Mixer powder drying real-time detection method based on humidity sensor

Abstract

The invention relates to the technical field of control science, and provides a mixer powder drying real-time detection method based on a humidity sensor. The method comprises the following steps: monitoring humidity data of the inner wall of the mixing machine in real time based on a humidity sensor, and constructing a data twinborn model; evaluating the humidity grade, and judging whether the drying degree meets a threshold value or not; if not, efficiency compensation is carried out by using historical data, and parameters and credibility are determined; simulating a humidity rule, and constructing an optimization space; and powder drying is achieved through parameter optimization and optimization control. The technical problem that the powder drying quality stability is low due to the fact that powder drying control optimization cannot be rapidly debugged and determined under the powder drying scene that different material types change or process conditions change is solved, the humidity condition in the mixing machine is monitored in real time, different drying requirements are automatically met, and the quality of powder drying is improved. And repeated testing and debugging for each type of materials are not needed, the controllability of powder drying is improved, and the technical effects of powder drying quality are guaranteed.

Description

Technical Field

[0001] This application relates to the field of control science and technology, specifically to the field of intelligent control technology, and particularly to a real-time detection method for powder drying in a mixer based on a humidity sensor. Background Art

[0002] With the continuous development and innovation of modern industrial technologies, powder drying in a mixer, as a key link in many production processes, has a crucial impact on product quality and production efficiency. However, the existing drying detection optimizes powder drying control by directly using empirical functions in combination with the color and texture of the powder material in the mixer. It can achieve intelligent control of the powder material that has been dried in large quantities. Once the material type changes or the process conditions vary, the original empirical rules may no longer apply, and long-term drying debugging is required. Summary of the Invention

[0003] This application provides a real-time detection method for powder drying in a mixer based on a humidity sensor, aiming to solve the technical problem that in the powder drying scenario where different material types change or process conditions vary, it is impossible to quickly debug and determine the optimization of powder drying control, resulting in low quality stability of powder drying.

[0004] In view of the above problems, this application provides a real-time detection method for powder drying in a mixer based on a humidity sensor.

[0005] The real-time detection method for powder drying in a mixer based on a humidity sensor disclosed in this application includes: based on the humidity sensor, continuously monitoring the inner wall of the container of the target mixer to obtain real-time monitoring data, where the real-time monitoring data includes humidity acquisition data at M key positions on the inner wall of the target mixer; obtaining the monitoring working characteristic indexes of the humidity sensor and the operating working characteristic indexes of the target mixer, and constructing a data twin model of the mixer; based on the change trend of the real-time monitoring data, evaluating the humidity level corresponding to the target mixer, judging the degree of powder drying according to the humidity level, and comparing it with a preset powder drying threshold; if the degree of powder drying does not meet the preset powder drying threshold, based on the historical monitoring data of the humidity sensor, combining the monitoring working characteristic indexes of the humidity sensor and the operating working characteristic indexes of the target mixer for efficiency compensation, determining the efficiency compensation parameter and the compensation credibility; based on the data twin model of the mixer, simulating the humidity level law under different working conditions, constructing a drying optimization space, and using the efficiency compensation parameter and the compensation credibility as the optimization auxiliary variables of the drying optimization space; performing parameter optimization in the drying optimization space to obtain the best combination of process parameters, and optimizing the powder drying control of the target mixer.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: The above real-time detection method for powder drying of a mixer based on a humidity sensor monitors the humidity of the inner wall of the target mixer container in real time and collects humidity data at multiple key positions. These data not only reflect the humidity state inside the mixer but also provide basic information for optimizing the drying process. Subsequently, by understanding the monitoring characteristics of the humidity sensor and the operating characteristics of the mixer, a data twin model of the mixer is constructed. This model can simulate the actual operating state of the mixer, helping to more accurately understand the relationship between humidity changes and the degree of powder drying. Then, using the real-time monitoring data, the humidity level inside the mixer is evaluated, and based on this, the degree of powder drying is judged. If the drying degree does not reach the preset threshold, it means that the drying process needs to be adjusted. At this time, combining the historical data of the humidity sensor and the characteristic indexes of the mixer and the sensor, efficiency compensation is carried out to determine the compensation parameters and credibility. Then, using the data twin model to simulate the humidity change law under different working conditions, a drying optimization space is constructed. In the drying optimization space, taking the efficiency compensation parameters and compensation credibility as optimization variables, through parameter optimization, the best combination of process parameters is found. This method realizes the precise control of the powder drying process of the mixer through steps of real-time monitoring, modeling, evaluation, and optimization, improves the drying efficiency, and ensures the product quality.

[0007] The above description is only an overview of the technical solution of this application. In order to be able to more clearly understand the technical means of this application, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of this application more obvious and understandable, the specific embodiments of this application are specifically listed below. Brief Description of the Drawings

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0009] Figure 1 It is a schematic flowchart of the real-time detection method for powder drying of a mixer based on a humidity sensor in an embodiment. Detailed Embodiments

[0010] By providing a real-time detection method for powder drying of a mixer based on a humidity sensor in the embodiments of this application, the technical problem of low quality stability of powder drying caused by the inability to quickly debug and determine the optimization of powder drying control in powder drying scenarios where different material types change or process conditions vary is solved.

[0011] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0012] It should be noted that the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0013] Embodiment 1 As Figure 1 shown, the present application provides a real-time detection method for powder drying of a mixer based on a humidity sensor. The method includes: Based on the humidity sensor, the inner wall of the container of the target mixer is monitored in real time to obtain real-time monitoring data, where the real-time monitoring data includes humidity acquisition data at M key inner wall positions of the target mixer. With the continuous progress of technology and the expansion of industrial production scale, powder drying, as a key link in many production processes, its control accuracy and efficiency play a crucial role in the stability of product quality and the improvement of production efficiency.

[0014] In the embodiments of the present application, the system terminal monitors the inner wall humidity of the target mixer in real time based on the humidity sensor. During the monitoring process, the humidity sensor will collect humidity data at M key inner wall positions of the mixer, providing real-time monitoring data on the internal humidity status of the mixer to the system terminal. Here, M is an integer greater than 0. The obtained real-time monitoring data not only reflects the humidity change inside the mixer but also provides an important basis for the system terminal to accurately control the degree of powder drying. Through data collection, the working state of the mixer can be more accurately understood, ensuring the effectiveness and efficiency of the powder drying process.

[0015] Obtain the monitoring working characteristic indexes of the humidity sensor and the operation working characteristic indexes of the target mixer, and construct a data twin model of the mixer; In one embodiment, in order to more accurately grasp the state of the powder drying process of the mixer, the system terminal calibrates the humidity sensor to ensure accurate measurement. Through testing, key parameters such as the measurement range, accuracy, and response time of the sensor are determined, and the determined key parameters are sorted out to obtain the monitoring working characteristic indicators of the humidity sensor, which reflect the performance of the sensor in real-time monitoring. At the same time, the real-time monitoring data, such as rotation speed, power consumption, temperature distribution, etc., are processed and analyzed to extract information such as the operating state, working efficiency, and energy consumption of the mixer, and the extracted information is sorted out to obtain the operating working characteristic indicators of the target mixer. After obtaining the monitoring working characteristic indicators and the operating working characteristic indicators, the system terminal uses the operating working characteristic indicators of the target mixer to determine the physical principle of the humidity change inside the mixer, that is, to determine the moisture diffusion or the flow of humid air. Subsequently, based on the determined physical principle, a basic equation describing the humidity change inside the mixer is established. These equations are established based on partial differential equations or algebraic equations, and the choice of equation depends on the complexity of the actual situation and the accuracy requirements. Then, the boundary conditions inside the mixer are analyzed, including the boundary conditions in terms of temperature, humidity, air flow, etc. These boundary conditions are determined by the operating working characteristic indicators. Then, the determined basic equations and boundary conditions are integrated into a model equation set to describe the overall process of the humidity change inside the mixer, thereby constructing an initial mixer data twin model. Further, the system terminal uses the monitoring working characteristic indicators of the humidity sensor to compare and calibrate the actual monitoring data with the model output to ensure that the model output is consistent with the actual monitoring data. If the output results are consistent, the initial mixer data twin model is directly used as the mixer data twin model. Otherwise, the basic equations or boundary conditions are reset until the output results are consistent. The mixer data twin model can simulate the actual operating conditions of the mixer and provide an important basis for subsequent drying control optimization. Through this step, the actual situation of the powder drying process of the mixer can be grasped more accurately, laying a solid foundation for improving the drying effect and quality.

[0016] Based on the change trend of the real-time monitoring data, evaluate the humidity level corresponding to the target mixer, judge the powder drying degree according to the humidity level, and compare it with the preset powder drying threshold; In one embodiment, the system terminal performs time serialization on the real-time monitoring data and sets humidity evaluation features based on the serialized real-time monitoring data. Subsequently, the set humidity evaluation features are compared according to the internal humidity levels in different humidity ranges to evaluate the humidity level inside the current mixer. The humidity level can help the system terminal determine the dryness of the powder, that is, whether the moisture content in the powder has reached the expected standard. Then, the humidity judgment result is compared with a preset powder drying threshold to analyze whether the current dryness meets the production requirements. This step is an important link to ensure the drying quality of the powder. Through real-time comparison and adjustment, precise control of the powder drying process can be achieved.

[0017] Furthermore, the present application provides a method for evaluating the humidity level corresponding to the target mixer based on the change trend of the real-time monitoring data and judging the dryness of the powder according to the humidity level. The method further includes: Determine M monitoring time series data streams based on the M key inner wall positions; Perform change analysis of the minimum humidity unit through the M monitoring time series data streams and set the first humidity evaluation feature, where the first humidity evaluation feature includes a drying rate feature and a humidity change sensitivity feature; Preferably, the system terminal determines the M key inner wall positions according to the working principle of the mixer, the powder flow characteristics, and the expected humidity distribution law. The selection of these positions should ensure that the humidity conditions in different regions inside the mixer can be comprehensively reflected. Subsequently, the real-time monitoring data of the determined M key inner wall positions are collected, and the collected original humidity data are cleaned to extract the outliers, improving the quality and consistency of the data and providing a reliable data basis for subsequent humidity analysis. After preprocessing, the humidity data of each key position are arranged in time series to form M monitoring time series data streams. Each data stream represents the change of humidity over time at a key position, providing important data support for subsequent analysis and optimization. Then, a detailed analysis is performed on the M monitoring time series data streams, with particular attention paid to the relationship between the M monitoring time series data streams and the minimum humidity unit. Among them, the minimum humidity unit is determined by the accuracy of the humidity sensor and represents the smallest change in humidity that can be observed. During the analysis process, the system terminal calculates the humidity fluctuation frequency and the humidity fluctuation amplitude and sets the first humidity evaluation feature according to the calculation results. Among them, the drying rate feature is used to describe how fast the humidity changes over time and can help understand the drying efficiency of the powder inside the mixer. The humidity change sensitivity feature reflects the sensitivity of the humidity change within the minimum unit, which is of great significance for precisely controlling the drying process and avoiding over-drying or under-drying. Through the analysis of these two features, the humidity change situation on the inner wall of the mixer can be understood more comprehensively and deeply, providing strong support for the optimization of the subsequent drying process.

[0018] Based on the M monitored time series data streams, analyze the humidity change of the inner wall of the container at the same time, and set the second humidity evaluation feature, where the second humidity evaluation feature includes the relative humidity fluctuation feature and the humidity distribution feature. Preferably, the system terminal analyzes the humidity change of the inner wall of the container at the same time based on the monitored time series data streams obtained at M key positions. The core of the humidity change analysis of the inner wall of the container at the same time lies in comparing the humidity data at different positions at the same time point, so as to reveal the spatial distribution and its change characteristics of the humidity on the inner wall of the container. In this process, the system terminal first splits the M monitored time series data streams to obtain a humidity acquisition data set at N time nodes. Subsequently, data change analysis is performed based on the humidity acquisition data set at N time nodes, and the second humidity evaluation feature is set according to the analysis results. The second humidity evaluation feature includes the relative humidity fluctuation feature and the humidity distribution feature. The relative humidity fluctuation feature mainly reflects the difference degree and change rate of humidity between different positions at the same time, which helps to understand the uniformity and stability of the humidity inside the container. The humidity distribution feature describes the spatial distribution pattern of humidity on the inner wall of the container, such as whether there is an obvious humidity gradient or local high humidity area, which is of great significance for optimizing the drying process, avoiding humidity accumulation and ensuring product quality. Through the analysis of these two features, the dynamic change of the humidity on the inner wall of the container can be more comprehensively understood, providing strong support for formulating subsequent drying control strategies. For example, if it is found that the relative humidity fluctuates greatly or the humidity distribution is uneven in some areas, the drying parameters can be adjusted accordingly or the operation mode of the mixer can be optimized to achieve a more uniform and efficient drying effect.

[0019] Based on the first humidity evaluation feature and the second humidity evaluation feature, compare with the internal humidity grades in different humidity intervals to determine the humidity grade corresponding to the target mixer.

[0020] Preferably, the system terminal analyzes and extracts the first humidity evaluation feature and the second humidity evaluation feature to obtain the drying rate feature, the humidity change sensitivity feature, the relative humidity fluctuation feature, and the humidity distribution feature. Among them, the level of the drying rate can reflect the speed of humidity reduction in the mixer, which is one of the important bases for determining the humidity level. The humidity change sensitivity feature helps to understand the sensitivity of the mixer to humidity changes and further provides a reference for determining the humidity level. The relative humidity fluctuation feature can reflect the uniformity and stability of the humidity inside the mixer. The humidity distribution feature helps to identify whether there are local high-humidity areas or humidity gradients, providing an important basis for determining the humidity level. Subsequently, based on the features in multiple dimensions such as the analyzed drying rate, humidity change sensitivity, relative humidity fluctuation, and humidity distribution, and by referring to the predefined humidity level standard and according to the definitions and ranges in the standard, it is determined which humidity level the target mixer is currently in. These standards are usually formulated based on historical experience and industry standards and are used to divide the humidity level into different levels or intervals. The obtained humidity level comprehensively reflects the humidity condition inside the mixer, including multiple aspects such as the change trend, stability, and uniformity of humidity. The above process converts complex humidity data into an intuitive and understandable humidity level, which not only helps to quickly understand the humidity state of the mixer but also provides an important reference basis for subsequent humidity control and optimization adjustment. By determining the humidity level, a more targeted drying strategy can be formulated and adjusted to achieve more efficient and precise operation management of the mixer.

[0021] Furthermore, the present application provides a method for analyzing the change of the minimum humidity unit through the M monitored time series data streams and setting the first humidity evaluation feature. The method further includes: Determining the minimum humidity unit based on the monitoring accuracy of the humidity sensor; Based on the M monitored time series data streams, using the minimum humidity unit as a reference, calculating the humidity fluctuation frequency and the humidity fluctuation amplitude; Setting the first humidity evaluation feature through the humidity fluctuation frequency and the humidity fluctuation amplitude.

[0022] Optionally, the system terminal determines a minimum humidity unit according to the monitoring accuracy of the humidity sensor. This minimum humidity unit is the basis for subsequent humidity analysis and evaluation, ensuring the accuracy and reliability of the humidity data.

[0023] After obtaining the minimum humidity unit, the system terminal selects consecutive data points from the M monitored time series data streams. These data points cover a sufficient time range to reflect the humidity fluctuations. Subsequently, for each data point, it is determined whether it constitutes a complete humidity fluctuation cycle. A fluctuation cycle includes the rising and falling processes of humidity. Based on the minimum humidity unit, it can be judged whether the change in humidity value reaches or exceeds this unit, thereby determining a complete fluctuation cycle. Within the selected time range, the number of complete humidity fluctuation cycles is counted. This number is a direct indicator of the humidity fluctuation frequency. Then, the number of counted fluctuation cycles is divided by the selected time range to obtain the humidity fluctuation frequency per unit time. Next, within each complete humidity fluctuation cycle, the maximum and minimum humidity values are found. These values should be rounded based on the small humidity unit. Then, the peak value of each fluctuation cycle is subtracted from the valley value to obtain the humidity fluctuation amplitude of that cycle. Through the above process, the system terminal obtains the humidity fluctuation frequency and the humidity fluctuation amplitude. Among them, the humidity fluctuation frequency describes the number of times the humidity changes within a certain period of time, which reflects the speed of humidity change; while the humidity fluctuation amplitude describes the magnitude of the humidity change, that is, the maximum difference in humidity values during the fluctuation process.

[0024] After obtaining the humidity fluctuation frequency and the humidity fluctuation amplitude, the system terminal further sets the first humidity evaluation feature. The first humidity evaluation feature is a comprehensive description of the humidity change characteristics inside the mixer, which includes two key aspects: the change frequency and the change amplitude of humidity. Through this feature, the dynamic change characteristics of the humidity inside the mixer can be more intuitively understood, providing an important reference basis for subsequent humidity control and management. In summary, by determining the minimum humidity unit, calculating the humidity fluctuation frequency and the humidity fluctuation amplitude, and setting the first humidity evaluation feature, a solid foundation is laid for comprehensively evaluating the humidity condition inside the mixer.

[0025] Furthermore, the present application provides an analysis of the humidity change of the inner wall of the container at the same time based on the M monitored time series data streams, and sets the second humidity evaluation feature. The method further includes: Based on the M monitored time series data streams, data splitting is performed based on the time reference to obtain a humidity acquisition data set at N time nodes. Among them, each humidity acquisition data set includes the humidity acquisition data at M key inner wall positions; Based on the humidity acquisition data set at the N time nodes, data change analysis is performed to obtain data change characteristics. The data change characteristics include the humidity average value, the humidity maximum value, the humidity minimum value, and the humidity change rate within N - 1 time periods; Based on the data change characteristics, the second humidity evaluation feature is set.

[0026] Optionally, the system terminal determines an appropriate time reference according to actual needs and the required analysis precision. This time reference can be fixed, such as data points per hour, per day, or per week, or it can be dynamic, set according to the fluctuations of the data. Subsequently, the M monitored time series data streams are split according to the determined time reference. This means cutting the continuous data stream into multiple time segments, each segment corresponding to a moment node. During the splitting process, it is necessary to ensure that the data at each moment node is complete, that is, it contains the humidity data of all key positions on the inner wall of the mixer. After that, for each moment node, the humidity data of the M key positions on the inner wall at that moment is collected. Then, these humidity data are organized into a data set, which contains the humidity information of all key positions at that moment node. Then, the above process of splitting and forming the set is repeated for the entire time series data stream until humidity acquisition data sets at N moment nodes are obtained. These sets will cover the entire analysis time period and provide a comprehensive humidity data set.

[0027] After obtaining the humidity acquisition data sets, the system terminal first clarifies the time relationship between the N moment nodes and divides them into N - 1 time periods. Each time period corresponds to the change in humidity data between two adjacent moment nodes. Subsequently, for each time period, data change analysis is carried out. Specifically, for all moment nodes within this time period, the system terminal first extracts the humidity data of the corresponding key positions on the inner wall. Then, these data are averaged to obtain the average humidity value within this time period. This average value reflects the overall humidity level within this time period. Subsequently, within this time period, the humidity data of all moment nodes are compared to find the maximum humidity value and the minimum humidity value. These two values respectively represent the highest and lowest humidity levels within this time period and reflect the fluctuation range of humidity. After that, by comparing the humidity data at the start and end moments of this time period, calculating the difference between the humidity at the end moment and the humidity at the start moment, and then dividing by the time length of the time period, the humidity change rate per unit time is obtained. The humidity change rate reflects how fast the humidity changes over time. Through the above calculation process, the system terminal obtains four data change characteristics within this time period: the average humidity value, the maximum humidity value, the minimum humidity value, and the humidity change rate. Finally, the above process is repeated to analyze each of the N - 1 time periods one by one to obtain the data change characteristics of each time period. These characteristics will provide the system terminal with comprehensive information about the humidity change inside the mixer, helping to better understand the change trend and fluctuation of humidity and providing a basis for subsequent humidity control and management.

[0028] After obtaining the data change characteristics, the system terminal sets the second humidity evaluation feature based on these calculated data change characteristics. This feature is a further description of the humidity change characteristics inside the mixer, which combines the overall humidity level, fluctuation situation, and change trend, providing a more comprehensive and in-depth humidity evaluation for the system terminal. In summary, this process is to split, analyze the changes, and extract features from time-series data to finally obtain the second humidity evaluation feature, so as to more accurately understand the humidity condition inside the mixer.

[0029] If the dryness degree of the powder does not meet the preset powder dryness threshold, based on the historical monitoring data of the humidity sensor, combined with the monitoring working characteristic index of the humidity sensor and the operating working characteristic index of the target mixer, efficiency compensation is performed to determine the efficiency compensation parameter and compensation credibility. In one embodiment, if the dryness degree of the powder does not reach the preset dryness threshold, it means that the system terminal needs to adjust the drying process. At this time, the system terminal uses the past historical monitoring data of the humidity sensor, combines the monitoring working characteristic index of the humidity sensor and the operating working characteristic index of the mixer, constructs an efficiency compensation model, and uses the efficiency compensation model to perform efficiency compensation to obtain an implicit correlation compensation result including the efficiency compensation parameter and compensation credibility. The purpose of this is to find out the key factors affecting the drying efficiency, determine the corresponding compensation parameters to improve the drying efficiency, and at the same time evaluate the credibility of the obtained compensation parameters to ensure the effectiveness and reliability of the adjustment measures. Through this step, the powder drying process can be more accurately optimized to ensure product quality and production efficiency.

[0030] Further, the present application provides efficiency compensation based on the historical monitoring data of the humidity sensor, combined with the monitoring working characteristic index of the humidity sensor and the operating working characteristic index of the target mixer to determine the efficiency compensation parameter and compensation credibility. The method further includes: Perform cross-correlation analysis based on the monitoring working characteristic index of the humidity sensor and the operating working characteristic index of the target mixer to obtain cross-correlation indexes. Preferably, the system terminal first obtains the error of the humidity sensor, and then through cross-correlation analysis, explores whether there is an association or mutual influence among the monitoring working characteristic indicators, the operating working characteristic indicators, and the error of the humidity sensor, and obtains the first cross-correlation index. Subsequently, the monitoring working characteristic indicators and the operating working characteristic indicators are combined with the working state of the mixer, and cross-correlation analysis is performed again to obtain the second cross-correlation index. After that, through the index fusion analysis of the first cross-correlation index and the second cross-correlation index, the cross-correlation index is obtained. The cross-correlation index can quantitatively describe the degree of mutual influence between the humidity sensor and the operation of the mixer. For example, whether the change in the rotation speed of the mixer will cause fluctuations in the humidity value monitored by the humidity sensor, or whether the humidity change monitored by the humidity sensor will affect the operating efficiency of the mixer. These cross-correlation indexes not only help the system terminal better understand the relationship between humidity and the operation of the mixer, but also provide important reference bases for subsequent humidity control, mixer optimization, etc. Generally speaking, performing cross-correlation analysis based on the monitoring working characteristic indicators of the humidity sensor and the operating working characteristic indicators of the target mixer can help the system terminal reveal the internal connection between the two, and provide strong support for the optimized operation of the mixer and the effective control of humidity.

[0031] Based on the cross-correlation index, an efficiency compensation model is established, and the efficiency compensation model is used to correct the implicit association compensation between the error of the humidity sensor and the working state of the target mixer; Preferably, the system terminal establishes an efficiency compensation model based on cross - correlation indicators for the purpose of correcting potential hidden correlations between humidity sensor errors and the working state of the target mixer. Specifically, in practical applications, humidity sensors may be affected by various factors, such as environmental factors and equipment aging, resulting in errors in the humidity data they monitor. At the same time, the working state of the mixer may also affect the monitoring results of the humidity sensor. For example, changes in the mixer's rotation speed, temperature, etc. may lead to uneven humidity distribution or inaccurate sensor readings. After obtaining cross - correlation indicators that can quantitatively describe the relationship between the humidity sensor and the mixer operation through cross - correlation analysis, the system terminal constructs an efficiency compensation model. Specifically, the system terminal first determines the inputs of the model, namely the original measurement data of the humidity sensor, the working state data of the target mixer, and the cross - correlation indicators. Then it determines the outputs of the model: the corrected efficiency compensation parameters and compensation credibility. Subsequently, according to the nature of the cross - correlation indicators and the characteristics of the data, the model structure is determined. For example, if the relationship between the cross - correlation indicator and the humidity sensor error is relatively simple and linear, a linear regression model is selected; if the relationship is slightly more complex and not completely non - linear, a polynomial regression model is selected. Specifically, taking the linear regression model as an example, the system terminal takes the error of the humidity sensor as the dependent variable, and the working state data of the mixer and the original data of the humidity sensor as independent variables to construct a linear regression function, and integrates this function into the linear regression model to construct an initial efficiency compensation model. Then, the obtained cross - correlation indicators are used as model constraints for the initial efficiency compensation model and added to the initial efficiency compensation model. These indicators reflect the degree of correlation between humidity sensor errors and the mixer working state, and can help the model more accurately predict and correct humidity data. Then, a sample monitoring data set is used to train the initial efficiency compensation model. During the training process, the initial efficiency compensation model will learn how to predict the humidity sensor error based on input features (including cross - correlation indicators), and obtain efficiency compensation parameters and compensation credibility according to the prediction results. Finally, a validation data set is used to verify the performance of the initial efficiency compensation model. By comparing the predicted values and actual values of the initial efficiency compensation model, the correction effect of the model on humidity sensor errors is evaluated. If the effect is not good, the initial efficiency compensation model is optimized, such as adjusting the model parameters or reconstructing the linear regression function, until there is no obvious difference between the predicted values generated by the initial efficiency compensation model and the actual values. The trained initial efficiency compensation model is then used as the efficiency compensation model. The efficiency compensation model can comprehensively consider the errors of the humidity sensor and the working state of the mixer, correct and compensate the monitoring data of the humidity sensor, help the system terminal more accurately obtain the humidity information inside the mixer, and reduce data deviation caused by sensor errors and changes in the mixer working state. This is of great significance for subsequent humidity control, mixer optimization, and product quality assurance, etc.In summary, the efficiency compensation model established based on the cross - correlation index is an efficient tool that can correct the implicit relationship between the humidity sensor error and the working state of the target mixer, improve the accuracy and reliability of humidity monitoring, and provide strong support for the operation optimization of the mixer and the improvement of product quality.

[0032] Based on the efficiency compensation model, combined with the historical monitoring data of the humidity sensor, efficiency compensation is performed to obtain the implicit relationship compensation result, and the implicit relationship compensation result includes an efficiency compensation parameter and a compensation credibility.

[0033] Preferably, the system terminal uses the already constructed efficiency compensation model and combines the historical monitoring data of the humidity sensor to perform efficiency compensation. Efficiency compensation means adjusting the data of the humidity sensor through the model to eliminate the implicit influence of the working state of the mixer on the humidity data. During the compensation process, the efficiency compensation model will use the cross - correlation index to identify and correct the errors in the humidity data according to the historical data of the humidity sensor and the working state data of the mixer, and generate the implicit relationship compensation result. The implicit relationship compensation result includes an efficiency compensation parameter and a compensation credibility. The efficiency compensation parameter is the specific value calculated by the efficiency compensation model during the compensation process, reflecting the degree of association between the humidity sensor error and the working state of the mixer. These parameters can help understand the degree and manner in which the humidity sensor data is affected by the working state of the mixer. The compensation credibility is an evaluation of the reliability of the compensation result, which is evaluated based on the fitting degree of the efficiency compensation model to the historical data and the verification result, and is used to indicate the accuracy and credibility of the compensation result. The level of compensation credibility will directly affect the degree of trust and the usage method of the compensation result. In summary, after performing efficiency compensation based on the efficiency compensation model combined with the historical monitoring data of the humidity sensor, the implicit relationship compensation result can be obtained, including the efficiency compensation parameter and the compensation credibility. These results will provide strong support for the system terminal to more accurately understand the implicit relationship between the humidity sensor data and the working state of the mixer.

[0034] Furthermore, the present application provides a method for performing cross - correlation analysis based on the monitoring working characteristic index of the humidity sensor and the operation working characteristic index of the target mixer to obtain a cross - correlation index. The method further includes: Set an error correction factor based on the error of the humidity sensor; Perform one - way cross - correlation analysis based on the monitoring working characteristic index of the humidity sensor and the operation working characteristic index of the target mixer with the error correction factor to obtain a first cross - correlation index; Optionally, based on the error of the humidity sensor, the system terminal first sets an error correction factor. The purpose of this correction factor is to quantify the measurement error of the humidity sensor for subsequent analysis and compensation. Subsequently, an error correction component is randomly extracted from the error correction factor. This error correction component provides the system terminal with a direction for error correction. Then, the monitoring working characteristic indicators and the operating working characteristic indicators are paired in correlation for the same time period. Next, a one-way cross-correlation analysis is performed based on the results of the same-time-period correlation pairing and the error correction component. The one-way cross-correlation analysis aims to find potential hidden correlations between the humidity sensor error and the working state of the target mixer. Through this analysis, a first cross-correlation index can be obtained, which can quantify the degree of correlation between the two and provides an important basis for constructing the subsequent efficiency compensation model and correcting the humidity data.

[0035] Based on the working state of the target mixer, set a working state correction factor; Based on the monitoring working characteristic indicators of the humidity sensor and the operating working characteristic indicators of the target mixer, perform a one-way cross-correlation analysis with the working state correction factor to obtain a second cross-correlation index; Optionally, based on the working state of the target mixer, the system terminal sets a working state correction factor. The main role of the working state correction factor is to quantify the possible impact of the differences in the working state of the mixer on the humidity sensor data, so as to more accurately analyze the correlation between the working state of the mixer and the humidity sensor data. Subsequently, using the method of obtaining the first cross-correlation index mentioned above, analyze in combination with the monitoring working characteristic indicators of the humidity sensor and the operating working characteristic indicators of the target mixer. Then, using the set working state correction factor, perform a one-way cross-correlation analysis on the monitoring working characteristic indicators of the humidity sensor and the operating working characteristic indicators of the mixer to deeply explore how the change in the working state of the mixer affects the monitoring data of the humidity sensor and find potential hidden correlations between the two. Through the one-way cross-correlation analysis, a second cross-correlation index can be obtained, which can quantify the degree of correlation between the working state of the mixer and the humidity sensor data.

[0036] Perform index fusion analysis through the first cross-correlation index and the second cross-correlation index to obtain a cross-correlation index.

[0037] Optionally, after obtaining the first cross-correlation index and the second cross-correlation index, the system terminal performs index fusion analysis. Index fusion analysis is to organically combine the two indexes to obtain a cross-correlation index that comprehensively reflects the implicit correlation degree between the humidity sensor error and the working state of the target mixer. In index fusion analysis, the system terminal first standardizes the first cross-correlation index and the second cross-correlation index to eliminate the deviation caused by different dimensions or numerical ranges, so that they have the same comparison basis in the fusion process. Subsequently, according to historical experience, weight allocation is performed on the standardized first cross-correlation index and the second cross-correlation index. The allocated weights represent the importance degree of each index in the comprehensive evaluation and reflect the influence size of each index on the cross-correlation index. When the weights are determined, the system terminal multiplies the values of the first cross-correlation index and the second cross-correlation index by the corresponding weights, then adds the product results and divides by 2. In this way, the system terminal organically fuses the information of the first cross-correlation index and the second cross-correlation index to obtain a cross-correlation index that comprehensively reflects the implicit correlation degree between the humidity sensor error and the working state of the target mixer. This index provides a more comprehensive and accurate perspective for the system terminal to understand the implicit correlation between the humidity sensor and the target mixer, and provides key support for the subsequent construction of the efficiency compensation model and the correction of humidity data.

[0038] Furthermore, the present application provides a method for performing one-way cross-correlation analysis based on the monitoring working characteristic index of the humidity sensor, the operating working characteristic index of the target mixer, and the error correction factor to obtain a first cross-correlation index. The method further includes: Randomly select a first error correction component from the error correction factors; Use the monitoring working characteristic index of the humidity sensor as the independent variable and the operating working characteristic index of the target mixer as the dependent variable, and perform correlation pairing in the same time period to obtain a first one-way cross-correlation index; Perform one-way cross-correlation analysis based on the first error correction component and the first one-way cross-correlation index to obtain a first cross-correlation index.

[0039] Optionally, the system terminal first analyzes the role of each error correction factor. Different correction factors compensate for different types of errors or errors under specific conditions. Understanding the role of these factors helps to more accurately select the appropriate correction component. Subsequently, on the basis of ensuring the understanding of each correction factor, a random method is used to select an error correction component as the first error correction component. This component will be used for subsequent cross-correlation analysis to help the system terminal more accurately understand the error situation of the humidity sensor.

[0040] After obtaining the first error correction component, the system terminal takes the monitoring working characteristic indexes of the humidity sensor as independent variables and the operating working characteristic indexes of the target mixer as dependent variables. For the monitoring working characteristic index values at each time point, the corresponding operating working characteristic index values are found to form one-to-one paired data. Subsequently, the monitoring working characteristic indexes in each pair of data are added together and then divided by the number of paired data to obtain the mean value of the monitoring working characteristic indexes. Similarly, the mean value of the operating working characteristic indexes is calculated using the same method. Then, the difference between each pair of monitoring working characteristic indexes and operating working characteristic indexes and their respective means is calculated, and then the difference between each pair of monitoring working characteristic indexes and the difference between the operating working characteristic indexes are multiplied, and the products calculated for all paired data are added together and then divided by the number of paired data to obtain the covariance of the paired data. Then, the Pearson correlation coefficient calculation formula is introduced to calculate the first unidirectional cross-correlation index. This index will reflect the linear correlation between the monitoring data of the humidity sensor and the operating state of the target mixer, and its value is between 0 and 1. The closer the absolute value is to 1, the stronger the correlation.

[0041] After completing the correlation pairing, the system terminal evaluates the nature of the first error correction component. For example, the magnitude, sign, and trend of change over time of the first error correction component. This will help understand how the error correction process affects the relationship between variables. Similarly, the strength and direction of the first unidirectional cross-correlation index are analyzed. A higher value indicates a stronger unidirectional influence, and positive and negative values indicate positive and negative influences respectively. Subsequently, combining the first error correction component and the first unidirectional cross-correlation index, a cross-correlation analysis is carried out, that is, observing whether the change trends of the two are consistent. If the change of the first error correction component is consistent with the change trend of the first unidirectional cross-correlation index, this indicates that there is an association between the error correction process and the unidirectional influence. Then, using the same method as calculating the first unidirectional cross-correlation index above, the first cross-correlation index is calculated. This index will quantify the degree of association between the first error correction component and the first unidirectional cross-correlation index, and provide a quantitative perspective for the system terminal to evaluate the implicit association degree between the humidity sensor error and the operating state of the target mixer, providing an important reference for subsequent efficiency and data correction work.

[0042] Based on the data twin model of the mixer, simulate the humidity level law under different working conditions, construct a drying optimization space, and use the efficiency compensation parameter and compensation credibility as the optimization auxiliary variables of the drying optimization space; In one embodiment, the system terminal sets different operating conditions according to actual requirements. For example, different material types, humidity requirements, production speeds, etc. Then, using the constructed data twin model of the mixer, it simulates the operation process of the mixer under these different operating conditions, especially paying attention to the change law of the humidity level. Subsequently, it analyzes the simulation results of the data twin model of the mixer, extracts the change trends and laws of the humidity level under different operating conditions, and identifies the key factors affecting the humidity level, such as material humidity, mixing time, mixing speed, etc. After that, based on the analysis results of the humidity level law, it determines the objectives and constraints of drying optimization, and uses the efficiency compensation parameter and compensation credibility as optimization auxiliary variables to construct a drying optimization space. The drying optimization space is used to explore how to achieve the best drying effect under various working conditions. In this optimization space, the efficiency compensation parameter and compensation credibility, as important optimization auxiliary variables, can guide the system terminal on how to adjust the drying parameters under different operating conditions to optimize the drying process. In this way, it is possible to more comprehensively understand the change law of the drying process and find the most suitable drying solution for the current operating conditions, thereby improving the drying efficiency and quality.

[0043] Parameter optimization is carried out in the drying optimization space to obtain the optimal combination of process parameters and optimize the powder drying control of the target mixer.

[0044] In one embodiment, in the constructed drying optimization space, the system terminal first clarifies the objectives of drying optimization, such as achieving a specific humidity level, improving drying efficiency, reducing energy consumption, etc. Subsequently, according to the simulation results of the data twin model of the mixer, it determines the key parameters affecting the drying effect, such as temperature, humidity, rotation speed, material flow rate, etc. Then, it sets reasonable value ranges for these key parameters based on historical experience to ensure that the optimization process is carried out within the feasible region. After that, the system terminal calls the drying optimization space and performs iterative search according to the set optimization objectives and parameter ranges. In each iteration, the drying optimization space generates a set of parameter combinations and uses the twin model for simulation evaluation to calculate indicators such as the humidity level and drying efficiency under this combination. Then, according to the simulation evaluation results, it calculates the credibility value of each parameter combination to evaluate its pros and cons. After multiple iterative searches, the drying optimization space will converge to an optimal solution or a set of relatively optimal solutions, that is, the optimal combination of process parameters. When the optimal combination of process parameters is determined, the system terminal applies the obtained optimal process parameters to the powder drying control of the target mixer, thereby optimizing the drying process. This can not only improve the drying efficiency, ensure product quality, but also reduce unnecessary energy consumption.

[0045] In summary, the embodiments of the present application at least have the following technical effects: In the embodiment of the present application, a humidity sensor is used to monitor the humidity condition of the inner wall of the target mixer container in real time, obtain humidity acquisition data at key positions, and establish a data twin model of the mixer. By monitoring the change trend of the monitored data, the humidity level of the mixer is evaluated, and the powder drying degree is judged according to the humidity level, and compared with the preset powder drying threshold. If the drying degree does not meet the preset threshold, efficiency compensation is performed using historical monitoring data and working characteristic indicators to determine compensation parameters and compensation credibility. Then, based on the data twin model of the mixer, a drying optimization space is constructed, and parameter optimization is performed in this space to obtain the optimal process parameter combination. In addition, the change analysis of the minimum humidity unit is performed by monitoring the time series data stream, and the first humidity evaluation feature is set. At the same time, the humidity change analysis of the inner wall of the container is performed, and the second humidity evaluation feature is set. Finally, a correction factor is set using the error and working state of the humidity sensor, and one-way cross-correlation analysis is performed to obtain the cross-correlation index. Through the above steps, the real-time monitoring, evaluation, compensation, and optimization of the powder drying process of the mixer are realized, improving production efficiency and product quality. These technical effects jointly solve the technical problem that in the powder drying scenario where the types of different materials change or the process conditions change, it is impossible to quickly debug and determine the optimization of powder drying control, resulting in low quality stability of powder drying, and realize the technical effects of real-time monitoring of the humidity condition in the mixer, automatically adapting to different drying requirements, without repeatedly testing and debugging for each type of material, improving the controllability of powder drying, and ensuring the quality of powder drying.

[0046] It should be noted that the above sequence of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above description of specific embodiments of this specification is given. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be executed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require the specific order and continuous sequence shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0047] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the protection scope of the present application.

[0048] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A real-time detection method for powder drying in a mixer based on a humidity sensor, characterized in that, The method includes: Based on a humidity sensor, the inner wall of the container of the target mixer is monitored in real time to obtain real-time monitoring data, and the real-time monitoring data includes humidity acquisition data at M key positions on the inner wall of the target mixer; Obtain the monitoring working characteristic indexes of the humidity sensor and the operating working characteristic indexes of the target mixer, and construct a data twin model of the mixer; Based on the change trend of the real-time monitoring data, evaluate the humidity level corresponding to the target mixer, judge the powder drying degree according to the humidity level, and compare it with a preset powder drying threshold; If the powder drying degree does not meet the preset powder drying threshold, based on the historical monitoring data of the humidity sensor, combine the monitoring working characteristic indexes of the humidity sensor and the operating working characteristic indexes of the target mixer to perform efficiency compensation, and determine the efficiency compensation parameter and compensation credibility; Based on the data twin model of the mixer, simulate the humidity level law under different working conditions, construct a drying optimization space, and use the efficiency compensation parameter and compensation credibility as the optimization auxiliary variables of the drying optimization space; Perform parameter optimization in the drying optimization space, obtain the optimal process parameter combination, and optimize the powder drying control of the target mixer.

2. The real-time detection method for drying of mixer powder based on a humidity sensor according to claim 1, characterized in that, Based on the change trend of the real-time monitoring data, evaluate the humidity level corresponding to the target mixer, and judge the powder drying degree according to the humidity level. The method includes: Based on the M key positions on the inner wall, determine M monitoring time series data streams; Perform a change analysis of the minimum humidity unit through the M monitoring time series data streams, and set a first humidity evaluation feature, where the first humidity evaluation feature includes a drying rate feature and a humidity change sensitivity feature; Perform an analysis of the humidity change of the inner wall of the container at the same time through the M monitoring time series data streams, and set a second humidity evaluation feature, where the second humidity evaluation feature includes a relative humidity fluctuation feature and a humidity distribution feature; Through the first humidity evaluation feature and the second humidity evaluation feature, compare with the internal humidity levels in different humidity intervals to determine the humidity level corresponding to the target mixer.

3. The real-time detection method for drying of mixer powder based on a humidity sensor according to claim 2, wherein Perform a change analysis of the minimum humidity unit through the M monitoring time series data streams, and set a first humidity evaluation feature. The method includes: Based on the monitoring accuracy of the humidity sensor, determine the minimum humidity unit; Based on the M monitoring time series data streams, use the minimum humidity unit as a reference to calculate the humidity fluctuation frequency and humidity fluctuation amplitude; Set a first humidity evaluation feature through the humidity fluctuation frequency and humidity fluctuation amplitude.

4. The real-time detection method for drying of mixer powder based on a humidity sensor according to claim 2, characterized in that, Perform an analysis of the humidity change of the inner wall of the container at the same time through the M monitoring time series data streams, and set a second humidity evaluation feature. The method includes: Based on the M monitoring time series data streams, perform data splitting based on a time reference to obtain a humidity acquisition data set at N time nodes, where each humidity acquisition data set includes humidity acquisition data at M key positions on the inner wall; Perform data change analysis on the humidity acquisition data set based on the N time nodes to obtain data change characteristics, where the data change characteristics include the humidity average value, humidity maximum value, humidity minimum value, and humidity change rate within N - 1 time periods; Set the second humidity evaluation feature based on the data change characteristics.

5. The real-time detection method for drying of mixer powder based on a humidity sensor according to claim 1, characterized in that, Based on the historical monitoring data of the humidity sensor, combine the monitoring working characteristic indicators of the humidity sensor and the operating working characteristic indicators of the target mixer to perform efficiency compensation, and determine the efficiency compensation parameter and compensation credibility. The method includes: Perform cross - correlation analysis based on the monitoring working characteristic indicators of the humidity sensor and the operating working characteristic indicators of the target mixer to obtain cross - correlation indicators; Based on the cross - correlation indicators, establish an efficiency compensation model, where the efficiency compensation model is used to correct the implicit correlation compensation between the error of the humidity sensor and the working state of the target mixer; Based on the efficiency compensation model, combine the historical monitoring data of the humidity sensor to perform efficiency compensation, and obtain the implicit correlation compensation result, where the implicit correlation compensation result includes the efficiency compensation parameter and compensation credibility.

6. The real-time detection method for drying of mixer powder based on a humidity sensor according to claim 5, wherein Perform cross - correlation analysis based on the monitoring working characteristic indicators of the humidity sensor and the operating working characteristic indicators of the target mixer to obtain cross - correlation indicators. The method includes: Set an error correction factor based on the error of the humidity sensor; Perform one - way cross - correlation analysis with the error correction factor based on the monitoring working characteristic indicators of the humidity sensor and the operating working characteristic indicators of the target mixer to obtain the first cross - correlation indicator; Set a working state correction factor based on the working state of the target mixer; Perform one - way cross - correlation analysis with the working state correction factor based on the monitoring working characteristic indicators of the humidity sensor and the operating working characteristic indicators of the target mixer to obtain the second cross - correlation indicator; Perform index fusion analysis through the first cross - correlation indicator and the second cross - correlation indicator to obtain cross - correlation indicators.

7. The real - time detection method for powder drying of a mixer based on a humidity sensor according to claim 6. Perform one - way cross - correlation analysis with the error correction factor based on the monitoring working characteristic indicators of the humidity sensor and the operating working characteristic indicators of the target mixer to obtain the first cross - correlation indicator. The method includes: Randomly select the first error correction component in the error correction factor; Use the monitoring working characteristic indicators of the humidity sensor as independent variables and the operating working characteristic indicators of the target mixer as dependent variables to perform correlation pairing in the same time period to obtain the first one - way cross - correlation indicator; Perform one - way cross - correlation analysis based on the first error correction component and the first one - way cross - correlation indicator to obtain the first cross - correlation indicator.

Images