Data management method and system for industrial internet of things

Abstract

The present application is suitable for the technical field of industrial internet of things intelligent control and material drying process optimization, and provides a data management method and system of industrial internet of things, which comprises: obtaining raw material type information of current batch of drying raw materials, extracting a plurality of target local historical data from historical drying data, which belong to the same type as the current batch of drying raw materials and have gradually increasing upstream storage time length, and extracting the corresponding current previous evaporation average rate sequence. Through the construction of a dynamic response recognition mechanism based on the influence of upstream storage time length, combined with the double-factor model of average slope deviation amplitude and stability deviation amplitude of the previous evaporation average rate sequence, the present application first realizes the self-adaptive correction and regulation of the initial temperature of hot air in the drying process.

Description

Technical Field

[0001] This invention belongs to the field of industrial Internet of Things (IoT) intelligent control and material drying process optimization technology, and particularly relates to an industrial IoT data management method and system. Background Technology

[0002] Currently, in the drying process of industrial materials, especially in the processing of intermediate raw materials sensitive to drying, such as lithium electrode sheets and ceramic powders, a common approach is to use pre-set drying process parameters based on the material type. The initial hot air temperature is the core control variable, usually given directly by empirical formulas or standard parameters. This approach fails to consider the evolution of the material's state during actual production due to non-process factors such as temporary storage and retention. Particularly in the early stages of drying, the evaporation rate often exhibits significant fluctuations and variability due to these historical factors. However, traditional control methods cannot dynamically identify and respond to these non-process disturbances affecting drying behavior, easily leading to mismatch in the initial drying stage.

[0003] While some existing industrial drying systems incorporate process data acquisition and feedback control, their focus is primarily on achieving moisture content targets or closed-loop temperature and humidity control in the mid-to-late stages, with a weak response mechanism for the early drying phase. In particular, changes in the raw material's moisture content can lead to problems such as evaporation lag, surface hardening, and localized rate deviations in the early evaporation process, affecting subsequent drying uniformity and overall quality. Existing systems lack the ability to identify the dynamic indicator of "average evaporation rate in the early stages" and cannot adjust parameters based on storage history and evaporation deviation trends, resulting in significant uncertainties in process control (initial hot air temperature). Summary of the Invention

[0004] The purpose of this invention is to provide a data management method and system for the Industrial Internet of Things (IIoT), aiming to solve the problems mentioned in the background art.

[0005] This invention is implemented as follows: a data management method for the Industrial Internet of Things (IIoT), the method comprising:

[0006] S100. Obtain the raw material type information of the current batch of dried raw materials, extract the historical drying data of the same type as the current batch of dried raw materials and the target local historical data with gradually increasing upstream storage time, and extract the corresponding current previous average evaporation rate sequence.

[0007] S200. Analyze whether the increase in upstream storage time has caused a systematic evolution of the current trend of the average evaporation rate sequence. If so, select drying samples from historical drying data that have a higher drying effect than the preset threshold during the overall drying process, and determine the raw material type with the largest proportion in these drying samples as the standard raw material type.

[0008] S300: Obtain all drying samples corresponding to the standard raw material type, and select reference samples that correspond to the upstream storage time of the current batch of dried raw materials, and extract the corresponding reference early-stage average evaporation rate sequence.

[0009] S400. Calculate the average slope deviation and stability deviation of the current previous average evaporation rate sequence compared to the reference previous average evaporation rate sequence.

[0010] S500: Obtain the initial temperature of the hot air in the current drying process, and correct the initial temperature of the hot air based on the deviation of the average slope and the deviation of the stability, so as to achieve dynamic adjustment of the evaporation process affected by the upstream storage time.

[0011] The dynamic adjustment achieves predictive correction of the initial hot air temperature by analyzing the historical trend correlation between upstream storage time and the previous average evaporation rate sequence (such as the correlation of linear regression R²≥0.8), combined with the two-factor deviation calculation between the current sequence and the reference sequence, rather than passive feedback adjustment based on a single time point rate.

[0012] In industrial practice, a single slope correction may result in 'correct trend but localized over-drying / over-wetting' (e.g., the rate trend is correct but sudden fluctuations are not suppressed); a single stability correction may 'suppress fluctuations but the trend deviates from the standard' (e.g., small rate fluctuations but overall slower). This invention addresses this issue through... and The weighting of temperature allows it to respond simultaneously to both 'macroeconomic trends' and 'microeconomic fluctuations', a synergistic mechanism that cannot be achieved through a single factor.

[0013] As a further limitation of the technical solution of the present invention, the upstream storage time refers to the time interval between the start time of temporary storage of the current batch of dried raw materials after the completion of the previous processing step and the start time of entering the drying step.

[0014] As a further limitation of the technical solution of this invention, the step of analyzing whether the increase in upstream storage time causes a systematic evolution of the current trend of the average evaporation rate sequence in the early stage, and if so, selecting several drying samples from historical drying data whose raw material drying effect is higher than a preset threshold during the overall drying process, and determining the raw material type with the largest proportion among these drying samples as the standard raw material type includes:

[0015] The analysis examines whether the current average evaporation rate sequence corresponding to the local historical data of the aforementioned targets shows a continuous increasing trend as the upstream storage time gradually increases.

[0016] When the above trend change characteristics are confirmed, the historical drying data is analyzed and several drying samples with raw material drying effect higher than the preset threshold are selected in the overall drying process.

[0017] In the aforementioned dried samples, the distribution of raw material types was statistically analyzed, and the raw material type with the largest proportion was determined as the standard raw material type.

[0018] As a further limitation of the technical solution of this invention, the steps of obtaining the initial temperature of the hot air in the current drying process and correcting the initial temperature of the hot air based on the deviation of the average slope and the deviation of the stability, so as to realize the dynamic adjustment of the evaporation process affected by the upstream storage time, include:

[0019] Obtain the initial hot air temperature of the current drying process and the preset temperature correction formula, and substitute the average slope deviation and stability deviation into the temperature correction formula to calculate the corrected initial hot air temperature.

[0020] The corrected initial hot air temperature is applied to the early heating stage of the current batch drying process to achieve dynamic adjustment of the evaporation process, which is affected by the upstream storage time.

[0021] As a further limitation of the technical solution of this embodiment of the invention, the temperature correction formula is as follows:

[0022] ;

[0023] in, This refers to the corrected initial temperature of the hot air;

[0024] This refers to the initial temperature of the hot air in the current drying process;

[0025] This refers to the average slope of the current previous average evaporation rate sequence;

[0026] This refers to the average slope of the previous average evaporation rate sequence;

[0027] This refers to the deviation of the average slope of the current previous period's average evaporation rate sequence from that of a reference previous period's average evaporation rate sequence;

[0028] This refers to the volatility parameter of the current previous average evaporation rate sequence;

[0029] This refers to the volatility parameter based on the previous average evaporation rate sequence;

[0030] This refers to the degree of stability deviation of the current previous average evaporation rate sequence compared to the reference previous average evaporation rate sequence;

[0031] and These refer to the adjustment factors corresponding to the deviation of the average slope and the deviation of the stability, respectively. and The range of values ​​is , ;

[0032] The volatility parameters include standard deviation or coefficient of variation, which are used to measure the degree of volatility in the previous average evaporation rate sequence.

[0033] This invention also provides a data management system for the Industrial Internet of Things (IIoT), employing the aforementioned IIoT data management method. The system includes: a current sequence acquisition module, a drying sample acquisition module, a reference sequence acquisition module, a deviation magnitude calculation module, and an initial temperature correction module, wherein:

[0034] The current sequence acquisition module is used to acquire the raw material type information of the current batch of dried raw materials, extract several target local historical data that belong to the same type as the current batch of dried raw materials and whose upstream storage time gradually increases from the historical drying data, and extract the corresponding current previous average evaporation rate sequence.

[0035] The drying sample acquisition module is used to analyze whether the increase in upstream storage time causes a systematic evolution of the current trend of the average evaporation rate sequence. If so, it selects several drying samples from historical drying data in which the raw material drying effect is higher than the preset threshold during the overall drying process, and determines the raw material type with the largest proportion in these drying samples as the standard raw material type.

[0036] The reference sequence acquisition module is used to acquire all drying samples corresponding to the standard raw material type, and to select reference samples corresponding to several upstream storage times corresponding to the current batch of dried raw materials, and to extract the corresponding reference early-stage average evaporation rate sequence.

[0037] The deviation magnitude calculation module is used to calculate the average slope deviation and stability deviation of the current previous average evaporation rate sequence compared with the reference previous average evaporation rate sequence, respectively.

[0038] The initial temperature correction module is used to obtain the initial temperature of the hot air in the current drying process and correct the initial temperature of the hot air based on the deviation of the average slope and the deviation of the stability, so as to achieve dynamic adjustment of the evaporation process affected by the upstream storage time.

[0039] As a further limitation of the technical solution of the present invention, the upstream storage time refers to the time interval between the start time of temporary storage of the current batch of dried raw materials after the completion of the previous processing step and the start time of entering the drying step.

[0040] As a further limitation of the technical solution of this embodiment of the invention, the dried sample acquisition module specifically includes:

[0041] The trend observation unit is used to analyze whether the current average evaporation rate sequence corresponding to the local historical data of the several targets shows a continuous increasing trend as the upstream storage time gradually increases.

[0042] The drying sample acquisition unit is used to analyze historical drying data and select several drying samples whose raw material drying effect is higher than a preset threshold during the overall drying process when the above-mentioned trend change characteristics are confirmed.

[0043] The standard raw material type determination unit is used to statistically analyze the distribution of raw material types in the plurality of dried samples and determine the raw material type with the largest proportion as the standard raw material type.

[0044] As a further limitation of the technical solution of this embodiment of the invention, the initial temperature correction module specifically includes:

[0045] The initial temperature correction unit is used to obtain the initial temperature of the hot air in the current drying process and the preset temperature correction formula, and to substitute the average slope deviation and stability deviation into the temperature correction formula to calculate the corrected initial temperature of the hot air.

[0046] The initial temperature correction application unit is used to apply the corrected initial hot air temperature to the early heating stage of the current batch drying process, so as to achieve dynamic adjustment of the evaporation process affected by the upstream storage time.

[0047] The initial temperature correction unit uses the same temperature correction formula as the method, and the parameters are substituted and calculated through real-time data interaction of the Industrial Internet of Things (such as real-time communication between the current sequence acquisition module and the deviation magnitude calculation module) to ensure the dynamic nature of the correction value.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] This invention, by constructing a dynamic response identification mechanism based on the influence of upstream storage time and combining a two-factor model of the deviation magnitude of the average slope and stability of the average evaporation rate sequence, achieves for the first time adaptive correction and control of the initial hot air temperature in the drying process. Compared to existing technologies that rely solely on fixed process parameters such as raw material type or set temperature, this invention can sense the evolution of material state caused by temporary storage, accurately identify its impact on evaporation trends and stability, and adjust the thermal driving intensity through a weighted correction formula. This effectively improves the consistency, responsiveness, and quality control capabilities of the drying process, demonstrating higher system intelligence and industrial application value. It is particularly suitable for raw material types such as intermediate materials for ceramic powder preparation that are sensitive to the initial drying response and easily affected by temporary storage conditions. Attached Figure Description

[0050] Figure 1 A flowchart of the method provided in an embodiment of the present invention;

[0051] Figure 2 This is a flowchart illustrating the process of determining the standard raw material type in the method provided in this embodiment of the invention;

[0052] Figure 3 This is a flowchart illustrating the correction of the initial hot air temperature in the current drying process in the method provided by this embodiment of the invention;

[0053] Figure 4 Application architecture diagram of the system provided in the embodiments of the present invention;

[0054] Figure 5 This is a structural block diagram of the dried sample acquisition module in the system provided in the embodiment of the present invention;

[0055] Figure 6 This is a structural block diagram of the initial temperature correction module in the system provided in an embodiment of the present invention. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0057] Figure 1 A flowchart of the method provided by an embodiment of the present invention is shown.

[0058] Specifically, an industrial Internet of Things (IIoT) data management method includes the following steps:

[0059] Step S100: Obtain the raw material type information of the current batch of raw materials to be dried, extract historical drying data of the same type as the current batch of raw materials to be dried, and target local historical data with gradually increasing upstream storage time, and extract the corresponding current previous average evaporation rate sequence. The upstream storage time refers to the time interval between the start time of temporary storage of the current batch of raw materials after completing the previous processing step and the start time of entering the drying step;

[0060] Standard for calculating the average evaporation rate sequence in the early stage:

[0061] Time window: heat-sensitive raw materials (thermal diffusivity < (e.g., lithium electrode sheets): For the first 10 minutes, raw material quality data is collected every 2 minutes; for conventional raw materials (thermal diffusivity) (e.g., ceramic powder): For the first 15 minutes, raw material quality data will be collected every 5 minutes.

[0062] Rate calculation: Average evaporation rate in the early stage = (starting mass of window - ending mass of window) / window duration (unit: g / min);

[0063] Sequence construction: Arrange the rate values ​​of each collection point in chronological order to form the current previous average evaporation rate sequence.

[0064] Taking ceramic powder as an example, its upstream storage time is 45 minutes. Historical data for the same type of ceramic powder with upstream storage times of 15 minutes, 30 minutes, 45 minutes, and 60 minutes were extracted from historical data. The corresponding current average evaporation rate sequences are [0.8 g / min, 0.9 g / min, 1.0 g / min], [0.9 g / min, 1.0 g / min, 1.1 g / min], [1.0 g / min, 1.1 g / min, 1.2 g / min], and [1.1 g / min, 1.2 g / min, 1.3 g / min] (the time window is the first 15 minutes, with one data point taken every 5 minutes).

[0065] The time window is determined based on the thermal diffusivity of the raw materials: for heat-sensitive raw materials (such as lithium electrode sheets), the thermal diffusivity is < Take the sample 10 minutes before use; for conventional raw materials (such as ceramic powder, thermal diffusivity) Take the first 15 minutes. Preliminary experiments can verify that the window is stable when the rate of change at three consecutive time points is <2%.

[0066] In this embodiment of the invention, the raw materials to be dried in the current batch can be various industrial materials with significant moisture content that require hot air drying, such as wet-coated lithium electrode sheets, agricultural and sideline product slices, raw materials for primary processing of medicinal materials, wet pulp boards for papermaking, and ceramic blanks. For ease of model classification and trend extraction, "raw material type information" is a higher-level classification, referring to a broad category of raw materials with common drying behavior characteristics. Within this scope, the same type of raw material can include multiple subcategories with different specifications, batch numbers, sizes, or supply batches. For example, electrode sheets with different coating thicknesses still belong to the "lithium electrode sheet" type.

[0067] The initial hot air temperature in the current drying process refers to the first stage of hot air supply temperature set before the current batch of raw materials officially enters the drying device or in the initial stage. This temperature directly determines the strength of the evaporation driving force in the initial stage of drying and is an important variable for regulating the start-up response of the evaporation process. This invention dynamically adjusts this temperature to adapt to the initial moisture content changes of different raw materials due to differences in upstream processing, thereby ensuring consistent drying quality.

[0068] Historical drying data refers to process data collected and recorded by drying equipment and its supporting systems during actual operation in an Industrial Internet of Things (IIoT) environment. This data can originate from edge node caches, enterprise data centers, or cloud storage platforms. It includes at least: raw material type and batch identification information, upstream storage duration, hot air temperature profile, air velocity / volume data, drying time, moisture content monitoring values, process temperature and humidity profiles, average evaporation rate in the early stages, and its timestamp. This data must possess timestamps and batch attribution attributes to enable cross-batch trend analysis and data comparison.

[0069] Upstream storage time refers to the time interval between the start of temporary storage of the current batch of raw materials after completing the previous processing step (such as coating, soaking, stirring, etc.) and the start time of entering the current drying process. The unit is usually minutes or hours. It reflects the effects of moisture redistribution, structural loosening, or surface oxidation that may occur in the material under uncontrolled conditions, and is an important factor causing differences in drying response.

[0070] The selection principle for several target historical data sets with gradually increasing upstream storage durations is as follows: Several batches of data similar to the current raw material are screened from the historical database, sorted in ascending order according to their upstream storage duration, and then several points are selected at medium intervals to form a sample set with a variation gradient. The interval can be set based on the historical sample density, for example, setting each 30 minutes as a group of difference samples. When storage duration has a significant impact on the evaporation response, it can be identified by observing the trend of evaporation behavior changes in this group of data. If it is found that the initial average evaporation rate shows a systematic shift due to changes in storage duration, it is necessary to adjust the initial hot air temperature of the current drying process to achieve dynamic regulation.

[0071] The average evaporation rate in the initial stage refers to the average amount of water lost by the raw material per unit time during the initial stage of the drying process (e.g., the first 10-20 minutes), commonly expressed in g / min or % / min. This indicator measures the response rate of the material during the initial heating stage and is a crucial basis for determining process stability and deviation from standards in this invention. In existing technologies, evaporation rate, as a core variable in drying curve analysis, has been applied in multiple fields, thus exhibiting good engineering identifiability.

[0072] The method for extracting the corresponding current average evaporation rate sequence from the target local historical data is as follows: Locate several batches with known upstream storage durations in the historical records. Within each batch, select continuous mass change values ​​within a fixed time period (e.g., the first 15 minutes) after the start of drying. Calculate the evaporation rate per unit time and perform time normalization to construct an average evaporation rate sequence arranged in ascending order of storage duration. This sequence can not only be used to determine trend changes but also serve as a reference for the response behavior of the current batch.

[0073] Furthermore, the data management approach for the Industrial Internet of Things (IIoT) also includes the following steps:

[0074] Step S200: Analyze whether the increase in upstream storage time causes a systematic evolution of the current trend of the average evaporation rate sequence. If so, select several drying samples from historical drying data in which the raw material drying effect is higher than the preset threshold during the overall drying process, and determine the raw material type with the largest proportion in these drying samples as the standard raw material type.

[0075] Specifically, Figure 2 A flowchart for determining the standard raw material type is shown.

[0076] The analysis of whether the increase in upstream storage time causes a systematic evolution in the current trend of the average evaporation rate sequence in the early stage, and if so, the following steps are taken to select several drying samples from historical drying data in which the raw material drying effect is higher than a preset threshold during the overall drying process, and to determine the raw material type with the largest proportion in these drying samples as the standard raw material type:

[0077] Step S201: Analyze whether the current average evaporation rate sequence corresponding to several target local historical data shows a continuous increasing trend as the upstream storage time gradually increases.

[0078] The trend of continuous increase refers to the fact that, through linear regression analysis, the slope of the current previous average evaporation rate sequence is >0, and the determination coefficient R² of the linear regression is ≥0.8, with a significance level of p <0.05, that is, the statistical significance level reaches more than 95%.

[0079] Step S202: When the above-mentioned trend change characteristics are confirmed, the historical drying data is analyzed and several drying samples with raw material drying effect higher than the preset threshold are selected in the overall drying process.

[0080] Step S203: In several dried samples, the distribution of raw material types is statistically analyzed, and the raw material type with the largest proportion is determined as the standard raw material type.

[0081] In this embodiment of the invention, the fundamental purpose of first analyzing whether the increase in upstream storage time causes a systematic evolution in the current trend of the average evaporation rate sequence is to determine whether the batch of dried raw materials has experienced a shift in response behavior due to the influence of upstream processing. This step, namely step S201, has prerequisite judgment significance and is the basis for whether the entire correction mechanism is triggered. If the average evaporation rate shows a significant increasing trend with the increase in upstream storage time, it indicates that the moisture content structure or surface characteristics of the raw materials have undergone a systematic change, and the originally set initial hot air temperature may no longer be able to effectively match the current material state. Only when such a trend shift exists is subsequent correction practically necessary, thereby avoiding ineffective correction of factors without influence by the system.

[0082] The preset threshold in step S202 is typically set based on statistical analysis of a large amount of historical operating data. The system can extract quantiles from the distribution of drying results for each batch, or combine this with quality evaluation indicators such as final moisture content, finished product qualification rate, and drying uniformity for normalized scoring, setting a score above a certain threshold as the standard for "good drying effect". This threshold can be a fixed value, or a corresponding standard range can be set for different raw material types. In actual system deployment, such thresholds are usually pre-stored in a historical database or used as part of a parameter model, dynamically loaded and called by the algorithm.

[0083] Selecting several dried samples whose raw material drying effect exceeded a preset threshold during the overall drying process aims to ensure the representativeness and process success of subsequent reference data. Directly using historical data from any batch might introduce samples with serious biases or drying anomalies, hindering the construction of a reliable reference trend. Therefore, selecting historical samples with good process performance as a foundation helps improve the stability and reliability of subsequent correction processes.

[0084] In step S203, determining the raw material type with the largest proportion in the selected samples as the standard raw material type is to establish a representative and generalizable data reference benchmark. In industrial scenarios, there may be multiple subcategories within the same major raw material type (such as different thicknesses, shapes, or supplier batches). Directly averaging all samples may lead to statistical bias. By selecting the raw material type that appears most frequently within the target quality range, not only can the matching accuracy of subsequent comparisons be improved, but the applicability of the correction model can also be broadened. The historical response trend corresponding to this raw material type constitutes the "standard reference trend" in this invention, used as the basis for subsequent deviation magnitude calculations and temperature corrections.

[0085] Furthermore, the data management approach for the Industrial Internet of Things (IIoT) also includes the following steps:

[0086] Step S300: Obtain all drying samples corresponding to the standard raw material type, and select reference samples corresponding to several upstream storage times corresponding to the current batch of dried raw materials, and extract the corresponding reference early-stage average evaporation rate sequence.

[0087] In this embodiment of the invention, the implementation of step S300 relies on a historical drying sample database already established in the industrial Internet of Things system. This database records information such as the type of raw materials to be dried in each batch, upstream storage duration, hot air temperature settings, quality change records, and previous evaporation behavior data. The system first filters out all historical drying samples from the database that match the standard raw material type determined in step S203 by calling the raw material type identifier field, forming a first data set. Subsequently, based on the upstream storage duration of the current batch of raw materials, the system uses this value as a search condition to filter out several historical samples with similar or corresponding storage durations from the set, constituting a reference sample set.

[0088] During the screening process, a tolerance range can be set for matching, such as ±5 minutes or ±10%, to ensure that the reference sample is comparable to the current batch in terms of upstream storage behavior. This retrieval process can be completed through SQL condition filtering, tag-based index matching, or segmented interval queries, or it can be automatically executed by a preset algorithm model in an edge computing module or cloud platform.

[0089] For each reference sample, the system further extracts its mass change data during the initial drying stage, averages the mass removal per unit time within a preset time window (e.g., the first 15 minutes), and obtains its corresponding reference average evaporation rate in the early stage, ultimately forming a reference rate sequence. This sequence can be used for deviation comparison analysis with the current batch data.

[0090] The significance of this step lies in establishing a historical sample reference system that highly matches the current batch's condition. By matching the upstream storage duration, the interference from external environmental variables and process conditions can be minimized, ensuring that subsequent deviation calculations accurately reflect the response differences between the current batch's raw material condition and existing good products. Furthermore, using reference samples of the same raw material type avoids structural response differences between types, improving the relevance and accuracy of standard curve comparisons and providing a reliable basis for subsequent temperature correction.

[0091] Furthermore, the data management approach for the Industrial Internet of Things (IIoT) also includes the following steps:

[0092] Step S400: Calculate the average slope deviation and stability deviation of the current previous average evaporation rate sequence compared to the reference previous average evaporation rate sequence.

[0093] Step S500: Obtain the initial temperature of the hot air in the current drying process, and correct the initial temperature of the hot air based on the deviation of the average slope and the deviation of the stability, so as to achieve dynamic adjustment of the evaporation process affected by the upstream storage time.

[0094] Specifically, Figure 3 A flowchart is shown to correct the initial temperature of the hot air in the current drying process.

[0095] The process of obtaining the initial hot air temperature of the current drying process and correcting it based on the average slope deviation and stability deviation to dynamically adjust the evaporation process affected by upstream storage time includes the following steps:

[0096] Step S501: Obtain the initial temperature of the hot air in the current drying process and the preset temperature correction formula, and substitute the average slope deviation and stability deviation into the temperature correction formula to calculate the corrected initial temperature of the hot air.

[0097] Step S502: The corrected initial hot air temperature is applied to the early heating stage of the current batch drying process to achieve dynamic adjustment of the evaporation process affected by the upstream storage time.

[0098] The temperature correction formula is:

[0099] ;

[0100] in: This refers to the corrected initial temperature of the hot air;

[0101] This refers to the initial temperature of the hot air in the current drying process;

[0102] This refers to the average slope of the current previous average evaporation rate sequence;

[0103] This refers to the average slope of the previous average evaporation rate sequence;

[0104] This refers to the deviation of the average slope of the current previous period's average evaporation rate sequence from that of a reference previous period's average evaporation rate sequence;

[0105] This refers to the volatility parameter of the current previous average evaporation rate sequence;

[0106] This refers to the volatility parameter based on the previous average evaporation rate sequence;

[0107] This refers to the degree of stability deviation of the current previous average evaporation rate sequence compared to the reference previous average evaporation rate sequence;

[0108] and These refer to the adjustment factors corresponding to the deviation of the average slope and the deviation of the stability, respectively. and The range of values ​​is , The specific values ​​are determined experimentally based on the type of raw material.

[0109] For heat-sensitive materials (such as lithium electrode sheets), it is recommended , ;

[0110] For conventional raw materials (such as ceramic powder), it is recommended , .

[0111] The calibration method is as follows:

[0112] Sample selection: Three groups of raw materials of the same type were selected, with upstream storage times of t-30min, t, and t+30min (t being the storage time of the current batch), and the sample size of each group was ≥5 replicates;

[0113] Variable control: Fix hot air velocity (e.g., 2 m / s) and total drying time (e.g., 60 min), only adjust... and ;

[0114] Test indicators: Record the coefficient of variation of the initial evaporation rate sequence (≤5% is acceptable) and the final moisture content fluctuation (≤±0.3% is acceptable);

[0115] Determining the optimal value: Through orthogonal experiments, select the value that simultaneously satisfies the above indicators. and Value (e.g., the optimal value for ceramic powder) , ).

[0116] Preset thresholds for lithium electrode sheets: final moisture content deviation ≤ preset range, drying uniformity poor ≤ preset range (sampling points are the four corners and center of each electrode sheet, measured using industry-standard moisture content testing instruments), surface defect rate ≤ preset ratio;

[0117] The preset thresholds for various raw materials are determined based on the statistical analysis of historical qualified batches of the same type of raw materials, with a statistical sample size of no less than 30 groups, and the threshold value is taken as the 90th percentile of the historical qualified data.

[0118] Volatility parameters, including standard deviation or coefficient of variation, are used to measure the degree of volatility in the previous average evaporation rate series.

[0119] Formula for calculating standard deviation: ,in For the first Evaporation rate at each time point The mean of the rate sequence, For the number of data points (e.g.) (This corresponds to one data point every 5 minutes within a 15-minute timeframe). Example: Ceramic powder rate sequence [1.0, 1.1, 1.2]. , ;

[0120] Formula for calculating coefficient of variation (CV): This method is suitable for comparing the stability of rate sequences at different magnitudes (e.g., CV is more sensitive when the rate of a lithium electrode sheet is low). Example: The above ceramic powder sequence. .

[0121] In this embodiment of the invention, the "average slope deviation" in step S400 is used to measure the degree of deviation of the evaporation response trend of the current batch of raw materials in the initial stage of drying from that of the standard sample, that is, the slope difference between the overall change trend of the current early-stage average evaporation rate sequence and the reference sequence. This indicator reflects whether the water loss capacity of the raw material under thermal driving is too strong or too weak, and is a key parameter characterizing the dynamic response of the drying process.

[0122] In contrast, the "stability deviation" reflects whether the volatility of the current batch of raw material evaporation behavior is consistent with the standard stability range. Its calculation is based on volatility parameters of the rate sequence (such as standard deviation or coefficient of variation) to measure whether there are abnormal fluctuations or local instability in the current batch's evaporation curve. This indicator can effectively identify evaporation disturbances caused by factors such as raw material homogeneity, cohesiveness, or surface moisture gradients.

[0123] The selection criteria for volatility parameters are as follows: when the mean difference between the current previous average evaporation rate sequence and the reference sequence is ≤20%, the standard deviation (reflecting the degree of absolute volatility) is preferred; when the mean difference is >20%, the coefficient of variation is preferred (to eliminate the influence of the difference in mean magnitude and reflect the degree of relative volatility). For example, if the mean of the current sequence for lithium electrode sheets is 1.5 g / min and the mean of the reference sequence is 1.0 g / min (a difference of 50%), then the coefficient of variation is used to calculate the stability deviation.

[0124] The purpose of jointly correcting the initial hot air temperature using the average slope deviation and stability deviation is to simultaneously assess both the "drying trend direction shift" and the "drying process stability shift" across two dimensions, and adjust the hot air drive parameters accordingly, thereby achieving more targeted dynamic regulation. Raw material batches with large slope deviations indicate that their evaporation start-up response differs significantly from the standard, requiring adjustments to the hot air thrust (temperature) to bring their water loss trend closer. Conversely, larger stability deviations indicate stronger fluctuations or nonlinear responses during the current batch's evaporation process, requiring the system to provide greater heat input to accelerate process convergence and improve the stability of evaporation drive and overall drying consistency. Therefore, this invention increases the initial hot air temperature, giving it stronger response adjustment capabilities to adapt to more complex unstable states. The combination of these two factors helps the system respond more intelligently and adaptively to differences in drying response caused by variations in upstream storage time.

[0125] In the temperature correction process, this invention employs a linear combination correction method. The system first obtains the originally set initial hot air temperature for the current drying process. Then, based on the two calculated deviations, it multiplies each by its corresponding adjustment coefficient, and finally, the corrected value is superimposed on the original temperature value, thereby generating an initial hot air temperature that better reflects the current state of the raw materials. This correction method balances response magnitude and adjustment intensity, possessing good interpretability and engineering applicability.

[0126] Regarding the calculation process of the average slope and volatility parameters, the system first sets a unified time window (e.g., the first 15 minutes) and collects the amount of water lost per unit time from the raw material during this period, forming an early evaporation rate sequence. The average slope can be fitted to this sequence using linear regression, and its first derivative (i.e., the slope) is extracted as a trend indicator; the volatility parameter is calculated based on the standard deviation or coefficient of variation of this rate sequence as a stability reference. This process can be completed in real time through an embedded data acquisition system, edge computing module, or cloud analysis platform, demonstrating strong technical implementation capabilities.

[0127] It is worth noting that the currently used linear weighted correction formula is only a basic scheme that is intuitive and effective. Further optimization can employ piecewise response functions, exponential adjustment models, sigmoid function mapping, and nonlinear correction strategies based on spline interpolation to construct adaptive control models that are more sensitive to different raw material types or fluctuation characteristics. This flexibility provides ample room for future system expansion and upgrades.

[0128] Furthermore, Figure 4 An application architecture diagram of the system provided in an embodiment of the present invention is shown.

[0129] This invention also provides an industrial IoT data management system, employing the aforementioned industrial IoT data management method. The system includes:

[0130] The current sequence acquisition module 100 is used to acquire the raw material type information of the current batch of drying raw materials, extract several target local historical data from historical drying data that belong to the same type as the current batch of drying raw materials and whose upstream storage time gradually increases, and extract the corresponding current previous average evaporation rate sequence. The upstream storage time refers to the time interval between the start time of temporary storage of the current batch of drying raw materials after completing the previous processing step and the start time of entering the drying step.

[0131] Furthermore, the data management system for the Industrial Internet of Things also includes:

[0132] The drying sample acquisition module 200 is used to analyze whether the increase in upstream storage time causes a systematic evolution of the current trend of the average evaporation rate sequence. If so, it selects several drying samples from historical drying data in which the raw material drying effect is higher than the preset threshold during the overall drying process, and determines the raw material type with the largest proportion in these drying samples as the standard raw material type.

[0133] For ceramic powder, the preset thresholds are: final moisture content deviation ≤ ±0.8%, drying uniformity poor ≤ 1.2%, and no surface cracks (defect rate < 1%). Thirty samples meeting these criteria were selected, of which ceramic powder accounted for 70% (21 samples), and were determined as the standard raw material type.

[0134] Specifically, Figure 5 The diagram shows a structural block diagram of the drying sample acquisition module 200 in the system provided in an embodiment of the present invention.

[0135] In a preferred embodiment of the present invention, the dried sample acquisition module 200 specifically includes:

[0136] Trend observation unit 201 is used to analyze whether the current average evaporation rate sequence corresponding to the local historical data of several targets shows a continuous increasing trend as the upstream storage time gradually increases.

[0137] The drying sample acquisition unit 202 is used to analyze historical drying data and select several drying samples whose raw material drying effect is higher than a preset threshold during the overall drying process when the above-mentioned trend change characteristics are confirmed.

[0138] The standard raw material type determination unit 203 is used to statistically analyze the distribution of raw material types in several dried samples and determine the raw material type with the largest proportion as the standard raw material type.

[0139] Furthermore, the data management system for the Industrial Internet of Things also includes:

[0140] The reference sequence acquisition module 300 is used to acquire all drying samples corresponding to the standard raw material type, and to select reference samples corresponding to several upstream storage times corresponding to the current batch of dried raw materials, and to extract the corresponding reference early-stage average evaporation rate sequence.

[0141] Furthermore, the data management system for the Industrial Internet of Things also includes:

[0142] The deviation calculation module 400 is used to calculate the average slope deviation and stability deviation of the current previous average evaporation rate sequence compared with the reference previous average evaporation rate sequence, respectively.

[0143] The average slope of the current early-stage evaporation rate sequence of ceramic powder is 0.02 g / (min·min) (increasing from 1.0 to 1.3 g / min within 15 minutes), while the average slope of the reference sequence (standard raw material type, same storage time 45 minutes) is 0.015 g / (min·min). Therefore, the deviation of the average slope ΔS = (0.02 - 0.015) / 0.015 ≈ 33.3%; the volatility parameter (standard deviation) of the current sequence is 0.05, while that of the reference sequence is 0.03, and the stability deviation ΔC = (0.05 - 0.03) / 0.03 ≈ 66.7%.

[0144] The initial temperature correction module 500 is used to obtain the initial temperature of the hot air in the current drying process and correct the initial temperature of the hot air according to the deviation of the average slope and the deviation of the stability, so as to realize the dynamic adjustment of the evaporation process affected by the upstream storage time.

[0145] Current initial temperature of hot air for ceramic drying Adjustment factor (Slope deviation adjustment) (Stability deviation adjustment), substituting into the formula:

[0146] .

[0147] Data interaction between modules: The current sequence acquisition module transmits "raw material type, upstream storage duration, and current early-stage average evaporation rate sequence" to the drying sample acquisition module; the drying sample acquisition module transmits "standard raw material type" to the reference sequence acquisition module; the "reference early-stage average evaporation rate sequence" extracted by the reference sequence acquisition module is transmitted together with the current sequence to the deviation magnitude calculation module; the deviation magnitude calculation module transmits "average slope deviation magnitude and stability deviation magnitude" to the initial temperature correction module, and the final corrected temperature is output by the initial temperature correction module to the drying equipment temperature control unit.

[0148] Specifically, Figure 6 A structural block diagram of the initial temperature correction module 500 in the system provided in an embodiment of the present invention is shown.

[0149] In a preferred embodiment of the present invention, the initial temperature correction module 500 specifically includes:

[0150] The initial temperature correction unit 501 is used to obtain the initial temperature of the hot air in the current drying process and the preset temperature correction formula, and to substitute the average slope deviation and stability deviation into the temperature correction formula to calculate the corrected initial temperature of the hot air.

[0151] The initial temperature correction application unit 502 is used to apply the corrected initial hot air temperature to the early heating stage of the current batch drying process, so as to achieve dynamic adjustment of the evaporation process affected by the upstream storage time.

[0152] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0153] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0154] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0155] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0156] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A data management method for the Industrial Internet of Things (IIoT), characterized in that, The method includes: S100. Obtain the raw material type information of the current batch of dried raw materials, extract the historical drying data of the same type as the current batch of dried raw materials and the target local historical data with gradually increasing upstream storage time, and extract the corresponding current previous average evaporation rate sequence. The selection principle for local target historical data with gradually increasing upstream storage time is as follows: filter several batches of data of the same type as the current raw material in the historical database, sort them in ascending order according to their upstream storage time, and then select several points at medium intervals to form a sample set with a changing gradient. S200. Analyze whether the increase in upstream storage time causes a systematic evolution of the current trend of the average evaporation rate sequence. If so, select drying samples from historical drying data where the raw material drying effect is higher than the preset threshold during the overall drying process, and determine the raw material subtype with the largest proportion in these drying samples as the standard raw material type. S300: Obtain all drying samples corresponding to the standard raw material type, and select reference samples that correspond to the upstream storage time of the current batch of dried raw materials, and extract the corresponding reference early-stage average evaporation rate sequence. S400. Calculate the average slope deviation and stability deviation of the current previous average evaporation rate sequence compared to the reference previous average evaporation rate sequence. S500: Obtain the initial temperature of the hot air in the current drying process, and correct the initial temperature of the hot air based on the deviation of the average slope and the deviation of the stability, so as to achieve dynamic adjustment of the evaporation process affected by the upstream storage time. The dynamic adjustment achieves predictive correction of the initial temperature of the hot air by analyzing the historical trend correlation between the upstream storage time and the previous average evaporation rate sequence, combined with the two-factor deviation calculation between the current sequence and the reference sequence, rather than passive feedback adjustment based on a single point in time.

2. The data management method for the Industrial Internet of Things according to claim 1, characterized in that, The upstream storage time refers to the time interval between the start time of temporary storage of the current batch of raw materials after the completion of the previous processing step and the start time of entering the drying process.

3. The data management method for the Industrial Internet of Things according to claim 2, characterized in that, Analyzing whether the increase in upstream storage time causes a systematic evolution in the current trend of the average evaporation rate sequence in the early stage, and if so, the steps to screen drying samples from historical drying data where the raw material drying effect is higher than a preset threshold during the overall drying process, and to determine the raw material type with the largest proportion in these drying samples as the standard raw material type, include: The analysis examines whether the current average evaporation rate sequence corresponding to the target local historical data shows a continuous increasing trend as the upstream storage time gradually increases. The continuously increasing trend refers to the fact that, through linear regression analysis, the slope of the current previous average evaporation rate sequence is >0, and the determination coefficient R² of the linear regression is ≥0.8, with a significance level of p<0.

05. When the above trend change characteristics are confirmed, the historical drying data is analyzed and drying samples with raw material drying effect higher than the preset threshold are selected in the overall drying process. In the dried sample, the distribution of raw material types is statistically analyzed, and the raw material type with the largest proportion is determined as the standard raw material type.

4. The data management method for the Industrial Internet of Things according to claim 3, characterized in that, The steps for obtaining the initial hot air temperature of the current drying process and correcting the initial hot air temperature based on the average slope deviation and stability deviation, in order to dynamically adjust the evaporation process affected by the upstream storage time, include: Obtain the initial hot air temperature of the current drying process and the preset temperature correction formula, and substitute the average slope deviation and stability deviation into the temperature correction formula to calculate the corrected initial hot air temperature. The corrected initial hot air temperature is applied to the early heating stage of the current batch drying process to achieve dynamic adjustment of the evaporation process, which is affected by the upstream storage time.

5. The data management method for the Industrial Internet of Things according to claim 4, characterized in that, The temperature correction formula is as follows: ； in, This refers to the corrected initial temperature of the hot air; This refers to the initial temperature of the hot air in the current drying process; This refers to the average slope of the current previous average evaporation rate sequence; This refers to the average slope of the previous average evaporation rate sequence; This refers to the deviation of the average slope of the current previous period's average evaporation rate sequence from that of a reference previous period's average evaporation rate sequence; This refers to the volatility parameter of the current previous average evaporation rate sequence; This refers to the volatility parameter based on the previous average evaporation rate sequence; This refers to the degree of stability deviation of the current previous average evaporation rate sequence compared to the reference previous average evaporation rate sequence; and These refer to the adjustment factors corresponding to the deviation of the average slope and the deviation of the stability, respectively. and The range of values ​​is , ; The volatility parameters include standard deviation or coefficient of variation, which are used to measure the degree of volatility in the previous average evaporation rate sequence.

6. A data management system for the Industrial Internet of Things (IIoT), employing the data management method for the Industrial Internet of Things as described in claim 5, characterized in that, The system includes: a current sequence acquisition module, a dried sample acquisition module, a reference sequence acquisition module, a deviation magnitude calculation module, and an initial temperature correction module, wherein: The current sequence acquisition module is used to acquire the raw material type information of the current batch of drying raw materials, extract the target local historical data that belongs to the same type as the current batch of drying raw materials and whose upstream storage time gradually increases from the historical drying data, and extract the corresponding current previous average evaporation rate sequence. The drying sample acquisition module is used to analyze whether the increase in upstream storage time causes a systematic evolution of the current trend of the average evaporation rate sequence. If so, it selects drying samples from historical drying data that have a higher drying effect than a preset threshold in the overall drying process, and determines the raw material subtype with the largest proportion in these drying samples as the standard raw material type. The reference sequence acquisition module is used to acquire all drying samples corresponding to the standard raw material type, and to select reference samples that correspond to the upstream storage time of the current batch of dried raw materials, and extract the corresponding reference early-stage average evaporation rate sequence. The deviation magnitude calculation module is used to calculate the average slope deviation and stability deviation of the current previous average evaporation rate sequence compared with the reference previous average evaporation rate sequence, respectively. The initial temperature correction module is used to obtain the initial temperature of the hot air in the current drying process and correct the initial temperature of the hot air based on the deviation of the average slope and the deviation of the stability, so as to achieve dynamic adjustment of the evaporation process affected by the upstream storage time.

7. The industrial IoT data management system according to claim 6, characterized in that, The upstream storage time refers to the time interval between the start time of temporary storage of the current batch of raw materials after the completion of the previous processing step and the start time of entering the drying process.

8. The industrial IoT data management system according to claim 7, characterized in that, The dried sample acquisition module specifically includes: The trend observation unit is used to analyze whether the current average evaporation rate sequence corresponding to the target local historical data shows a continuous increasing trend as the upstream storage time gradually increases. The drying sample acquisition unit is used to analyze historical drying data and select drying samples whose raw material drying effect is higher than a preset threshold during the overall drying process when the above-mentioned trend change characteristics are confirmed. The standard raw material type determination unit is used to statistically analyze the distribution of raw material types in the dried sample and determine the raw material type with the largest proportion as the standard raw material type.

9. The industrial IoT data management system according to claim 8, characterized in that, The initial temperature correction module specifically includes: The initial temperature correction unit is used to obtain the initial temperature of the hot air in the current drying process and the preset temperature correction formula, and to substitute the average slope deviation and stability deviation into the temperature correction formula to calculate the corrected initial temperature of the hot air. The initial temperature correction application unit is used to apply the corrected initial hot air temperature to the early heating stage of the current batch drying process, so as to achieve dynamic adjustment of the evaporation process affected by the upstream storage time.

10. The industrial IoT data management system according to claim 9, characterized in that, The initial temperature correction unit uses the temperature correction formula described in claim 5, and the parameter substitution and calculation are realized through real-time data interaction of the Industrial Internet of Things to ensure the dynamic nature of the correction value.

Images