Drying machine control method based on industrial-grade self-adaptive parameter adjustment

Abstract

The invention provides a dryer control method based on industrial-grade self-adaptive parameter adjustment, and relates to the technical field of self-adaptive parameter adjustment. The method comprises the following steps: collecting historical drying control data of different types of drying objects, extracting optimal parameter control information for different drying control stages, and forming corresponding optimal parameter control data; performing dimension reduction analysis of multi-parameter control on the optimal parameter control data corresponding to different types of drying objects to form corresponding optimal parameter dimension reduction control data; obtaining object condition information of different types of drying objects, and performing control parameter adjustment analysis for condition parameters in combination with the corresponding optimal parameter dimension reduction control data to form condition change control parameter regulation data; and target condition information of the target drying object is obtained, and corresponding target optimal parameter control data are determined in combination with the condition change control parameter regulation and control data. According to the method, more efficient and energy-saving process parameter regulation and control are realized through reasonable regulation and control parameter analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of adaptive parameter adjustment, and in particular to a dryer control method based on industrial-grade adaptive parameter adjustment. Background Art

[0002] A dryer is a mechanical device that uses heat to reduce the moisture content of materials. It is used to dry objects by vaporizing moisture from the material through heating, resulting in a solid material with a specified moisture content. To achieve efficient dehumidification using a dryer, it is necessary to properly control parameters at different stages of the drying process to ensure efficient drying while saving energy.

[0003] Currently, most of the control over desiccant operating parameters is still based on simple monitoring data feedback and empirical judgment. Although it can reasonably adjust the drying parameters of the same product to a certain extent, it has the limitation that the product type and status affect the parameter control, and it is impossible to achieve more intelligent parameter control to ensure the efficiency and energy saving of the drying process.

[0004] Therefore, designing a dryer control method based on industrial-grade adaptive parameter adjustment to achieve more efficient and energy-saving process parameter control through reasonable control parameter analysis is an urgent problem to be solved. Summary of the Invention

[0005] The purpose of the present invention is to provide a dryer control method based on industrial-grade adaptive parameter adjustment, which collects historical drying control data of multiple drying objects of different types, and after clustering the data of the same object conditions, determines the optimal parameter control data corresponding to different drying control stages according to the energy consumption rate and operation time of the control, and on this basis uses the optimal parameter control data corresponding to drying objects with different object conditions to perform a control parameter change correlation analysis for changes in object conditions. At the same time, the change correlation analysis uses parameter vectorization to achieve dimensionality reduction processing, which greatly improves the efficiency of data processing and reduces the difficulty of processing, and also ensures the rationality and accuracy of the analysis. The data analysis results formed can make reasonable parameter control predictions for object conditions that have not appeared in history, and provide a reasonable, accurate and effective data reference for efficient and energy-saving drying control of the target object, making the parameter control of the dryer more intelligent, efficient and energy-saving.

[0006] In a first aspect, the present application provides a drying machine control method based on industrial self-adaptive parameter adjustment, comprising: collecting historical drying control data of different types of drying objects, extracting optimal parameter control information for different drying control stages, and forming optimal parameter control data corresponding to different types of drying objects; performing dimensionality reduction analysis of multi-parameter control on the optimal parameter control data corresponding to different types of drying objects, and forming corresponding optimal parameter dimensionality reduction control data; obtaining object condition information of different types of drying objects, and combining the corresponding optimal parameter dimensionality reduction control data to perform control parameter adjustment analysis for condition parameters, and forming condition change control parameter regulation data; obtaining target condition information of a target drying object, and combining the condition change control parameter regulation data to determine corresponding target optimal parameter control data.

[0007] In the present application, the method collects historical drying control data of a plurality of different types of drying objects, determines optimal parameter control data corresponding to different drying control stages according to the energy consumption rate and operation time of the control after clustering data of the same object condition, and on this basis, performs control parameter change correlation analysis for object condition changes using optimal parameter control data corresponding to drying objects with different object conditions, while the change correlation analysis is assisted by parameter vectorization to realize dimensionality reduction processing, greatly improving the efficiency of data processing and reducing the difficulty of processing, and also ensuring the rationality and accuracy of the analysis, and the data analysis results formed can reasonably predict the parameter regulation for object conditions that have never appeared in history, providing reasonable and accurate and effective data reference for efficient and energy-saving drying control of target objects, making the parameter regulation of the drying machine more intelligent, efficient and energy-saving.

[0008] As a possible implementation manner, collecting historical drying control data of different types of drying objects, extracting optimal parameter control information for different drying control stages, and forming optimal parameter control data corresponding to different types of drying objects, comprises: clustering object condition information of the historical drying control data of different types of drying objects to form different same-type object historical drying control data sets; extracting same-type object stage drying control information corresponding to different drying objects in the same drying control stage in the same-type object historical drying control data set from different same-type object historical drying control data sets to form a same-type object stage drying control information set; performing comparison analysis based on unit time energy consumption on different same-type object stage drying control information sets in the same-type object historical drying control data set to determine corresponding same-type object optimal drying control information; and combining the same-type object optimal drying control information corresponding to different drying control stages in the same-type object historical drying control data set to form corresponding same-type object optimal parameter control data.

[0009] In the present application, the object conditions of different drying objects themselves have an impact on the parameter control of the drying process, such as the volume, density, porosity, surface area size, heat transfer efficiency of the drying object, etc., so the objects need to be divided according to different object conditions to determine the corresponding optimal parameter regulation data of the drying process. This provides more reasonable and accurate basic data for subsequent analysis of optimal regulation data. Of course, for the clustering of object condition information, objects with the same object conditions can be confirmed as objects of the same type. It should be noted that the object conditions determined in the present application mainly consider conditions that have a significant impact on the drying process, such as weight and material category, which do not have a direct impact. For the stage process of drying, the drying stages based on the drying rate curve can be determined, including the preheating period, constant-speed drying period, falling-speed drying period, and equilibrium period. This ensures the uniformity of the stage division standard and guarantees the rationality and accuracy of the data analysis based on the stage. The extraction of the optimal drying control information of the same type of object in the same stage mainly considers two aspects: the drying time and the energy consumption of drying, which are important indicators for evaluating the drying effect. Therefore, the energy consumption per unit time can be used as the standard for evaluating the optimal data.

[0010] As a possible implementation, for different same-type object stage drying control information sets under the same-type object historical drying control data set, a comparative analysis based on the energy consumption per unit time is performed to determine the corresponding same-type object optimal drying control information, including: determining the stage control parameters corresponding to different drying control stages, for different same-type object stage drying control information sets, determining the stage control parameter values of the different stage control parameters corresponding to the different same-type drying objects in the drying control stages and the corresponding stage drying processing time , n represents the number of different drying control stages, k represents the number of different stage control parameters corresponding to the drying control stage numbered n, and m represents the number of different same-type drying objects; for different same-type drying objects, according to the stage control parameter values of the corresponding different stage control parameters and the stage drying processing time , the corresponding same-type object stage unit energy consumption value is determined; according to the different same-type object stage unit energy consumption values , and in combination with the corresponding stage drying processing time , the following comparative analysis is performed to determine the same-type object optimal drying control information: the same-type object stage unit energy consumption values are arranged in descending order, and the adjacent same-type object stage unit energy consumption values corresponding stage drying processing time length When the difference between the adjacent same type object stage unit energy consumption values corresponding stage drying processing time length When the difference between the adjacent same type object stage unit energy consumption values the greater same type object stage unit energy consumption value The corresponding same type object stage drying control information of the same type object is determined as the same type object optimal drying control information.

[0011] In the present application, in each drying control stage, the control of different stage control parameters requires energy consumption, and the consumption of energy reflects the necessary energy consumption required for dehumidification drying on the one hand, and considers that energy saving is not the higher the energy consumption, the higher the drying efficiency obtained, after all, the amount of evaporated water vapor that can be carried away by the gas through convection drying is limited, and blindly increasing the temperature, flow rate and the like of the gas can play a role within a certain range, and beyond the limit can only be a useless waste of energy. Therefore, considering these aspects, the determination of the optimal drying control information needs to consider the limiting effect of parameter regulation on drying efficiency when comparing the unit time energy consumption, which can be determined by the length of the drying stage duration corresponding to the unit time energy consumption from large to small. If the parameter regulation continues to increase the energy consumption and has a significant effect on improving the drying effect, then the corresponding duration will be shortened when the unit time energy consumption increases. If the parameter regulation continues to increase the energy consumption and cannot significantly improve the drying effect, then the corresponding duration will basically remain unchanged when the unit time energy consumption increases. In this way, the duration corresponding to the best effect of parameter regulation energy consumption can be determined, and the energy consumption affecting duration can be set according to the actual situation, or it can be determined based on the big data analysis of the time length change rate. In addition, the energy consumption of the stage control parameters of the drying control stage can be accurately determined by obtaining the electric energy consumed by the drying machine in the corresponding drying stage in the actual process. The present application also considers that some forms of drying machines are system integrated and cannot directly obtain the energy consumption of the entire system, so it is better to convert the energy consumption value according to the parameter value. The parameter value energy conversion factor is determined according to the actual energy utilization rate of the energy consumption equipment of the corresponding drying machine. It should be noted that the stage control parameter value change function required for determining the unit energy consumption value is mainly formed by fitting the discrete parameter values collected within the corresponding duration of the stage control parameters. The fitting method is various, which can be least square or multiple power fitting with precision target.

[0012] As a possible implementation, the optimal parameter control data corresponding to different types of drying objects is subjected to multi-parameter control dimension reduction analysis to form corresponding optimal parameter dimension reduction control data, including: determining the optimal stage control parameter values of the control parameters at different stages in the time dimension according to the optimal parameter control data of the same type of objects at different drying control stages corresponding to the optimal parameter control data of different types of drying objects; establishing corresponding stage multi-parameter correlation vector data according to the optimal stage control parameter values of all stage control parameters at different drying control stages; performing parameter dimension reduction analysis on the stage multi-parameter correlation vector data corresponding to different drying control stages to form corresponding stage optimal parameter vector dimension reduction data; performing time dimension correlation vector change analysis on the stage optimal parameter vector dimension reduction data corresponding to different drying control stages to form corresponding stage optimal parameter dimension reduction control data; and collecting the stage optimal parameter dimension reduction control data corresponding to different drying control stages to form corresponding optimal parameter dimension reduction control data for different types of drying objects.

[0013] In the present application, the optimal parameter control data corresponding to the same type of drying object is determined, and the highest efficient and energy-saving parameter control data of each drying control stage can be selected when the same type of drying object is dried in the future. However, the use of these optimal parameter control data has great limitations. As long as the object conditions of the drying object change significantly, it is no longer applicable. In order to improve the adaptability of the optimal parameter control data, it is necessary to perform a reasonable correlation analysis of the object conditions. Before performing the correlation analysis of the object conditions, the optimal parameter control data needs to be reasonably processed. After all, there are many stage control parameters involved. If the original data is directly analyzed for the object conditions, on the one hand, it will increase the amount of data analysis and reduce the efficiency of analysis. On the other hand, the relationship between different stage control parameters is complex. Directly analyzing the original parameter data will greatly increase the complexity of the analysis. Therefore, before performing the correlation analysis, the stage control parameters need to be reasonably reduced in dimension. Considering that different stage control parameters have a strong mutual relationship, reasonable vectorization of them can not only preserve the relationship between the stage control parameters, but also greatly reduce the dimension of the analysis data. Of course, after vectorization, on the one hand, reasonable dimension reduction parameters need to be determined to ensure the rationality and accuracy of feature data extraction. On the other hand, the stage control parameters themselves are also changing in some drying control stages, and the processing of the corresponding dimension reduction parameters also needs to have time characteristics. In addition, it should be noted that the stage control parameter values obtained in the determination of the optimal drying control information are essentially discrete data collected in the corresponding stage control time based on the time dimension sequence. The unit time energy consumption value needs to be fitted in the time dimension to form a change function, and then the accurate unit time energy consumption value is obtained more reasonably. Here, the optimal stage control parameter value is also discrete data. After vectorization and dimension reduction, the change amount in the control time needs to be analyzed to form reasonable dimension reduction change data.

[0014] As a possible implementation manner, according to the optimal stage control parameter values of all stage control parameters of different drying control stages, a corresponding stage multi-parameter correlation vector data is established, including: for different drying control stages, a corresponding control parameter coordinate system is established according to the number of corresponding stage control parameters; the optimal stage control parameter values of corresponding different stage control parameters at the same time point are mapped into the control parameter coordinate system to form a corresponding time point optimal parameter control vector , r represents the number of different types of drying objects, represents the time length value of the drying object numbered r at the corresponding time point of the drying control stage numbered n; a set of time point optimal parameter control vectors corresponding to all time points , form the stage multi-parameter related vector data corresponding to the dry control stage.

[0015] In the present application, the fastest way of dimension reduction processing is vectorization, and the simplest vectorization is to form a coordinate system based on different stage control parameters for vectorization. Considering that the parameter values have time characteristics, the data collected at the same time point need to be vectorized to ensure the correctness of the vectorized data.

[0016] As a possible implementation manner, the stage multi-parameter related vector data corresponding to different dry control stages is subjected to parameter dimension reduction analysis to form corresponding stage optimal parameter vector dimension reduction data, including: for different dry control stages, determining the stage unit vector in the control parameter coordinate system corresponding to the stage ; according to the stage unit vector and the stage multi-parameter related vector data corresponding to the dry control stage, the following dimension reduction information is extracted to form the corresponding stage optimal parameter vector dimension reduction data: for different time point optimal parameter control vectors , the time point vector module is determined; for different time point optimal parameter control vectors , the time point vector angle of the same stage unit vector is determined ; for different time point optimal parameter control vectors , the time point vector reference rotation angle of the same stage unit vector is determined ; the time point vector module , the time point vector angle and the time point vector reference rotation angle corresponding to different time point optimal parameter control vectors are collected to form the corresponding stage optimal parameter vector dimension reduction data.

[0017] In the present application, the feature extraction of the dimension reduction information is an important content for ensuring the accuracy and rationality of the result formed by the subsequent correlation analysis of the object condition information using the extracted dimension reduction feature data. Since the information is expressed in the form of a vector, the completeness of the feature extraction of the dimension reduction information is converted into the accuracy of the target vector position information. The present application accurately determines the accurate position of the target vector in the coordinate system by extracting three parameter information including the size of the vector, the included angle between the vector and the unit vector, and the relative rotation azimuth angle between the vector and the unit vector. The combination of the drying control parameters corresponding to the three parameters is unique, so that the obtained dimension reduction feature information has rationality and accuracy. The extracted feature information only contains three parameter values based on the time parameter, which greatly reduces the complexity of data analysis compared with the correlation analysis using the original drying control parameters, while retaining the correlation information between different drying control parameters. The analysis efficiency is improved, and the rationality, accuracy and completeness of the data analysis result are fully guaranteed.

[0018] As a possible implementation, the time dimension correlation vector change analysis is performed on the stage optimal parameter vector dimension reduction data corresponding to different drying control stages to form corresponding stage optimal parameter dimension reduction control data, including: establishing a corresponding stage dimension reduction parameter coordinate system based on the time point vector module, time point vector angle, time point vector reference rotation angle and time length for different drying control stages; mapping the corresponding time point vector module , time point vector angle and time point vector reference rotation angle to the stage dimension reduction parameter coordinate system, and performing fitting analysis on the time dimension parameters to form the corresponding stage optimal control parameter dimension reduction change function .

[0019] In the present application, the correlation change analysis of the three vector parameter values also needs to consider the change of the parameters in the time dimension, so a four-dimensional coordinate system including the time parameter is established to express the correlation change data of the three vector parameter values, and reasonable fitting analysis is performed combined with the characteristics of the function to form a dimension reduction change function containing four parameters. This can ensure that the correlation between the stage control parameters can be accurately and reasonably expressed in the time dimension, providing an important data basis for subsequent applicability expansion analysis. The fitting analysis can be in the form of least squares or multiple power search with accuracy targets.

[0020] As a possible implementation manner, the object condition information of different types of drying objects is acquired, and a control parameter adjustment analysis on condition parameters is performed in combination with corresponding optimal parameter dimension reduction control data to form condition change control parameter regulation data, including: determining object condition values of all object conditions corresponding to different types of drying objects according to different object condition information corresponding to different types of drying objects , i represents the number of different object condition information; clustering stage optimal control parameter dimension reduction change functions of different types of drying objects in different drying control stages according to optimal parameter dimension reduction control data corresponding to different types of drying objects , to form a stage optimal control parameter dimension reduction change data set; performing control parameter adjustment analysis on different stage optimal control parameter dimension reduction change data sets in the following manner: extracting an arbitrary stage optimal control parameter dimension reduction change function and corresponding object condition values of all object conditions , and respectively marking them as a stage reference parameter dimension reduction function and a reference object condition value ; determining a change function difference of other stage optimal control parameter dimension reduction change functions from the stage reference parameter dimension reduction function and a condition difference value of corresponding object condition values from the reference object condition value , z represents the number of the remaining stage optimal control parameter dimension reduction change functions , and z = r-1; performing fitting analysis according to different change function differences and corresponding condition difference values of all different object conditions to determine the following stage condition-parameter reference change relationship.

[0021] In the present application, after obtaining the optimal parameter dimension reduction control data corresponding to different object conditions in the historical data, a correlation analysis of the optimal parameter dimension reduction control data changing with the object conditions can be performed, and the results of the analysis can not only be applied to the drying objects with the object condition combinations that have appeared in history, but also can predict the parameter regulation of the drying objects with new object condition combinations. In the correlation analysis, the synergistic relationship between the changes of the vector parameters and the changes of the object conditions is established. Different drying control stages are performed, and the differences between the object conditions and the corresponding dimension reduction functions of other different drying objects are determined based on any dimension reduction function as a reference. Then, the different difference amounts obtained are fitted as discrete data to form the synergistic relationship between the differences of the condition objects relative to the reference data and the differences between the dimension reduction functions and the reference data. Here, the number of items of the phase condition parameter correlation factor to be fitted and determined is determined according to the needs, and therefore the product form of the phase condition parameter correlation factor and the corresponding target condition difference can also be expressed as a polynomial of multiple powers, which can improve the accuracy of the relationship. Of course, it is necessary to ensure that the difference data obtained is sufficient to determine the constant term of the power.

[0022] As a possible implementation manner, the target condition information of the target drying object is obtained, and the corresponding target optimal parameter control data is determined by combining the condition change control parameter regulation data, including: determining the target object condition values of different condition objects according to the target condition information of the target drying object; determining the target object stage optimal control parameter dimension reduction change function corresponding to different drying control stages of the target drying object according to all target object condition values of the target drying object and combining the stage-condition parameter reference change relationship; performing dimension elevation processing on the different target object stage optimal control parameter dimension reduction change functions corresponding to different drying control stages to determine the corresponding target optimal parameter control data.

[0023] In the present application, after determining the stage-condition-parameter reference change relationship, the relationship can be used to reasonably analyze the parameter regulation of the target drying object corresponding to the new or historical condition object combination. In different drying regulation stages, the dimension reduction function of the target drying object is determined by using the corresponding relationship, and the dimension reduction function contains the numerical correlation information between different object conditions. The accurate prediction data can be obtained by performing dimension elevation processing on the correlation information.

[0024] As a possible implementation, the dimension reduction change function of the different target object stages corresponding to different drying control stages is processed in a higher dimension, and the corresponding target optimal parameter control data is determined, including: according to the target object stage optimal control parameter dimension reduction change function corresponding to the different drying control stages of the target object, mapping the function in the control parameter coordinate system corresponding to the drying control stage, and performing single parameter data splitting in the time dimension for different stage control parameters to form a parameter regulation continuous change target function of the different stage control parameters with time; the parameter regulation continuous change target functions of all stage control parameters corresponding to the drying control stage are collected to form stage optimal parameter control data; and the stage optimal parameter control data corresponding to different drying control stages is collected to form target optimal parameter control data.

[0025] In the present application, the dimension reduction function is processed in a higher dimension, and the vector parameter information involved in the function needs to be mapped into the corresponding parameter coordinate system. Therefore, the specific values of the different stage control parameters can be accurately determined, and the parameter value control information of all parameters in the entire drying control stage can be obtained.

[0026] The drying machine control method based on industrial self-adaptive parameter adjustment provided by the present application has the following advantages: The method collects the historical drying control data of a plurality of drying objects of different types, determines the optimal parameter control data corresponding to different drying control stages according to the energy consumption rate and operation time after clustering the data of the same object conditions, and uses the optimal parameter control data corresponding to the drying objects with different object conditions to analyze the correlation of the control parameters corresponding to the change of the object conditions. The dimension reduction processing is realized by means of parameter vectorization, which greatly improves the efficiency of data processing, reduces the difficulty of processing, ensures the rationality and accuracy of analysis, and further forms a data analysis result that can reasonably predict the parameter regulation of object conditions that have never appeared in history, thereby providing a reasonable, accurate and effective data reference for efficient and energy-saving drying control of the target object, and making the parameter regulation of the drying machine more intelligent, efficient and energy-saving. BRIEF DESCRIPTION OF DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0028] Fig. 1 The working implementation step diagram of the drying machine control method based on industrial-level adaptive parameter adjustment provided by the embodiment of the present application is provided. Fig. 2 The structural schematic diagram of the drying machine control method based on industrial-level adaptive parameter adjustment provided by the embodiment of the present application is provided. DETAILED DESCRIPTION

[0029] The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

[0030] The drying machine refers to a mechanical device for reducing the moisture of materials by using heat energy, which is used for drying operation on objects, and the moisture in the materials is vaporized and escaped by heating to obtain solid materials with a specified moisture content. To realize efficient dehumidification of materials by using the drying machine, reasonable parameter control needs to be performed on different stages of the drying process to ensure that the drying is completed efficiently and energy-savingly.

[0031] At present, the operation parameter control of the drying agent is mostly based on simple monitoring data feedback and experience judgment processing. Although the drying parameter control of the same product can be reasonably controlled to a certain extent, the product type and state affect the parameter control, and more intelligent parameter control cannot be realized to ensure the efficiency and energy saving of the drying process.

[0032] Reference Figs. 1-2 The embodiment of the present application provides a drying machine control method based on industrial-level adaptive parameter adjustment. The method collects historical drying control data of a plurality of drying objects of different types, determines optimal parameter control data corresponding to different drying control stages according to the energy consumption rate and operation time length of the control after clustering data of the same object condition, and performs correlation analysis of the change of the control parameter according to the optimal parameter control data corresponding to the drying object with different object conditions, and the correlation analysis of the change is realized by means of parameter vectorization to reduce the dimension, which greatly improves the efficiency of data processing and reduces the difficulty of processing, and also ensures the rationality and accuracy of the analysis, and the data analysis result formed can reasonably predict the parameter control of the object condition that has never appeared in history, and provides reasonable and accurate and effective data reference for efficient and energy-saving drying control of the target object, so that the parameter control of the drying machine is more intelligent, efficient and energy-saving.

[0033] The drying machine control method based on industrial-level adaptive parameter adjustment is specifically configured as follows: S1: Collecting historical drying control data of different types of drying objects, extracting optimal parameter control information for different drying control stages, and forming optimal parameter control data corresponding to different types of drying objects.

[0034] The historical drying control data of different types of drying objects is collected, the optimal parameter control information for different drying control stages is extracted, and the optimal parameter control data corresponding to different types of drying objects is formed, including: clustering the object condition information of the historical drying control data of different types of drying objects to form different same-type object historical drying control data sets; extracting the same-type object stage drying control information corresponding to different drying objects in the same drying control stage in the same-type object historical drying control data set from different same-type object historical drying control data sets to form a same-type object stage drying control information set; based on the comparison and analysis of the energy consumption per unit time, the corresponding same-type object optimal drying control information is determined from different same-type object stage drying control information sets in the same-type object historical drying control data set; and the same-type object optimal drying control information corresponding to different drying control stages in the same-type object historical drying control data set is collected to form the corresponding same-type object optimal parameter control data.

[0035] The object conditions of different drying objects themselves have an impact on the parameter control of the drying process, such as the volume, density, porosity, surface area, heat transfer efficiency, etc. of the drying objects, so the objects need to be divided according to different object conditions to determine the corresponding optimal parameter control data of the drying process. This provides more reasonable and accurate basic data for subsequent analysis of optimal control data. Of course, for the clustering of object condition information, only objects with the same object conditions can be confirmed as same-type objects. It should be noted that the object conditions determined in the present application mainly consider conditions that have a significant impact on the drying process, such as weight and material category, which do not have a direct impact on the conditions. For the stage process of drying, the drying stages based on the drying rate curve can be determined, including the preheating period, constant-speed drying period, falling-speed drying period, and equilibrium period. This ensures the uniformity of the stage division standard and guarantees the rationality and accuracy of the data analysis based on the stage. The extraction of the optimal drying control information of the same-type objects in the drying stage mainly considers two aspects: the drying time and the energy consumption during drying, which are important indicators for evaluating the drying effect. Therefore, the energy consumption per unit time can be used as the standard for evaluating the optimal data.

[0036] The different same-type object stage drying control information sets of the same-type object historical drying control data set are compared and analyzed based on the energy consumption per unit time to determine the corresponding same-type object optimal drying control information, including: determining the stage control parameter corresponding to different drying control stages, and determining the stage control parameter value of the different stage control parameters corresponding to the different same-type drying objects in the drying control stage for the different same-type object stage drying control information sets and the corresponding stage drying processing time , n represents the number of different drying control stages, k represents the number of different stage control parameters corresponding to the drying control stage numbered n, and m represents the number of different same-type drying objects; for different same-type drying objects, the corresponding same-type object stage unit energy consumption value is determined according to the stage control parameter value of the corresponding different stage control parameters and the stage drying processing time , , , wherein k represents the number of the stage control parameter, and represents the parameter value energy conversion factor corresponding to the stage control parameter numbered k , represents all stage control parameter values of the stage control parameter numbered k within the entire stage drying processing time obtained according to the same-type drying object numbered m in the drying control stage numbered n, and represents the stage control parameter value change function fitted by the stage control parameter values ; the following comparative analysis is performed according to the different same-type object stage unit energy consumption values and the corresponding stage drying processing time to determine the same-type object optimal drying control information: the adjacent same-type object stage unit energy consumption values are compared in the order of the same-type object stage unit energy consumption values from large to small, and the corresponding stage drying processing time ; when the difference between the adjacent same-type object stage unit energy consumption values and the corresponding stage drying processing time is not less than the energy consumption influence time, the larger same-type object stage unit energy consumption value of the adjacent two same-type object stage unit energy consumption values is determined as the same-type object optimal drying control information corresponding to the same-type object of the same-type object stage drying control information.

[0037] ​In each drying control stage, the control of different stage control parameters requires energy consumption, and the energy consumption not only reflects the necessary energy consumption required for dehumidification drying, but also considers that energy saving is not always the case where the greater the energy consumption, the higher the drying efficiency. After all, the amount of evaporated water vapor that can be carried away by the gas through convection drying is limited. Simply increasing the temperature, flow rate, etc. of the gas can have an effect within a certain range, but beyond the limit, it is only a waste of energy consumption. Therefore, considering these aspects, the determination of the optimal drying control information needs to consider the limitations of parameter regulation on drying efficiency when comparing energy consumption per unit time. This limitation can be determined by the duration of the drying stage corresponding to the energy consumption per unit time from large to small. If the parameter regulation continues to increase energy consumption and has a significant effect on improving drying efficiency, then the duration corresponding to the increase in energy consumption per unit time will also be shortened. If the parameter regulation continues to increase energy consumption and cannot significantly improve the effect of drying efficiency, then the duration corresponding to the increase in energy consumption per unit time will remain basically unchanged. In this way, the duration corresponding to the best effect of parameter regulation energy consumption can be determined. The time length affected by energy consumption can be set according to the actual situation, or it can be determined based on big data analysis of the time length change rate. In addition, the energy consumption of the stage control parameters of the drying control stage can be accurately determined by obtaining the electric energy consumed by the drying machine during the corresponding drying stage. The present application also considers that some forms of drying machines are system integrated and may not be able to directly obtain the energy consumption of the entire system, so it is better to convert the energy consumption value according to the parameter value. The parameter value energy conversion factor is determined according to the actual energy utilization rate of the energy consumption equipment of the corresponding drying machine. It should be noted that the stage control parameter value change function required for the determination of the unit energy consumption value is mainly formed by fitting the discrete parameter values collected within the corresponding time length of the stage control parameters. The fitting method is diverse, which can be least squares or multiple power fitting with precision targets.

[0038] S2: Perform multi-parameter control dimensionality reduction analysis on the optimal parameter control data corresponding to different types of drying objects to form corresponding optimal parameter dimensionality reduction control data.

[0039] The optimal parameter control data corresponding to different types of drying objects is subjected to multi-parameter control dimension reduction analysis to form corresponding optimal parameter dimension reduction control data, including: determining the optimal stage control parameter values of the control parameters in the time dimension for different stages according to the optimal parameter control data of the same type of objects corresponding to different drying control stages for different types of drying objects; establishing corresponding stage multi-parameter correlation vector data according to the optimal stage control parameter values of all stage control parameters in different drying control stages; performing parameter dimension reduction analysis on the stage multi-parameter correlation vector data corresponding to different drying control stages to form corresponding stage optimal parameter vector dimension reduction data; performing time dimension correlation vector change analysis on the stage optimal parameter vector dimension reduction data corresponding to different drying control stages to form corresponding stage optimal parameter dimension reduction control data; and collecting the stage optimal parameter dimension reduction control data corresponding to different drying control stages to form corresponding optimal parameter dimension reduction control data for different types of drying objects.

[0040] After the optimal parameter control data corresponding to the same type of drying object is determined, the most efficient and energy-saving parameter control data of each drying control stage can be selected when the same type of drying object is dried in the future. However, the use of these optimal parameter control data has great limitations. As long as the object conditions of the drying object change significantly, it is no longer applicable. In order to improve the adaptability of the optimal parameter control data, it is necessary to conduct a reasonable analysis of the relevance of the object conditions. Before conducting the analysis of the relevance of the object conditions, the optimal parameter control data needs to be reasonably processed. After all, there are many stage control parameters involved. If the original data is directly analyzed for the relevance of the object conditions, on the one hand, it will increase the amount of data analysis, resulting in a decrease in analysis efficiency. On the other hand, the relationship between different stage control parameters is complex. Direct analysis of the original parameter data will greatly increase the complexity of the analysis. Therefore, before conducting the relevance analysis, the stage control parameters need to be reasonably reduced in dimension. Considering that different stage control parameters have a strong mutual relationship, reasonable vectorization of them can not only preserve the relationship between the stage control parameters, but also greatly reduce the dimensionality of the analysis data. Of course, after vectorization, on the one hand, reasonable dimensionality reduction parameters need to be determined to ensure the rationality and accuracy of feature data extraction. On the other hand, the stage control parameters themselves change in some drying control stages, and the processing of the corresponding dimensionality reduction parameters also needs to have time characteristics. In addition, it should be noted that the stage control parameter values obtained in the determination of the optimal drying control information are essentially discrete data collected in the corresponding stage control duration based on the time dimension sequence. The unit time energy consumption value needs to be fitted in the time dimension to form a change function, and then the accurate unit time energy consumption value is obtained more reasonably. Here, the optimal stage control parameter values are also discrete data. After vectorization and dimensionality reduction, the change amount in the control duration also needs to be considered to form reasonable dimensionality reduction change data.

[0041] According to the optimal stage control parameter values of all stage control parameters of different drying control stages, the corresponding stage multi-parameter correlation vector data is established, including: for different drying control stages, a control parameter coordinate system is established according to the number of corresponding stage control parameters; the optimal stage control parameter values of corresponding different stage control parameters at the same time point are mapped into the control parameter coordinate system to form the corresponding time point optimal parameter control vector , r represents the number of different types of drying objects, represents the time duration value of the drying object numbered r at the drying control stage numbered n corresponding to different time points; the time point optimal parameter control vector at all time points is collected to form the stage multi-parameter correlation vector data corresponding to the drying control stage.

[0042] The fastest way of dimension reduction processing is vectorization, and the simplest vectorization is to form a coordinate system based on different stages of control parameters for vectorization. Considering that parameter values have time characteristics, data collected at the same time point needs to be vectorized to ensure the correctness of the vectorized data.

[0043] The parameter dimension reduction analysis is performed on the stage multi-parameter related vector data corresponding to different drying control stages to form corresponding stage optimal parameter vector dimension reduction data, including: determining the stage unit vector in the control parameter coordinate system corresponding to different drying control stages ; according to the stage unit vector and the stage multi-parameter related vector data corresponding to the drying control stage, the following dimension reduction information is extracted to form the corresponding stage optimal parameter vector dimension reduction data: determining the time point vector module of the different time point optimal parameter control vectors , wherein , represents the length of the time point optimal parameter control vector ; determining the time point vector angle of the same stage unit vector of the different time point optimal parameter control vectors , wherein , represents the dot product of the time point optimal parameter control vector and the stage unit vector ; determining the parameter control vector intersection point on the corresponding time point optimal parameter control vector in the reference plane perpendicular to the stage unit vector with the vector point of the stage unit vector as the center, and obtaining the time point vector reference rotation angle between the connection line of the parameter control vector intersection point and the reference circle vector on the reference plane ; collecting the time point vector module , the time point vector angle and the time point vector reference rotation angle corresponding to the different time point optimal parameter control vectors to form the corresponding stage optimal parameter vector dimension reduction data.

[0044] The feature extraction of the dimension reduction information is important for the completeness of the feature data analysis. Since the information is expressed in the form of a vector, the completeness of the feature extraction of the dimension reduction information is converted into the accuracy of the target vector position information. The three parameter information including the size of the vector, the included angle between the vector and the unit vector, and the relative rotation azimuth angle between the vector and the unit vector are extracted to accurately determine the accurate position of the target vector in the coordinate system. The combination of the drying control parameters corresponding to the three parameters is unique, so that the obtained dimension reduction feature information has rationality and accuracy. The extracted feature information only contains three parameter values based on the time parameter, which greatly reduces the complexity of data analysis compared with the analysis of the correlation of the original drying control parameters, and also retains the correlation information between different drying control parameters. The rationality, accuracy and completeness of the data analysis results are guaranteed while improving the analysis efficiency.

[0045] The time dimension correlation vector change analysis of the stage optimal parameter vector dimension reduction data corresponding to different drying control stages is performed to form the corresponding stage optimal parameter dimension reduction control data, including: establishing a corresponding stage dimension reduction parameter coordinate system based on the time point vector module, the time point vector angle, the time point vector reference rotation angle and the time length for different drying control stages; mapping the corresponding time point vector module , the time point vector angle and the time point vector reference rotation angle to the stage dimension reduction parameter coordinate system according to different time points, and performing fitting analysis on the time dimension parameters to form the corresponding stage optimal control parameter dimension reduction change function .

[0046] The change analysis of the correlation of the three vector parameter values also needs to consider the change of the parameters in the time dimension. Therefore, a four-dimensional coordinate system including the time parameter is established to express the correlation change data of the three vector parameter values, and reasonable fitting analysis is performed combined with the characteristics of the function to form a dimension reduction change function containing four parameters. This can ensure that the correlation between the stage control parameters can be accurately and reasonably expressed in the time dimension, providing an important data basis for subsequent applicability expansion analysis. The fitting analysis can be in the form of least squares or multiple power search with accuracy targets.

[0047] S3: Obtain object condition information of different types of drying objects, and combine corresponding optimal parameter dimension reduction control data to perform control parameter adjustment analysis on condition parameters to form condition change control parameter regulation data.

[0048] Obtaining object condition information of different types of drying objects, and combining corresponding optimal parameter dimension reduction control data to perform control parameter adjustment analysis on condition parameters to form condition change control parameter regulation data, comprising: determining object condition values of all object conditions corresponding to different types of drying objects according to different object condition information corresponding to different types of drying objects , i represents the number of different object condition information; clustering stage optimal control parameter dimension reduction change functions of different types of drying objects in different drying control stages according to optimal parameter dimension reduction control data corresponding to different types of drying objects to form a stage optimal control parameter dimension reduction change data set; performing control parameter adjustment analysis on different stage optimal control parameter dimension reduction change data sets in the following manner: extracting any one stage optimal control parameter dimension reduction change function and corresponding all object condition values , respectively labeled as stage reference parameter dimension reduction function and reference object condition value ; determining the change function difference of other stage optimal control parameter dimension reduction change functions and the stage reference parameter dimension reduction function and the condition difference value of corresponding object condition values and the reference object condition value , wherein , , z represents the number of remaining stage optimal control parameter dimension reduction change functions , and z = r-1; performing fitting analysis according to different change function differences and corresponding condition difference values of all different object conditions to determine the following stage condition-parameter reference change relationship: wherein, represents the target object stage optimal control parameter dimension reduction change function, represents the target condition difference value corresponding to the object condition numbered i, and , represents the target object condition value of the object condition numbered i of the target object, represents the stage condition parameter related factor corresponding to the object condition numbered i.

[0049] After the optimal parameter dimension reduction control data corresponding to different object conditions appearing in the historical data is obtained, a correlation analysis of the optimal parameter dimension reduction control data changing with the object conditions can be performed. The results of the analysis can not only be applied to the drying objects with the object condition combinations appearing in the history, but also can predict the parameter regulation of the drying objects with new object condition combinations. In the correlation analysis, the synergistic relationship between the changes of the vector parameters and the changes of the object conditions is established. Different drying control stages are performed. Based on any dimension reduction function, the differences between the object conditions and the corresponding dimension reduction functions of other different drying objects and the reference data are determined. Then, the different difference conditions obtained are fitted as discrete data to form the synergistic relationship between the differences of the condition objects relative to the reference data and the differences between the dimension reduction functions and the reference data. Here, the number of the power terms of the stage condition parameter correlation factors to be determined is determined according to the needs, so the product form of the stage condition parameter correlation factors and the corresponding target condition difference can also be expressed by a polynomial with multiple powers. In this way, the accuracy of the relationship can be improved. Of course, it is necessary to ensure that the difference data obtained is sufficient to determine the constant term of the power.

[0050] S4: Obtain target condition information of the target drying object, and determine corresponding target optimal parameter control data in combination with the condition change control parameter regulation data.

[0051] Obtaining target condition information of the target drying object and determining corresponding target optimal parameter control data in combination with the condition change control parameter regulation data includes: determining target object condition values of different condition objects according to the target condition information of the target drying object; determining target object stage optimal control parameter dimension reduction change functions corresponding to different drying control stages of the target drying object in combination with the stage-condition parameter reference change relationship formula according to all target object condition values of the target drying object; performing dimension elevation processing on the different target object stage optimal control parameter dimension reduction change functions corresponding to different drying control stages to determine corresponding target optimal parameter control data.

[0052] After the stage-condition-parameter reference change relationship formula is determined, the relationship formula can be used to reasonably analyze the parameter regulation of the target drying object corresponding to the new or historical condition object combinations. In different drying regulation stages, the dimension reduction function of the target drying object is determined by using the corresponding relationship formula. The dimension reduction function contains the numerical correlation information between different object conditions. The accurate prediction data can be obtained by performing dimension elevation processing on the correlation information.

[0053] The dimension reduction change function of the optimal control parameter corresponding to different target object stages in different drying control stages is processed in a dimension increasing manner to determine the corresponding target optimal parameter control data, including: according to the target object stage optimal control parameter dimension reduction change function corresponding to the different drying control stages of the target object, mapping the function in the control parameter coordinate system corresponding to the drying control stage, and performing single parameter data splitting in the time dimension for different stage control parameters to form a parameter regulation continuous change target function of the different stage control parameters with time; the parameter regulation continuous change target functions of all stage control parameters corresponding to the drying control stage are collected to form stage optimal parameter control data; and the stage optimal parameter control data corresponding to different drying control stages are collected to form target optimal parameter control data.

[0054] The dimension increasing processing of the dimension reduction function needs to map the vector parameter information involved in the function into the corresponding parameter coordinate system, so that the specific values of the different stage control parameters can be accurately determined due to the uniqueness of the vectors on the parameter coordinate system and the vector parameters of the dimension reduction function, and then the parameter value control information of all parameters in the entire drying control stage can be obtained.

[0055] The application also provides specific components of the system, which include a data acquisition unit for acquiring historical drying control data of different types of drying objects and target condition information of a target drying object; a feature analysis unit for extracting optimal parameter control information for different drying control stages according to the historical drying control data of different types of drying objects acquired by the data acquisition unit, forming optimal parameter control data corresponding to different types of drying objects, and performing dimension reduction analysis of multi-parameter control to form corresponding optimal parameter dimension reduction control data, and then combining object condition information of different types of drying objects to perform control parameter adjustment analysis of condition parameters to form condition change control parameter regulation data; and a parameter regulation analysis unit for determining corresponding target optimal parameter control data according to the target condition information of the target drying object acquired by the data acquisition unit and the condition change control parameter regulation data formed by the feature analysis unit.

[0056] In summary, the drying machine control method based on industrial self-adaptive parameter adjustment provided by the embodiments of the application has the following beneficial effects: The method collects historical drying control data of a plurality of drying objects of different types, determines optimal parameter control data corresponding to different drying control stages according to the energy consumption rate and operation time length of the control after clustering the data of the same object conditions, and uses the optimal parameter control data corresponding to the drying objects with different object conditions to analyze the correlation of the control parameters changing with the change of the object conditions, and the correlation analysis is assisted by parameter vectorization to realize dimension reduction, greatly improving the efficiency of data processing and reducing the difficulty of processing, and ensuring the rationality and accuracy of the analysis, and the data analysis result formed can reasonably predict the parameter regulation and control of the object conditions that have never appeared in history, providing a reasonable and accurate and effective data reference for efficient and energy-saving drying control of the target object, making the parameter regulation and control of the drying machine more intelligent, efficient and energy-saving.

[0057] In the embodiments of the present application, the indication can include direct indication and indirect indication, and can also include explicit indication and implicit indication. The information indicated by a certain information is referred to as to-be-indicated information, and in the specific implementation process, there are many ways to indicate the to-be-indicated information, for example but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or an index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship. The to-be-indicated information can also be indicated only by a part of the to-be-indicated information, and the other part of the to-be-indicated information is known or agreed in advance. For example, the indication of a specific information can also be achieved by means of the arrangement order of each information agreed in advance (for example, a protocol), thereby reducing the indication overhead to a certain extent. At the same time, the common part of each information can be identified and indicated uniformly, so as to reduce the indication overhead caused by separately indicating the same information.

[0058] In addition, the specific indication manner can also be various existing indication manners, for example but not limited to, the above-mentioned indication manners and various combinations thereof. The specific details of various indication manners can refer to the prior art, which will not be described herein. As known from the above, for example, when multiple information of the same type needs to be indicated, the indication manners of different information can be different. In the specific implementation process, the required indication manner can be selected according to the specific needs, and the selected indication manner is not limited in the embodiments of the present application, so that the indication manner involved in the embodiments of the present application should be understood as covering various methods that can enable the to-be-indicated party to know the to-be-indicated information.

[0059] It should be understood that the to-be-indicated information can be sent together as a whole or can be sent separately in multiple sub-information, and the sending period and / or sending occasion of the sub-information can be the same or different. The specific sending method is not limited in the embodiments of the present application. The sending period and / or sending occasion of the sub-information can be predefined, for example, predefined according to a protocol, or configured by the sending end device to the receiving end device by sending configuration information.

[0060] The "predefined" or "preconfigured" can be implemented by pre-storing corresponding codes, tables or other means for indicating related information in the device, and the specific implementation manner is not limited in the embodiments of the present application. The "storing" can mean storing in one or more memories. The one or more memories can be separately arranged or integrated in the encoder or decoder, processor or communication device. The one or more memories can be partially separately arranged and partially integrated in the decoder, processor or communication device. The type of the memory can be any form of storage medium, and the embodiments of the present application do not limit this.

[0061] The "protocol" involved in the embodiments of the present application can refer to a protocol family in the communication field, a standard protocol similar to the protocol family frame structure, or a related protocol applied to a future communication system, and the embodiments of the present application do not limit this.

[0062] In the embodiments of the present application, "when", "in the case of", "if" and the like all refer to that the device will make corresponding processing under certain objective conditions, and are not limited in time, and do not require the device to have a judgment action when implemented, nor mean that there are other limitations.

[0063] In the description of the embodiments of the present application, unless otherwise specified, " / " represents that the objects before and after the " / " are in an "or" relationship, for example, A / B can represent A or B; "and / or" in the embodiments of the present application is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone, wherein A and B can be singular or plural. In addition, in the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more than two. "At least one of the following" or the like means any combination of the items, including any combination of single item or multiple items. For example, at least one of a, b or c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, and c can be single or multiple. In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, "first", "second", and the like are used to distinguish the same items or similar items with basically the same function and role. Those skilled in the art can understand that "first", "second", and the like do not limit the quantity and execution order, and "first", "second", and the like do not necessarily mean different. At the same time, in the embodiments of the present application, "exemplary" or "for example" means to serve as an example, illustration or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, "exemplary" or "for example" is used to present the relevant concept in a specific manner, for understanding.

[0064] It should be understood that the processor in the embodiments of the present application can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0065] It should also be understood that the memory in the embodiments of the present application can be a volatile memory or a nonvolatile memory, or can include both volatile and nonvolatile memory. Among them, the nonvolatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, and not limitation, many forms of random access memory (RAM) can be used, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0066] The above-described embodiments can be implemented in whole or in part by software, hardware (such as a circuit), firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center through a wired (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. containing one or more available medium collections. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0067] It should be understood that the term "and / or" herein merely describes an association relationship of associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after it, but it can also represent an "and / or" relationship, which can be understood according to the context before and after it.

[0068] In this application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions means any combination of these items, including any combination of single item or multiple items. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0069] It should be understood that in various embodiments of the present application, the size of the sequence number of the above-described processes does not mean the order of execution, and the execution order of the processes should be determined according to their functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0070] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0071] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0072] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0073] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0074] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0075] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0076] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A dryer control method for adaptive tuning based on industrial grade, characterized by, The method comprises the following steps: Collecting historical drying control data of different types of drying objects, extracting optimal parameter control information for different drying control stages, and forming optimal parameter control data corresponding to different types of drying objects; Performing multi-parameter control dimension reduction analysis on the optimal parameter control data corresponding to different types of drying objects to form corresponding optimal parameter dimension reduction control data; Obtaining object condition information of different types of drying objects, and combining the corresponding optimal parameter dimension reduction control data to perform control parameter adjustment analysis for condition parameters to form condition change control parameter regulation data; Obtaining target condition information of a target drying object, and combining the condition change control parameter regulation data to determine corresponding target optimal parameter control data.

2. The dryer control method based on industrial grade adaptive tuning according to claim 1, wherein, The method comprises the following steps: Performing data clustering of object condition information on the historical drying control data of different types of drying objects to form different same-type object historical drying control data sets; Extracting same-type object stage drying control information corresponding to different drying objects in the same drying control stage from the same-type object historical drying control data set to form a same-type object stage drying control information set; Performing comparison analysis based on unit time energy consumption on different same-type object stage drying control information sets under the same-type object historical drying control data set to determine corresponding same-type object optimal drying control information; Collecting the same-type object optimal drying control information corresponding to different drying control stages under the same-type object historical drying control data set to form corresponding same-type object optimal parameter control data.

3. The dryer control method for adaptive tuning based on industrial grade according to claim 2, characterized in that, The method comprises the following steps: determining the phase control parameter values of the different phase control parameters corresponding to the different drying control stages for the different same-type drying object phase drying control information sets and the corresponding phase drying processing time length , n represents the number of different drying control stages, k represents the number of different phase control parameters corresponding to the drying control stage numbered n, and m represents the number of different same-type drying objects. for different same-type drying objects, according to the phase control parameter values of the corresponding different phase control parameters and the phase drying processing time length , determine the phase unit energy consumption values of the corresponding same-type objects ; According to different same type object stage unit energy consumption values And combined with corresponding stage drying processing time length The following way of comparative analysis determines the best drying control information of the same type object: the same type of object phase unit energy consumption value adjacent to the same type of object phase unit energy consumption value in descending order the corresponding phase drying processing time length When the difference between adjacent same type of object phase unit energy consumption values the corresponding phase drying processing time length When the difference between adjacent same type of object phase unit energy consumption values the larger same type of object phase unit energy consumption value The same type of object phase drying control information corresponding to the same type of object is determined as the best drying control information of the same type of object.

4. The dryer control method for industrial grade adaptive tuning based on, as claimed in claim 3, wherein, The method comprises the following steps: According to the same-type object optimal parameter control data of different drying control stages, determining the optimal stage control parameter value of different stage control parameters in the time dimension; Establishing corresponding stage multi-parameter correlation vector data according to the optimal stage control parameter value of all stage control parameters in different drying control stages; Performing parameter dimension reduction analysis on the stage multi-parameter correlation vector data corresponding to different drying control stages to form corresponding stage optimal parameter vector dimension reduction data; Performing time dimension correlation vector change analysis on the stage optimal parameter vector dimension reduction data corresponding to different drying control stages to form corresponding stage optimal parameter dimension reduction control data; The stage optimal parameter dimension reduction control data corresponding to different drying control stages is formed by collecting the stage optimal parameter dimension reduction control data corresponding to different drying control stages for different types of drying objects.

5. The dryer control method for industrial grade adaptive tuning based on, as claimed in claim 4, wherein, The stage optimal parameter dimension reduction control data corresponding to different drying control stages is formed by collecting the stage optimal parameter dimension reduction control data corresponding to different drying control stages for different types of drying objects. The control parameter coordinate system corresponding to different drying control stages is established according to the number of stage control parameters corresponding to different drying control stages. mapping the optimal stage control parameter values of the corresponding different stage control parameters at the same time point into the control parameter coordinate system to form a corresponding time point optimal parameter control vector r represents the number of different drying objects of different types, trn represents the time length value of the drying object numbered r at the different time points corresponding to the drying control stage numbered n. collecting the time point optimal parameter control vectors corresponding to all time points forming the stage multi-parameter correlation vector data corresponding to the dry control stage 6. The dryer control method for industrial grade adaptive tuning based on, as claimed in claim 5, wherein, The stage optimal parameter vector dimension reduction data corresponding to different drying control stages is formed by performing parameter dimension reduction analysis on the stage multi-parameter correlation vector data corresponding to different drying control stages. for different drying control phases, determining a phase unit vector in the corresponding control parameter coordinate system ; according to the phase unit vector corresponding to the drying control phase and the phase multi-parameter correlation vector data, the following dimension reduction information is extracted to form the corresponding phase optimal parameter vector dimension reduction data: optimal parameter control vector for different time points , determine time point vector module ; optimal parameter control vector for different time points , determine the time point vector angle of the phase unit vector ; optimal parameter control vector for different time points , determine the time point vector reference rotation angle of the phase unit vector ;​ set of different said time point optimal parameter control vectors corresponding said time point vector module said time point vector angle and said time point vector reference rotation angle forming corresponding said stage optimal parameter vector reduced dimension data.

7. The dryer control method for industrial grade adaptive tuning based on, as claimed in claim 6, wherein, The stage optimal parameter dimension reduction control data corresponding to different drying control stages is formed by performing time dimension correlation vector change analysis on the stage optimal parameter vector dimension reduction data corresponding to different drying control stages. The stage dimension reduction parameter coordinate system corresponding to different drying control stages is established by taking the time point vector, the time point vector angle, the time point vector reference rotation angle, and the time length as the reference. According to the corresponding time point vector module at different time points , the time point vector angle , and the time point vector reference rotation angle , map to the stage dimension reduction parameter coordinate system, and perform fitting analysis for the time dimension parameter to form the corresponding stage optimal control parameter dimension reduction change function .

8. The dryer control method for industrial grade adaptive tuning based on claim 7, wherein, The condition change control parameter regulation data is formed by collecting the object condition information of different types of drying objects and performing condition parameter control parameter adjustment analysis on the corresponding optimal parameter dimension reduction control data. According to the different object condition information corresponding to different types of drying objects, the object condition values of all object conditions corresponding to different types of drying objects are determined , i represents the number of different object condition information; According to the optimal parameter dimension reduction control data corresponding to different types of drying objects, the stage optimal control parameter dimension reduction change functions of different types of drying objects in different drying control stages are clustered , to form a stage optimal control parameter dimension reduction change data set; The control parameter adjustment analysis is performed on different stage optimal control parameter dimension reduction change data sets in the following manner: extracting a stage optimal control parameter reduced dimension variation function and all the corresponding object condition values , respectively denoted as stage reference parameter reduced dimension function and reference object condition values ; determining a change function of the reduced dimensionality of the optimal control parameters of the other stages a change function of the reduced dimensionality of the reference parameters of the stages a difference of the change functions and a corresponding object condition value a difference of the condition values from the reference object condition value a difference of the condition values from the reference object condition value z denotes the number of the change function of the reduced dimensionality of the optimal control parameters of the other stages and z = r - 1; According to different said change function difference And the corresponding condition difference of all different object conditions , The fitting analysis is carried out, and the following stage condition-parameter reference change relationship is determined.

9. The dryer control method for industrial grade adaptive tuning based on claim 8, wherein, The target optimal parameter control data is determined by collecting the target condition information of the target drying object and combining the condition change control parameter regulation data. The target object condition values of different condition objects are determined according to the target condition information of the target drying object. The target object stage optimal control parameter dimension reduction change function corresponding to different drying control stages of the target drying object is determined by combining the stage-condition parameter reference change relationship with all target object condition values of the target drying object. The target optimal parameter control data is determined by performing dimension reduction processing on different target object stage optimal control parameter dimension reduction change functions corresponding to different drying control stages.

10. The dryer control method based on industrial grade adaptive tuning according to claim 9, wherein, The target optimal parameter control data is determined by performing dimension reduction processing on different target object stage optimal control parameter dimension reduction change functions corresponding to different drying control stages. The parameter regulation continuous change target function of different stage control parameters changing with time is formed by mapping the function in the control parameter coordinate system corresponding to the drying control stage and performing single parameter data splitting in the time dimension for different stage control parameters according to the target object stage optimal control parameter dimension reduction change function corresponding to different drying control stages of the target object. The stage optimal parameter control data is formed by collecting the parameter regulation continuous change target function of all stage control parameters corresponding to different drying control stages. The target optimal parameter control data is formed by collecting the stage optimal parameter control data corresponding to different drying control stages.

Images