drying and humidity influence coefficients stored in the database , temperature and humidity interaction coefficient , Drying humidity correction factor The specific steps for obtaining are: first, extract the corresponding change data of temperature and humidity in different drying batches and classify them by time, batch or drying stage; then, use linear or nonlinear regression method to fit the slope of the effect of humidity change on temperature response intensity, and obtain Then, the coupling term of temperature and humidity is introduced, and the synergistic influence intensity of the interaction between the two is extracted through multivariate regression or partial least squares modeling. Finally, by performing error analysis on the measured drying temperature and the temperature predicted by the ideal model, the systematic deviation is reversely corrected and the drying humidity correction coefficient is deduced. , in order to improve the model fitting accuracy, the whole process can be completed through the database automatic analysis script, or it can be optimized with manual participation combined with experimental data.

[0045] The specific implementation of calculating the correction value of the rice drying temperature in the drying bin is as follows, with the following parameters:

[0046] The comprehensive index of rice drying temperature in the drying bin is approximately: 44.820 (unit: ℃).

[0047] The comprehensive index of rice drying humidity in the drying chamber is approximately: 0.217 (unit: kg / kg, which is the unit of dry basis moisture content, converted based on moisture content).

[0048] The dryness and humidity influence coefficient stored in the database is approximately: 1.245.

[0049] The temperature-humidity interaction coefficient stored in the database is approximately 0.030.

[0050] The dryness and humidity correction factor stored in the database is approximately: 0.896.

[0051] Substituting the above data into the specific formula for the correction value of the rice drying temperature in the drying bin, we obtain:

[0052] Corrected value of rice drying temperature in the drying bin = 44.820×(1+(0.896×((ln(1+(0.217^1.245))) / (1+0.030×44.820))))≈47.009℃

[0053] In this embodiment, by constructing a temperature and humidity data collection and analysis mechanism based on multiple layers of depth, multiple measuring points, and multiple time points, a high-dimensional, full-coverage perception of the drying state of rice in the drying bin is achieved, and a multi-level indicator system of drying temperature comprehensive index, drying humidity comprehensive index and temperature correction value is introduced, so that the temperature control decision no longer depends on a single measuring point or static average value, but is based on dynamic, multi-source fusion data results, thereby more comprehensively reflecting the current true drying state of rice. In addition, the calculation of the temperature correction value introduces the drying humidity influence coefficient, temperature and humidity interaction influence coefficient and drying humidity correction coefficient derived from historical drying data training, and realizes parameter adaptive optimization through regression modeling, error inversion and other methods, so that the correction result has the unity of model logic and real physics. This structure not only effectively improves the accuracy and robustness of temperature control judgment, but also has a high degree of automated processing capability, can widely adapt to different drying bin environments and raw material conditions, and significantly improves the intelligence level of the drying process and product quality stability.

[0054] Specifically, if Figure 4 As shown, the specific steps of taking a preset temperature increase control measure for the rice in the drying bin are as follows: performing a difference analysis between a rice drying temperature correction value in the drying bin and a preset rice drying temperature threshold value (i.e., subtracting the rice drying temperature correction value from the preset rice drying temperature threshold value) to obtain a temperature increase difference of the rice drying temperature in the drying bin; obtaining current drying state data and drying state parameter data in the drying bin, wherein the current drying state data includes a current drying airflow velocity value and a drying airflow velocity parameter value, and the drying state parameter data includes a current drying radiation intensity value and a drying radiation intensity parameter value; inputting the rice drying temperature increase difference, the current drying state data, and the drying state parameter data in the drying bin into a preset temperature increase control model for comprehensive analysis to obtain a rice temperature increase control index in the drying bin; and taking a preset temperature increase control treatment on the rice in the drying bin based on the rice temperature increase control index in the drying bin.

[0055] The specific temperature regulation model is as follows: ;

[0056] in, is the temperature adjustment index of rice in the drying bin. is the temperature rise difference of rice drying temperature in the drying bin, is the logarithmic correction coefficient of temperature difference rise stored in the database, is the temperature difference warming weight correction coefficient stored in the database, is the comprehensive adjustment coefficient of temperature difference and heating stored in the database, is the first temperature difference rising threshold in the database, is the temperature difference heating power correction coefficient stored in the database, is the current drying air flow velocity value in the drying chamber, is the parameter value of the drying air flow velocity in the drying chamber, is the correction coefficient of the airflow difference heating index stored in the database, is the airflow difference temperature rise influence coefficient stored in the database, is the airflow difference temperature rise adjustment coefficient stored in the database, is the second temperature difference threshold in the database, is the airflow difference temperature rise correction coefficient stored in the database, is the temperature difference radiation heating influence coefficient stored in the database, is the current drying radiation intensity value in the drying chamber, is the parameter value of the drying radiation intensity in the drying chamber, is the radiation heating adjustment coefficient stored in the database, It is the temperature rise interaction adjustment coefficient stored in the database (controlling the influence of temperature, airflow and radiation on the temperature rise adjustment amount).

[0057] It should be explained that the temperature difference logarithmic correction coefficient stored in the database is , Temperature difference warming weight correction coefficient , Temperature difference heating comprehensive adjustment coefficient The specific steps of obtaining are: by performing segmented regression modeling on the heating efficiency data under different temperature difference intervals in historical drying batches, the fitting factors of the logarithmic response curve are extracted respectively (obtaining ), temperature difference amplification factor (derived ), and combined with the principle of minimum residual square between temperature difference and actual adjustment response, the overall temperature rise response degree after inversion fitting correction is used as .

[0058] Temperature difference heating power correction coefficient stored in the database , airflow difference temperature rise index correction coefficient , Airflow difference temperature rise influence coefficient , airflow difference temperature rise adjustment coefficient The specific steps of obtaining are: by extracting the data of the system heating behavior under different combinations of temperature difference and airflow difference, constructing a power function fitting model dominated by temperature difference to obtain , and then perform exponential regression extraction based on the changing trend of air flow velocity difference and temperature control response , calculate the modulation intensity of the airflow difference on the temperature rise slope change and get Finally, the overall adjustment capacity coefficient is fitted based on the deviation between the adjustment result of the heating rate by the air flow change and the theoretical value. .

[0059] Airflow difference temperature rise correction coefficient stored in the database , Temperature difference radiation heating influence coefficient , radiation heating adjustment coefficient , Temperature rise interaction adjustment coefficient The specific steps of obtaining are: first, compare the difference model of a large number of airflow differences and temperature rise results, and extract the , and then fit the combined data of temperature difference and radiation intensity to get , characterizes its influence on the radiation response; then, the causal curve fitting is carried out by adjusting the historical radiation intensity change and the heating rate Finally, the coupled data of temperature, airflow and radiation were introduced to construct a multi-factor cross regression model to extract the three-factor regulation coupling strength as .

[0060] In this embodiment, by constructing a multi-parameter driven temperature regulation model, the temperature rise behavior in the rice drying process is refined and intelligently regulated, which has significant engineering application value. Unlike the traditional temperature control method that relies on empirical thresholds or linear adjustment, the model introduces three types of dynamic data: temperature difference, airflow difference, and radiation intensity difference when calculating the temperature rise regulation index, and combines the coefficients of the corresponding dynamic data extracted from the database to construct a nonlinear regulation function with response elasticity and regulation boundary perception capabilities. In particular, the temperature difference interval is segmented modeled in the model, and different response curves are set for different difference intervals, which effectively solves the problem of insufficient regulation of the traditional model under large differences and excessive regulation under small differences. At the same time, through the introduction of airflow and radiation differences and parameter coupling, the model has the ability of coordinated regulation, and can automatically allocate the regulation ratios of heating, ventilation, and irradiation according to different working conditions, thereby improving the heating efficiency and energy utilization rate. Overall, the temperature rise model not only improves the intelligent decision-making ability and adaptability of the temperature control system, but also significantly enhances the precision control and energy saving level of the drying process.

[0061] Specifically, the specific steps of taking a preset temperature control treatment on the rice in the drying bin based on the rice temperature control index in the drying bin are as follows: the rice temperature control index in the drying bin is judged and analyzed with a plurality of preset temperature control intervals, and each temperature control interval corresponds to a preset temperature control measure, for example, a temperature increase of 2°C; the rice in the drying bin is temperature-controlled based on the temperature control measure corresponding to the preset temperature control interval in which the rice temperature control index is located.

[0062] In this embodiment, by matching and judging the temperature rise control index with a plurality of preset temperature rise control intervals, and setting corresponding temperature rise control measures for each interval, a graded response and flexible adjustment of the temperature control strategy are achieved. Compared with the traditional one-size-fits-all fixed temperature rise strategy, this method can flexibly select different control means and amplitudes according to the strength of the actual temperature rise demand, such as temperature rise only, temperature rise + air flow, temperature rise + air flow + radiation and other combinations, thereby avoiding over-adjustment or response lag problems, improving control accuracy and response efficiency, and also helping to reduce energy consumption and ensure the uniformity and quality stability of the rice drying process.

[0063] Specifically, the specific steps of taking preset cooling control measures for the rice in the drying bin are as follows: performing difference analysis on the rice drying temperature correction value in the drying bin and the preset rice drying temperature threshold value (i.e., subtracting the preset rice drying temperature threshold value from the rice drying temperature correction value) to obtain the rice drying temperature cooling difference in the drying bin; reading current drying state data and drying state parameter data in the drying bin, and inputting the data and the rice drying temperature cooling difference in the drying bin into a preset cooling control model for comprehensive analysis to obtain a rice cooling control index in the drying bin; and taking a preset cooling control treatment on the rice in the drying bin based on the rice cooling control index in the drying bin.

[0064] The cooling regulation model is as follows: ; in, It is the temperature adjustment index of rice in the drying bin. is the temperature difference of rice drying in the drying bin. is the temperature difference cooling logarithmic correction coefficient stored in the database, is the temperature difference cooling weight correction coefficient stored in the database, is the temperature difference cooling comprehensive adjustment coefficient stored in the database, is the first temperature difference cooling threshold in the database, is the temperature difference cooling power correction coefficient stored in the database, is the current drying air flow velocity value in the drying chamber, is the parameter value of the drying air flow velocity in the drying chamber, is the airflow difference cooling index correction coefficient stored in the database, is the airflow difference cooling influence coefficient stored in the database, is the airflow difference cooling adjustment coefficient stored in the database, is the second temperature difference cooling threshold in the database, is the airflow difference cooling correction coefficient stored in the database, is the temperature difference radiation cooling influence coefficient stored in the database, is the current drying radiation intensity value in the drying chamber, is the parameter value of the drying radiation intensity in the drying chamber, is the radiation cooling adjustment coefficient stored in the database, It is the cooling interaction adjustment coefficient stored in the database (controlling the influence of temperature, airflow and radiation on the cooling adjustment amount).

[0065] It should be explained that the temperature difference cooling logarithmic correction coefficient stored in the database , Temperature difference cooling weight correction coefficient , comprehensive adjustment coefficient of temperature difference cooling The specific steps of obtaining θ are as follows: by statistically analyzing the natural cooling trend of the system when the temperature is higher than the set value in a large number of historical drying batches, the logarithmic fitting relationship between the temperature difference and the temperature adjustment rate is used to determine θ. , and perform weighted average analysis on the regulation response intensity in different temperature ranges to extract the correction factor Finally, the error between the measured actual temperature drop and the theoretical model fitting output is minimized, and the comprehensive regulation capability index is inverted. .

[0066] Temperature difference cooling power correction coefficient stored in the database , airflow difference cooling index correction coefficient , airflow difference cooling influence coefficient , airflow difference cooling adjustment coefficient The specific steps for obtaining the temperature difference are as follows: first, perform nonlinear curve fitting on the temperature difference-dominated cooling stage, extract the power sensitivity of temperature to cooling response, and obtain Then, the relationship between the airflow difference and the temperature drop rate is fitted into an exponential form, and its inhibition / enhancement trend is calculated to obtain Then, the average adjustment ratio of the airflow difference to the cooling slope per unit time is analyzed to obtain the influence intensity Finally, the hysteresis matching degree between dynamic airflow regulation and system temperature response is introduced to fit the airflow difference cooling regulation coefficient .

[0067] Airflow difference cooling correction factor stored in the database , Temperature difference radiation cooling influence coefficient , radiation cooling adjustment coefficient , cooling interaction adjustment coefficient The specific acquisition steps are: extract the direct adjustment response curve of air flow velocity change to cooling rate and perform linear correction fitting to obtain the basic correction coefficient Then, a binary regression model was established to extract the combined effects of temperature difference and radiation intensity in the cooling process. , obtained by performing nonlinear fitting on the regulation behavior of the temperature drop amplitude due to the change of radiation intensity Finally, a multi-factor coupling model was constructed by combining the temperature, airflow and radiation change data, and the interactive adjustment weight distribution was modeled to extract the cooling interactive adjustment coefficient. .

[0068] In this embodiment, by constructing a multi-factor driven cooling regulation model, precise cooling control is achieved in the overheating state during the rice drying process, which significantly improves the intelligence and adaptability of the temperature control system. Unlike the traditional method of simply adjusting the air volume or stopping the heat treatment based on temperature exceeding the limit, the present invention comprehensively considers three key variables: temperature difference, airflow difference and radiation difference when calculating the cooling regulation index, and cooperates with the corresponding coefficients of each variable extracted from the database to form a complex regulation model that highly fits the actual cooling behavior. In particular, in parameter acquisition, regression fitting, error inversion, multivariate coupling modeling and other technologies are used respectively, so that the model has stronger data drive and regulation logic, and can intelligently allocate control means and intensity for different cooling scenarios. The model also supports segmented response and multivariable collaborative regulation to ensure rapid response when the temperature exceeds the limit seriously, and flexible convergence when approaching the threshold, effectively avoiding overregulation or temperature control oscillation problems, significantly improving drying safety, process stability and energy utilization efficiency, and providing strong control support for high-quality, low-energy intelligent drying.

[0069] Specifically, the specific steps of taking a preset cooling control treatment on the rice in the drying bin based on the rice cooling control index in the drying bin are as follows: the rice cooling control index in the drying bin is judged and analyzed with a plurality of preset cooling control intervals, and each cooling control interval corresponds to a preset cooling control measure, for example, a temperature reduction of 2°C; based on the cooling control measure corresponding to the preset cooling control interval in which the rice cooling control index is, the rice in the drying bin is cooled and controlled.

[0070] In this implementation scheme, by matching and analyzing the cooling control index with multiple preset cooling control intervals, and setting corresponding cooling control measures for each interval, a graded response and intelligent selection of cooling strategies are achieved. Compared with traditional fixed cooling methods, this method can flexibly select different control combinations according to the degree of over-temperature, such as ventilation cooling only, enhanced airflow intensity, linked radiation cooling, etc., thereby avoiding the problem of one-size-fits-all over-processing. This mechanism not only improves the accuracy and response efficiency of temperature control, but also helps to ensure the stability and safety of the drying process, while reducing energy consumption and heat loss, and improving the overall drying quality control level.

[0071] See also Figure 5 An embodiment of the present invention provides a technical solution: a product temperature control system based on data analysis, comprising: a division unit, configured to divide rice in a drying bin into a plurality of drying depth layers, and randomly select a plurality of measurement positions for each drying depth layer; a real-time acquisition unit, configured to acquire rice drying state data at each measurement position at each drying depth layer in the drying bin in real time, and perform comprehensive analysis to obtain a correction value of the rice drying temperature in the drying bin; a judgment unit, configured to perform judgment and analysis between the correction value of the rice drying temperature in the drying bin and a preset rice drying temperature threshold; a temperature increase control unit, configured to take a preset temperature increase control measure for the rice in the drying bin if the correction value of the rice drying temperature in the drying bin is lower than the preset rice drying temperature threshold; and a temperature decrease control unit, configured to take a preset temperature decrease control measure for the rice in the drying bin if the correction value of the rice drying temperature in the drying bin is higher than the preset rice drying temperature threshold.

[0072] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0073] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A product temperature control method based on data analysis, characterized in that: The following steps are involved: The rice in the drying bin is divided into several drying depths, and for each drying depth, several measurement points are randomly selected; Real-time acquisition of rice drying state data at each measurement point at each drying depth in the drying bin, and comprehensive analysis to obtain a correction value of the rice drying temperature in the drying bin; The rice drying temperature correction value in the drying bin is compared with the preset rice drying temperature threshold value; If the rice drying temperature correction value in the drying bin is lower than the preset rice drying temperature threshold, a preset temperature increase control measure is taken for the rice in the drying bin; If the rice drying temperature correction value in the drying bin is higher than the preset rice drying temperature threshold, a preset temperature reduction control measure is taken for the rice in the drying bin; The specific steps for obtaining the correction value of the rice drying temperature in the drying bin are as follows: Based on the rice drying state data at each measurement position point at each drying depth in the drying bin, respectively analyze the rice drying state feature set in the drying bin, including the rice drying temperature comprehensive index and the rice drying humidity comprehensive index; Comprehensively analyze the rice drying state feature set in the drying bin to obtain the rice drying temperature correction value in the drying bin; The specific formula for calculating the correction value of rice drying temperature in the drying bin is as follows: ； in, is the correction value of rice drying temperature in the drying bin, is the comprehensive index of rice drying temperature in the drying bin, It is the comprehensive index of rice drying humidity in the drying bin. is the drying and humidity influence coefficient stored in the database, is the temperature-humidity interaction coefficient stored in the database, It is the drying humidity correction factor stored in the database.

2. The product temperature control method based on data analysis according to claim 1, characterized in that: The rice drying state data includes rice drying temperature values ​​and rice drying humidity values ​​at several time points.

3. The product temperature control method based on data analysis according to claim 2, characterized in that: The specific steps for analyzing the feature set of rice drying state in the drying bin are as follows: Read the rice drying temperature value and rice drying humidity value at each measurement position point at each drying depth in the drying bin, and perform comprehensive analysis to obtain the rice drying temperature measurement mean and rice drying humidity measurement mean at each drying depth in the drying bin; The average rice drying temperature measurement value and the average rice drying humidity measurement value at each drying depth in the drying bin were comprehensively analyzed to obtain the comprehensive index of rice drying temperature and comprehensive index of rice drying humidity in the drying bin.

4. The product temperature control method based on data analysis according to claim 1, characterized in that: The specific steps for taking preset temperature control measures for the rice in the drying bin are as follows: Performing a difference analysis on the rice drying temperature correction value in the drying bin and the preset rice drying temperature threshold value to obtain the rice drying temperature rise difference in the drying bin; Acquire current drying state data and drying state parameter data in the drying chamber, wherein the current drying state data includes a current drying airflow velocity value and a drying airflow velocity parameter value, and the drying state parameter data includes a current drying radiation intensity value and a drying radiation intensity parameter value; The rice drying temperature difference in the drying bin, the current drying state data and the drying state parameter data are respectively input into a preset temperature rise adjustment model for comprehensive analysis to obtain the rice temperature rise adjustment index in the drying bin; Based on the rice temperature control index in the drying bin, a preset temperature control process is adopted for the rice in the drying bin.

5. The product temperature control method based on data analysis according to claim 4, characterized in that: The temperature rise regulation model is as follows: ； in, is the temperature adjustment index of rice in the drying bin. is the temperature rise difference of rice drying temperature in the drying bin, is the logarithmic correction coefficient of temperature difference rise stored in the database, is the temperature difference warming weight correction coefficient stored in the database, is the comprehensive adjustment coefficient of temperature difference and heating stored in the database, is the first temperature difference rising threshold in the database, is the temperature difference heating power correction coefficient stored in the database, is the current drying air flow velocity value in the drying chamber, is the parameter value of the drying air flow velocity in the drying chamber, is the correction coefficient of the airflow difference heating index stored in the database, is the airflow difference temperature rise influence coefficient stored in the database, is the airflow difference temperature rise adjustment coefficient stored in the database, is the second temperature difference threshold in the database, is the airflow difference temperature rise correction coefficient stored in the database, is the temperature difference radiation heating influence coefficient stored in the database, is the current drying radiation intensity value in the drying chamber, is the parameter value of the drying radiation intensity in the drying chamber, is the radiation heating adjustment coefficient stored in the database, It is the temperature rise interaction adjustment coefficient stored in the database.

6. The product temperature control method based on data analysis according to claim 4, characterized in that: The specific steps of taking a preset temperature control process on the rice in the drying bin based on the rice temperature control index in the drying bin are as follows: The rice temperature control index in the drying bin is judged and analyzed with a plurality of preset temperature control intervals, and each temperature control interval corresponds to a preset temperature control measure; Based on the temperature control measures corresponding to the rice temperature control index being in the preset temperature control range, the temperature of the rice in the drying bin is controlled.

7. The product temperature control method based on data analysis according to claim 4, characterized in that: The specific steps for taking preset cooling control measures for the rice in the drying bin are as follows: Performing a difference analysis on the rice drying temperature correction value in the drying bin and the preset rice drying temperature threshold value to obtain the rice drying temperature drop difference in the drying bin; The current drying state data and the drying state parameter data in the drying bin are read, and the difference between the current drying state data and the rice drying temperature in the drying bin is input into a preset cooling adjustment model for comprehensive analysis to obtain the rice cooling adjustment index in the drying bin; Based on the rice cooling control index in the drying bin, a preset cooling control treatment is taken on the rice in the drying bin.

8. The product temperature control method based on data analysis according to claim 7, characterized in that: The specific steps of taking a preset temperature reduction control treatment on the rice in the drying bin based on the rice temperature reduction control index in the drying bin are as follows: The rice cooling control index in the drying bin is judged and analyzed with a plurality of preset cooling control intervals, and each cooling control interval corresponds to a preset cooling control measure; Based on the cooling control measures corresponding to the rice cooling control index being in the preset cooling control range, the rice in the drying bin is cooled and controlled.

9. A product temperature control system based on data analysis, applying the product temperature control method based on data analysis according to any one of claims 1 to 8, characterized in that: include: A division unit is used to divide the rice in the drying bin into a plurality of drying depths, and randomly select a plurality of measurement positions for each drying depth; A real-time acquisition unit is used to acquire the rice drying state data at each measurement position point at each drying depth in the drying bin in real time, and perform comprehensive analysis to obtain a correction value of the rice drying temperature in the drying bin; a judgment unit, configured to judge and analyze the rice drying temperature correction value in the drying bin and a preset rice drying temperature threshold; A temperature control unit is used to take preset temperature control measures on the rice in the drying bin when the correction value of the rice drying temperature in the drying bin is lower than a preset rice drying temperature threshold; The temperature reduction control unit is used to take preset temperature reduction control measures for the rice in the drying bin when the correction value of the rice drying temperature in the drying bin is higher than the preset rice drying temperature threshold.

Images