Material drying control method, system and equipment and storage medium

Abstract

The invention discloses a material drying control method, system and device and a storage medium, and the key points of the technical scheme are as follows: inputting material features into a trained drying prediction model to obtain predicted drying parameters and predicted material data; setting drying parameters of the target material according to the predicted drying parameters, and obtaining real-time material data and real-time drying parameters in the drying process of the target material; real-time drying parameters are adjusted in real time according to the real-time material data and the target material data; calculating a first prediction error of the real-time drying parameter and the predicted drying parameter, and calculating a second prediction error of the real-time material data and the predicted material data; and controlling the adjustment of the dryness prediction model according to the first prediction error, the second prediction error and the historical dryness data. According to the method, real-time feedback adjustment and predictive adjustment are combined, the materials are prevented from being too dry or wet, and meanwhile optimization suggestions and decision support of the drying process are provided for operators.

Description

Technical Field

[0001] The present invention belongs to the technical field of material drying, and in particular relates to a material drying control method, system, equipment and storage medium. Background Art

[0002] A dryer is a mechanical device that uses heat energy to reduce the moisture content of materials. It is mainly used to dry materials. By heating, the moisture in the material, generally referring to water or other volatile liquid components, is vaporized and escaped to obtain solid materials with a specified moisture content. The purpose of drying is to meet the needs of material use or further processing. The material drying control method aims to monitor and accurately control the material moisture content in the drying process in real time to improve drying efficiency and product quality.

[0003] However, the existing material drying control method of the dryer has the disadvantage of poor adaptability. When processing materials of different types or different particle sizes, the existing system may be difficult to adjust effectively, resulting in unsatisfactory control effect. Summary of the invention

[0004] The object of the present invention is to provide a material drying control method, system, device and storage medium, which combines real-time feedback adjustment and predictive adjustment to avoid excessive drying or moisture of materials, and at the same time provide operators with optimization suggestions and decision support for the drying process.

[0005] A first aspect of the present invention provides a material drying control method, comprising:

[0006] Inputting the material characteristics into a trained drying prediction model to obtain predicted drying parameters and predicted material data;

[0007] Dry the target material according to the predicted drying parameters, and obtain real-time material data and real-time drying parameters during the drying process of the target material;

[0008] Adjust the real-time drying parameters in real time according to the real-time material data and the target material data;

[0009] Calculating a first prediction error between the real-time drying parameter and the predicted drying parameter, and calculating a second prediction error between the real-time material data and the predicted material data;

[0010] Adjustment of the drying prediction model is controlled according to the first prediction error, the second prediction error and the historical drying data.

[0011] In some embodiments, the real-time material data includes: a plurality of sub-real-time data, the target material data includes: a plurality of sub-target data, and the real-time adjustment of the drying parameters according to the real-time material data and the target material data includes:

[0012] Presetting a first priority parameter, a second priority parameter and a third priority parameter among the drying parameters;

[0013] Calculating the deviation between each of the sub-real-time data and the sub-target data;

[0014] Deviations exceeding the first threshold among all deviations are recorded as valid deviations, and the first priority parameter, the second priority parameter and the third priority parameter are adjusted in sequence according to all valid deviations.

[0015] In some embodiments, the first priority parameter includes: drying medium temperature and drying medium flow rate, the second priority parameter includes: material residence time, the third priority parameter includes: feed amount, and the first priority parameter, the second priority parameter and the third priority parameter are adjusted in sequence according to all effective deviations, including:

[0016] Determine the adjustment sequence of drying medium temperature and drying medium flow rate according to all effective deviations;

[0017] The first adjustment amount is preset to adjust the drying parameter arranged first in the adjustment sequence;

[0018] When the effective deviation exceeds the second threshold, adjusting the drying parameter arranged later in the adjustment sequence according to a preset second adjustment amount;

[0019] When the effective deviation exceeds a third threshold, adjusting the material residence time according to a preset time adjustment amount;

[0020] When the effective deviation exceeds a third threshold value and the duration exceeds a time threshold value, the feed amount is adjusted according to a preset feed adjustment amount.

[0021] In some embodiments, controlling the adjustment of the drying prediction model according to the first prediction error, the second prediction error and the historical drying data includes:

[0022] When the first prediction error exceeds a first error threshold, selecting from the historical drying data the historical drying parameters corresponding to the historical material having the highest similarity to the target material characteristics;

[0023] adjusting the drying prediction model according to the historical drying parameters and the first prediction error;

[0024] When the second prediction error exceeds a second error threshold, selecting historical material data corresponding to the historical material having the highest similarity to the target material characteristics from the historical drying data;

[0025] The drying prediction model is adjusted according to the historical material data and the second prediction error.

[0026] In some embodiments, the training method of the drying prediction model includes:

[0027] Collect drying data of different types of materials during the drying process, mark the drying data, and distinguish the real drying data corresponding to different types of materials;

[0028] Dividing the drying data into a training set and a test set;

[0029] Using the training set to train the drying prediction model until a training termination condition is reached, thereby obtaining a trained drying prediction model;

[0030] The trained drying prediction model is tested using the test set, and when the test result meets the preset requirements, a trained drying prediction model is obtained.

[0031] In some embodiments, before inputting the material characteristics into the trained drying prediction model to obtain the predicted drying parameters and predicted material data, the method further includes:

[0032] Selecting a corresponding target drying mode according to the material characteristics of the target material;

[0033] The drying mode for the target material is set according to the target drying mode.

[0034] A second aspect of the present invention provides a material drying control system, comprising:

[0035] A drying prediction module, used for inputting the material characteristics into a trained drying prediction model to obtain predicted drying parameters and predicted material data;

[0036] A data acquisition module, drying the target material according to the predicted drying parameters, and acquiring real-time material data and real-time drying parameters during the drying process of the target material;

[0037] A real-time adjustment module, used for adjusting the real-time drying parameters in real time according to the real-time material data and target material data;

[0038] An error calculation module, used for calculating a first prediction error between the real-time drying parameter and the predicted drying parameter, and calculating a second prediction error between the real-time material data and the predicted material data;

[0039] The model adjustment module is used to control the adjustment of the drying prediction model according to the first prediction error, the second prediction error and the historical drying data.

[0040] In some embodiments, the real-time material data includes: a plurality of sub-real-time data, the target material data includes: a plurality of sub-target data, and the real-time adjustment module includes:

[0041] A parameter setting unit, used for presetting a first priority parameter, a second priority parameter and a third priority parameter among the drying parameters;

[0042] A deviation calculation unit, used for calculating the deviation between each of the sub-real-time data and the sub-target data;

[0043] The parameter adjustment unit is used to record the deviations exceeding the first threshold among all the deviations as valid deviations, and adjust the first priority parameter, the second priority parameter and the third priority parameter in sequence according to all the valid deviations.

[0044] A third aspect of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0045] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0046] The technical solution provided by the present invention has the following advantages and effects: by using a trained drying prediction model, the direction of the drying process of the target material can be predicted, and the drying process of the target material can be predictively adjusted, which can improve the robustness of the control and provide optimization suggestions and decision support for the drying process for operators. By acquiring the material data and drying parameters of the target material in the drying process in real time, the working parameters of the dryer are dynamically adjusted according to these data, and real-time feedback control is performed to make the control more precise, improve production efficiency and product quality, and through real-time feedback and intelligent adjustment, the drying process can be more accurately controlled to avoid problems such as overdrying or moisture, improve product quality stability, realize the combination of real-time feedback adjustment and predictive adjustment, avoid overdrying or moisture of the material, and provide optimization suggestions and decision support for the drying process for operators. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic flow chart of the material drying control method provided by the present invention;

[0048] Figure 2 It is a structural block diagram of the material drying control system provided by the present invention;

[0049] Figure 3 It is a diagram of the internal structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] In order to facilitate the understanding of the present invention, specific embodiments of the present invention will be described in more detail below with reference to the accompanying drawings.

[0051] Unless otherwise specified or defined, the "first, second..." used in this article is merely used to distinguish names and does not represent a specific quantity or order.

[0052] Unless specifically stated or defined otherwise, the term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0053] It should be noted that, in this document, “fixed to” or “connected to” may mean directly fixing or connecting to an element, or indirectly fixing or connecting to an element.

[0054] like Figure 1 As shown, this embodiment provides a material drying control method, including the following steps S1 to S5:

[0055] Step S1, obtaining material characteristics of the target material to be dried; in practical applications, material characteristics include: initial moisture content, material type, material particle size, material density, material specific heat capacity and material composition, etc.

[0056] Step S2: input the material characteristics into the trained drying prediction model to obtain predicted drying parameters and predicted material data.

[0057] In practical applications, the target material is dried by a dryer. The drying parameters of the dryer include: drying medium temperature, drying medium flow rate, material residence time and feed amount. The predicted drying parameters are the specific values ​​of drying medium temperature, drying medium flow rate, material residence time and feed amount. The material data include: moisture content, drying rate, surface temperature and internal temperature. The predicted material data are the specific values ​​of moisture content, drying rate, surface temperature and internal temperature. The predicted drying parameters and predicted material data of the target material are obtained by predicting the drying prediction model, which can predictively adjust the drying process of the target material, improve the robustness of the control, and provide optimization suggestions and decision support for the drying process for operators.

[0058] Specifically, the training method of the drying prediction model includes:

[0059] Collect drying data of different types of materials during the drying process, mark the drying data, and distinguish the real drying data corresponding to different types of materials;

[0060] Dividing the drying data into a training set and a test set;

[0061] Using the training set to train the drying prediction model until a training termination condition is reached, thereby obtaining a trained drying prediction model;

[0062] The trained drying prediction model is tested using the test set, and when the test result meets the preset requirements, a trained drying prediction model is obtained.

[0063] In practical applications, the real drying data includes: material characteristics and drying parameters. The drying prediction model can use a regression model or a neural network model to determine the loss function of the drying prediction model. In the process of training the drying prediction model using a training set, the training prediction data is obtained. The difference between the training prediction data and the real drying data is calculated according to the loss function. The parameters of the drying prediction model are updated according to the difference until the model converges or reaches the maximum number of training times, that is, after the training termination condition is reached, the trained drying prediction model is obtained. In order to evaluate the quality of the drying prediction model, the trained drying prediction model is tested with a test set to obtain test results. The test results are performance evaluation indicators. The performance evaluation indicators include mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE) and R 2 Indicators, etc., when the test results meet the preset requirements, a trained drying prediction model is obtained. By using the drying data of different types of materials as training sets, the model can learn the drying characteristics and optimal drying parameters of different types of materials.

[0064] Specifically, before inputting the material characteristics into the trained drying prediction model to obtain the predicted drying parameters and predicted material data, the method further includes:

[0065] Selecting a corresponding target drying mode according to the material characteristics of the target material;

[0066] The drying mode for the target material is set according to the target drying mode.

[0067] In practical applications, the drying mode of the same type of material is usually fixed. Therefore, the drying mode can be selected in advance according to the type of material. The drying modes include: conventional drying mode, fast drying mode, intermittent drying mode and multi-stage drying mode. After obtaining the material characteristics of the target material, the corresponding target drying mode can be determined, and then the drying mode of the dryer for the target material is set according to the target drying mode. By selecting the drying mode in advance, the training of the model in terms of drying mode selection is reduced, thereby improving the model training speed. Specifically, by providing an operation interface, the operator is allowed to manually select the drying mode and adjust the necessary parameters according to the target material, and save the parameter combination for future use.

[0068] Step S3: Dry the target material according to the predicted drying parameters, and obtain real-time material data and real-time drying parameters during the drying process of the target material.

[0069] In practical applications, the drying parameters of the dryer are set according to the predicted drying parameters, so that the dryer dries the target material according to the predicted drying parameters. During the drying process, different types of sensors are used to monitor the real-time material data of the target material during the drying process in real time to obtain a more comprehensive data reference, and the data of different types of sensors are integrated to improve the detection accuracy and reliability. The sensors include: a moisture content sensor, a first temperature sensor, a second temperature sensor, a humidity sensor, and a particle size sensor; the first temperature sensor is used to detect the surface temperature of the target material, and the second temperature sensor is used to detect the internal temperature of the target material. At the same time, the drying parameters of the dryer are also obtained in real time to obtain the real-time drying parameters. By comparing the obtained real-time drying parameters with the predicted drying parameters, the error between the two can be obtained, which is convenient for adjusting the drying prediction model according to the error, realizing the adaptive adjustment of the drying prediction model, and further improving the prediction accuracy of the drying prediction model.

[0070] Step S4: adjusting the real-time drying parameters in real time according to the real-time material data and the target material data.

[0071] Specifically, the real-time material data includes: a plurality of sub-real-time data, the target material data includes: a plurality of sub-target data, and the real-time adjustment of the real-time drying parameters according to the real-time material data and the target material data includes:

[0072] Presetting a first priority parameter, a second priority parameter and a third priority parameter among the drying parameters;

[0073] Calculating the deviation between each of the sub-real-time data and the sub-target data;

[0074] Deviations exceeding the first threshold among all deviations are recorded as valid deviations, and the first priority parameter, the second priority parameter and the third priority parameter are adjusted in sequence according to all valid deviations.

[0075] In practical applications, the first threshold is pre-set, and the allowable range of deviation is limited by the first threshold. When the deviation between the sub-real-time data and the sub-target data exceeds the first threshold, the drying parameters of the dryer can be adjusted according to the priority order of the drying parameters by setting the first priority parameter, the second priority parameter and the third priority parameter. When an effective deviation occurs, appropriate drying parameters can be adjusted to prevent the effective deviation from being difficult to adjust in time due to improper parameter adjustment, or the occurrence of other deviations other than the effective deviation.

[0076] Specifically, the first priority parameter includes: drying medium temperature and drying medium flow rate, the second priority parameter includes: material residence time, the third priority parameter includes: feed amount, and the first priority parameter, the second priority parameter and the third priority parameter are adjusted in sequence according to all effective deviations, including:

[0077] Determine the adjustment sequence of drying medium temperature and drying medium flow rate according to all effective deviations;

[0078] The first adjustment amount is preset to adjust the drying parameter arranged first in the adjustment sequence;

[0079] When the effective deviation exceeds the second threshold, adjusting the drying parameter arranged later in the adjustment sequence according to a preset second adjustment amount;

[0080] When the effective deviation exceeds a third threshold, adjusting the material residence time according to a preset time adjustment amount;

[0081] When the effective deviation exceeds a third threshold value and the duration exceeds a time threshold value, the feed amount is adjusted according to a preset feed adjustment amount.

[0082] In practical applications, the multiple sub-real-time data include: real-time moisture content, real-time surface temperature, real-time internal temperature and real-time drying rate, and the multiple sub-target data include: target moisture content, target surface temperature, target internal temperature and target drying rate. In this embodiment, taking moisture content as an example, the calculation formula for the deviation between the real-time moisture content and the target moisture content is as follows:

[0083] |ΔM|=|M actual -M target ∣,

[0084] Where: M actual is the real-time moisture content currently measured, M target It is the preset target moisture content. Set an allowable deviation range (for example, 0.5%), which is the first threshold. When the deviation exceeds the first threshold, that is, when an effective deviation occurs, the system will make adjustments. The specific adjustment method is as follows:

[0085] 1. First adjust the drying medium temperature (Temperature, T). When the deviation |ΔM|>0.5, adjust the drying medium temperature. The temperature adjustment amount: for every 0.1% deviation, the temperature change ΔT is 0.5℃ (the upper limit is the maximum allowable temperature). At this time, the temperature adjustment amount is the first adjustment amount. Through fine temperature adjustment, the drying process can be controlled more accurately, so that the real-time moisture content of the material gradually approaches and reaches the target moisture content. It helps to reduce errors in the drying process and improve drying accuracy and product quality.

[0086] 2. If the effective deviation reaches the second threshold after reaching the maximum allowable temperature, the second threshold is 1, that is, when the effective deviation |ΔM|>1.0, adjust the drying medium flow rate (Flow Rate, F), the flow rate adjustment amount: for every 0.5% deviation, the flow rate change ΔF is 1% (the upper limit is the maximum allowable flow rate), and the flow rate adjustment amount is the second adjustment amount. When the temperature has reached the upper limit and cannot be adjusted further, increasing the flow rate can further increase the drying rate and accelerate the evaporation of water, thereby more effectively reducing the moisture content deviation. In addition, the increase in flow rate helps to improve the airflow distribution in the drying chamber, so that the various parts of the material are heated more evenly and reduce quality problems caused by uneven drying. Since the effective deviation continues to increase after the drying medium temperature is adjusted to the maximum allowable temperature, more significant adjustments are required to quickly respond to and correct the deviation. For every 0.5% deviation, the flow rate adjustment amount is greater than the temperature adjustment amount, that is, the second adjustment amount is greater than the first adjustment amount.

[0087] 3. If the effective deviation reaches the third threshold after reaching the maximum allowable flow rate, the third threshold is 2, that is, when the effective deviation |ΔM|>2.0, adjust the material residence time (Residence Time, t), time adjustment amount: for every 1.0% deviation, the residence time change Δt is 5% (upper limit is the maximum allowable time). Every 1.0% deviation corresponds to a 5% residence time change. Such a proportional setting can ensure a significant reduction in moisture content within a reasonable time, thereby accelerating the process of reaching the target moisture content. Since the effective deviation continues to increase after adjusting the drying medium temperature and the drying medium flow rate to the maximum allowable range, more significant adjustments are required to quickly respond to and correct the deviation. If the adjustment amount is too small, it may take a long time to correct the moisture content deviation, affecting the drying efficiency.

[0088] 4. If the effective deviation reaches the fourth threshold after reaching the maximum allowable time, and the duration exceeds the time threshold, that is, when the effective deviation continues to exceed 2% for a certain period of time (for example, 1 hour), adjust the feed rate (Feed Rate, Q), feed adjustment amount: for every 1.0% deviation, the feed rate change ΔQ is 2% (the upper limit is the maximum capacity of the equipment). By adjusting the feed rate, the system state can be changed quickly, which helps to correct the deviation in a short time and avoid further expansion of the deviation. Reasonable feed rate adjustment can ensure that the residence time of the material in the system is effectively utilized, avoiding the decrease in production efficiency caused by too long or too short residence time. At the same time, by accurately controlling the feed rate, a smooth transition of material flow can be achieved to avoid fluctuations and instability in the production process.

[0089] For the drying rate, the adjustment order of the first priority parameter is as follows: 1) Adjust the drying medium temperature: If the drying rate is too fast and the surface temperature of the material is close to or exceeds its maximum allowable temperature, or the internal temperature shows signs of overheating, it is first necessary to lower the drying medium temperature, because the effect of temperature on the drying rate is very direct. Lowering the temperature can effectively slow down the drying rate and protect the material from overheating; 2) Adjust the drying medium flow rate: If the drying rate is too fast, but the material temperature is far from reaching a dangerous level, the flow rate can be reduced. The effect of the flow rate adjustment on the drying rate is slightly slower than that of the temperature, but it can reduce the evaporation rate on the material surface and avoid overdrying.

[0090] For the surface temperature, the adjustment order of the first priority parameter is: 1) adjust the drying medium temperature or the drying medium flow rate. If the surface temperature is too high, you can directly reduce the drying medium temperature or reduce the drying medium flow rate: reduce the surface evaporation rate and reduce the surface temperature; 2) adjust the drying medium temperature. If the surface temperature is too low, increase the drying medium temperature to increase the evaporation rate.

[0091] For the internal temperature, the adjustment order of the first priority parameter is: 1) adjust the drying medium temperature or the drying medium flow rate. If the internal temperature is too high, lower the temperature to prevent the internal temperature of the material from being too high and causing quality degradation, or reduce the drying medium flow rate to reduce heat conduction into the material; 2) adjust the drying medium temperature. If the internal temperature is too low, increase the temperature to ensure that the internal temperature of the material reaches the effective drying temperature range.

[0092] In the present invention, the drying medium temperature and the drying medium wind speed are adjusted first, because they have the most direct impact on the drying rate and material temperature, and then the material residence time is adjusted, because the change of time has a relatively slow impact on the drying process, and finally the feed amount is adjusted, because it directly affects the load and stability of the dryer.

[0093] Step S5, calculating a first prediction error between the real-time drying parameter and the predicted drying parameter, and calculating a second prediction error between the real-time material data and the predicted material data.

[0094] In practical applications, the first prediction error and the second prediction error are calculated by an error calculation formula, and the error calculation formula is:

[0095]

[0096] Among them, the Y p represents the predicted value of the drying prediction model, Y a It represents the real-time value of the target material obtained, the real-time drying parameters and the predicted drying parameters are substituted into the error calculation formula to obtain the first prediction error, and the real-time material data and the predicted material data are substituted into the error calculation formula to obtain the second prediction error.

[0097] Step S6: controlling the adjustment of the drying prediction model according to the first prediction error, the second prediction error and the historical drying data.

[0098] Specifically, controlling the adjustment of the drying prediction model according to the first prediction error, the second prediction error and the historical drying data includes:

[0099] When the first prediction error exceeds a first error threshold, selecting from the historical drying data the historical drying parameters corresponding to the historical material having the highest similarity to the target material characteristics;

[0100] adjusting the drying prediction model according to the historical drying parameters and the first prediction error;

[0101] When the second prediction error exceeds a second error threshold, selecting historical material data corresponding to the historical material having the highest similarity to the target material characteristics from the historical drying data;

[0102] The drying prediction model is adjusted according to the historical material data and the second prediction error.

[0103] In practical applications, the first error threshold and the second error threshold are both pre-set, and the first error threshold and the second error threshold can be the same. According to the characteristics of the target material (for example, initial moisture content, material type, particle size, etc.), find materials with high similarity in the historical drying data, compare the drying process of the target material and similar historical materials, analyze their differences, and adjust the drying strategy, such as parameter adjustment, model correction and alarm mechanism, according to the analysis results, that is, the first prediction error and the second prediction error. If it is found that the drying rate of the target material is slower than that of similar historical materials, the drying medium temperature or the drying medium flow rate can be appropriately increased. On the contrary, if the drying rate is too fast, the drying medium temperature or the drying medium flow rate can be reduced to avoid overheating or quality degradation of the material; if it is found that the drying prediction model has a large error in predicting the drying process of the target material, the model needs to be corrected, and the model parameters are updated according to the error to achieve self-learning of the model. If an abnormal situation is detected, the alarm mechanism is triggered to remind the operator to intervene.

[0104] The material drying control method of the present invention predicts the direction of the drying process of the target material through a trained drying prediction model, can predictively adjust the drying process of the target material, can improve the robustness of control, and provide optimization suggestions and decision support for the drying process for operators. By acquiring material data and drying parameters of the target material in the drying process in real time, the working parameters of the dryer are dynamically adjusted according to these data, and real-time feedback control is performed to make the control more precise, improve production efficiency and product quality. Through real-time feedback and intelligent adjustment, the drying process can be controlled more accurately, problems such as overdrying or moisture can be avoided, and the stability of product quality can be improved. The combination of real-time feedback adjustment and predictive adjustment is realized, overdrying or moisture of the material can be avoided, and optimization suggestions and decision support for the drying process are provided to operators.

[0105] like Figure 2 As shown, the embodiment of the present invention further provides a material drying control system, comprising:

[0106] A feature acquisition module 10 is used to acquire material features of the target material to be dried;

[0107] A drying prediction module 20, for inputting the material characteristics into a trained drying prediction model to obtain predicted drying parameters and predicted material data;

[0108] A data acquisition module 30 dries the target material according to the predicted drying parameters, and acquires real-time material data and real-time drying parameters during the drying process of the target material;

[0109] A real-time adjustment module 40, used for adjusting the real-time drying parameters in real time according to the real-time material data and target material data;

[0110] An error calculation module 50, used to calculate a first prediction error between the real-time drying parameter and the predicted drying parameter, and to calculate a second prediction error between the real-time material data and the predicted material data;

[0111] The model adjustment module 60 is used to control the adjustment of the drying prediction model according to the first prediction error, the second prediction error and the historical drying data.

[0112] As an optional implementation, the real-time material data includes: a plurality of sub-real-time data, the target material data includes: a plurality of sub-target data, and the real-time adjustment module includes the following units not shown in the figure:

[0113] A parameter setting unit, used for presetting a first priority parameter, a second priority parameter and a third priority parameter among the drying parameters;

[0114] A deviation calculation unit, used for calculating the deviation between each of the sub-real-time data and the sub-target data;

[0115] The parameter adjustment unit is used to record the deviations exceeding the first threshold among all the deviations as valid deviations, and adjust the first priority parameter, the second priority parameter and the third priority parameter in sequence according to all the valid deviations.

[0116] As an optional embodiment, the first priority parameter includes: drying medium temperature and drying medium flow rate, the second priority parameter includes: material residence time, the third priority parameter includes: feed amount, and the parameter adjustment unit includes the following units not shown in the figure:

[0117] A sequence determination unit, used for determining the adjustment sequence of the drying medium temperature and the drying medium flow rate according to all effective deviations;

[0118] A first adjustment unit, used to adjust the drying parameter arranged first in the adjustment sequence by a preset first adjustment amount;

[0119] A second adjustment unit, configured to adjust the drying parameter arranged later in the adjustment sequence according to a preset second adjustment amount when the effective deviation exceeds a second threshold;

[0120] A third adjustment unit, configured to adjust the material residence time according to a preset time adjustment amount when the effective deviation exceeds a third threshold;

[0121] The fourth adjustment unit is used to adjust the feed amount according to a preset feed adjustment amount when the effective deviation exceeds the third threshold and the duration exceeds the time threshold.

[0122] As an optional implementation, the model adjustment module includes the following units not shown in the figure:

[0123] A first selection unit is used to select, from the historical drying data, historical drying parameters corresponding to the historical material having the highest similarity to the target material characteristics when the first prediction error exceeds a first error threshold;

[0124] a fifth adjustment unit, configured to adjust the drying prediction model according to the historical drying parameter and the first prediction error;

[0125] A second selection unit is used to select historical material data corresponding to the historical material with the highest similarity to the target material characteristics from the historical drying data when the second prediction error exceeds a second error threshold;

[0126] The sixth adjustment unit is used to adjust the drying prediction model according to the historical material data and the second prediction error.

[0127] As an optional implementation, the material drying control system includes the following units not shown in the figure:

[0128] A data collection unit, used to collect drying data of different types of materials during the drying process, mark the drying data, and distinguish the real drying data corresponding to different types of materials;

[0129] A data division unit, used for dividing the drying data into a training set and a test set;

[0130] A model training unit, used to train the drying prediction model using the training set until a training termination condition is reached to obtain a trained drying prediction model;

[0131] The model testing unit is used to test the trained drying prediction model using the test set, and obtain the trained drying prediction model when the test result meets the preset requirements.

[0132] As an optional implementation, the material drying control system includes the following units not shown in the figure:

[0133] A mode selection unit, used for selecting a corresponding target drying mode according to the material characteristics of the target material;

[0134] The mode setting unit is used to set a drying mode for a target material according to the target drying mode.

[0135] Each module of the material drying control system can be implemented in whole or in part by software, hardware and their combination. Each module and unit can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0136] like Figure 3 As shown, an embodiment of the present invention discloses a computer device, including a memory and a processor, wherein the memory stores a computer program;

[0137] The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the material drying control method described in the above embodiments is implemented.

[0138] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0139] An embodiment of the present invention further discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the material drying control method described in the above embodiments.

[0140] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0141] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A material drying control method, characterized in that: include: Obtaining material characteristics of the target material to be dried; Inputting the material characteristics into a trained drying prediction model to obtain predicted drying parameters and predicted material data; Dry the target material according to the predicted drying parameters, and obtain real-time material data and real-time drying parameters during the drying process of the target material; Adjust the real-time drying parameters in real time according to the real-time material data and the target material data; Calculating a first prediction error between the real-time drying parameter and the predicted drying parameter, and calculating a second prediction error between the real-time material data and the predicted material data; Adjustment of the drying prediction model is controlled according to the first prediction error, the second prediction error and the historical drying data.

2. The material drying control method according to claim 1, characterized in that: The real-time material data includes: a plurality of sub-real-time data, the target material data includes: a plurality of sub-target data, and the real-time adjustment of the real-time drying parameters according to the real-time material data and the target material data includes: Presetting a first priority parameter, a second priority parameter and a third priority parameter among the drying parameters; Calculating the deviation between each of the sub-real-time data and the sub-target data; Deviations exceeding the first threshold among all deviations are recorded as valid deviations, and the first priority parameter, the second priority parameter and the third priority parameter are adjusted in sequence according to all valid deviations.

3. The material drying control method according to claim 2, characterized in that: The first priority parameter includes: drying medium temperature and drying medium flow rate, the second priority parameter includes: material residence time, the third priority parameter includes: feed amount, and the first priority parameter, the second priority parameter and the third priority parameter are adjusted in sequence according to all effective deviations, including: Determine the adjustment sequence of drying medium temperature and drying medium flow rate according to all effective deviations; Adjusting the drying parameter arranged first in the adjustment sequence according to a preset first adjustment amount; When the effective deviation exceeds the second threshold, adjusting the drying parameter arranged later in the adjustment sequence according to a preset second adjustment amount; When the effective deviation exceeds a third threshold, adjusting the material residence time according to a preset time adjustment amount; When the effective deviation exceeds a third threshold value and the duration exceeds a time threshold value, the feed amount is adjusted according to a preset feed adjustment amount.

4. The material drying control method according to claim 1, characterized in that: The step of controlling the adjustment of the drying prediction model according to the first prediction error, the second prediction error and the historical drying data comprises: When the first prediction error exceeds a first error threshold, selecting from the historical drying data the historical drying parameters corresponding to the historical material having the highest similarity to the target material characteristics; adjusting the drying prediction model according to the historical drying parameters and the first prediction error; When the second prediction error exceeds a second error threshold, selecting historical material data corresponding to the historical material having the highest similarity to the target material characteristics from the historical drying data; The drying prediction model is adjusted according to the historical material data and the second prediction error.

5. The material drying control method according to any one of claims 1 to 4, characterized in that: The training method of the drying prediction model comprises: Collect drying data of different types of materials during the drying process, mark the drying data, and distinguish the real drying data corresponding to different types of materials; Dividing the drying data into a training set and a test set; Using the training set to train the drying prediction model until a training termination condition is reached, thereby obtaining a trained drying prediction model; The trained drying prediction model is tested using the test set, and when the test result meets the preset requirements, a trained drying prediction model is obtained.

6. The material drying control method according to any one of claims 1 to 4, characterized in that: Before inputting the material characteristics into the trained drying prediction model to obtain the predicted drying parameters and predicted material data, the method further includes: Selecting a corresponding target drying mode according to the material characteristics of the target material; The drying mode for the target material is set according to the target drying mode.

7. Material drying control system, characterized in that: include: A feature acquisition module, used to acquire material features of a target material to be dried; A drying prediction module, used for inputting the material characteristics into a trained drying prediction model to obtain predicted drying parameters and predicted material data; A data acquisition module, drying the target material according to the predicted drying parameters, and acquiring real-time material data and real-time drying parameters during the drying process of the target material; A real-time adjustment module, used for adjusting the real-time drying parameters in real time according to the real-time material data and target material data; An error calculation module, used for calculating a first prediction error between the real-time drying parameter and the predicted drying parameter, and calculating a second prediction error between the real-time material data and the predicted material data; The model adjustment module is used to control the adjustment of the drying prediction model according to the first prediction error, the second prediction error and the historical drying data.

8. The material drying control system according to claim 7, characterized in that: The real-time material data includes: a plurality of sub-real-time data, the target material data includes: a plurality of sub-target data, and the real-time adjustment module includes: A parameter setting unit, used for presetting a first priority parameter, a second priority parameter and a third priority parameter among the drying parameters; A deviation calculation unit, used for calculating the deviation between each of the sub-real-time data and the sub-target data; The parameter adjustment unit is used to record the deviations exceeding the first threshold among all the deviations as valid deviations, and adjust the first priority parameter, the second priority parameter and the third priority parameter in sequence according to all the valid deviations.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images