System for accurately controlling moisture content in polycarbodiimide reaction process

Abstract

The invention relates to the technical field of industrial control software, in particular to a system for accurately controlling moisture content in a polycarbodiimide reaction process. The system comprises a data acquisition module used for acquiring multi-source monitoring data; the attention evaluation calculation module is used for calculating attention evaluation values corresponding to the monitoring data; the abnormal monitoring index screening module is used for obtaining an attention evaluation sequence and screening out abnormal monitoring indexes based on the attention evaluation sequence; the ventilation adjustment factor calculation module is used for calculating a ventilation adjustment factor; the ventilation environment abnormal degree analysis module is used for determining the abnormal degree of the current ventilation environment; and the ventilation capacity dynamic adjustment module is used for weighting the current ventilation capacity based on the abnormal degree of the current ventilation environment, generating target ventilation capacity, determining a control signal level and adjusting operation parameters of the ventilation execution mechanism based on the control signal level. According to the invention, accurate control of the moisture content of the polycarbodiimide reaction system is realized.

Description

Technical Field

[0001] This invention relates to the field of industrial control software technology, specifically to a precise control system for moisture content during the polycarbodiimide reaction process. Background Technology

[0002] Polycarbodiimide, as a high-performance polymer reinforcing agent, has a key functional group (-N=C=N-) that is highly sensitive to water and is prone to hydrolysis and failure. Therefore, high-temperature drying gas needs to be introduced into the reaction system during production to remove moisture.

[0003] However, the ventilation process not only removes moisture but also carries away various components such as reactants, intermediates, and volatile solvents, resulting in a complex composition of the outlet gas. While existing monitoring technologies can detect multiple gas components, different sensors have varying requirements for the measurement environment (such as airflow velocity), and the sensors in the integrated gas channel are coupled, making it difficult to independently and in real-time adjust the required local airflow environment for abnormalities in each detected indicator. This leads to a mismatch between the periodic adjustment of airflow velocity and the dynamic changes in the actual gas state, causing data distortion and decreased reliability, ultimately affecting the accurate judgment and control of the moisture content in the reaction system. Summary of the Invention

[0004] To address the technical problem of low accuracy in controlling the moisture content of the polycarbodiimide reaction system, the present invention aims to provide a precise moisture content control system for the polycarbodiimide reaction process, applicable to a system including at least two sensors. The specific technical solution adopted is as follows: In a first aspect, embodiments of the present invention provide a precise moisture content control system for the reaction of polycarbodiimide, the system comprising: The data acquisition module is used to collect multi-source monitoring data during the polycarbodiimide reaction process via sensors; The attention evaluation calculation module is used to calculate the attention evaluation value corresponding to each monitoring data based on the real-time data of each monitoring data. The anomaly monitoring indicator filtering module is used to sort the attention evaluation values ​​of all monitoring data at the current time to obtain the attention evaluation sequence, and to filter out anomaly monitoring indicators based on the attention evaluation sequence. The ventilation adjustment factor calculation module is used to calculate the ventilation adjustment factor within a preset time window based on the fluctuation of the attention evaluation value corresponding to the abnormal monitoring indicator and the number of abnormal monitoring indicators. The ventilation environment anomaly analysis module is used to construct a historical sequence of ventilation adjustment factors, calculate the effective state factors of multi-source monitoring data based on the changing trends of the historical sequence of ventilation adjustment factors, and determine the current anomaly level of the ventilation environment by combining the effective state factors of each monitoring data. The ventilation volume dynamic adjustment module is used to weight the current ventilation volume based on the degree of abnormality of the current ventilation environment, generate a target ventilation volume, determine the control signal level based on the current ventilation volume and the target ventilation volume, and adjust the operating parameters of the ventilation actuator based on the control signal level.

[0005] In some embodiments, the collection of multi-source monitoring data includes: Set the acquisition frequency for each sensor and broadcast a synchronization clock pulse to each sensor; Real-time data is collected by various sensors at the same time from multiple monitoring data. By associating the real-time data of each monitoring data point with the time of data collection, a time-series data of the monitoring data is formed.

[0006] In some embodiments, the calculation of the attention evaluation value corresponding to each monitoring data point based on real-time data of each monitoring data point includes: Obtain the monitoring values ​​and maximum allowable values ​​of each monitoring data at the time of collection; Calculate the first ratio between the monitored value and the maximum permissible value; The current wind speed and the maximum wind speed that the sensor can collect are obtained at the time of data acquisition. Calculate the second ratio of the current wind speed to the maximum wind speed; The attention evaluation value corresponding to each monitoring data is calculated based on the first ratio and the second ratio.

[0007] In some embodiments, sorting the attention evaluation values ​​of all monitoring data at the current time to obtain an attention evaluation sequence, and filtering out abnormal monitoring indicators based on the attention evaluation sequence, includes: Extract the attention evaluation value corresponding to all monitoring data at the current moment; The attention scores are sorted in ascending order of numerical value to obtain the attention score sequence; Calculate the first-order difference sequence of the attention evaluation sequence, and extract the maximum difference value from the first-order difference sequence; Anomaly monitoring indicators are determined based on the maximum difference value.

[0008] In some embodiments, determining the anomaly monitoring index based on the maximum difference value includes: Obtain the adjacent attention evaluation value corresponding to the maximum difference value; Compare the adjacent attention scores corresponding to the largest difference value and determine the larger value; obtain the maximum value in the attention score sequence. The monitoring data corresponding to the attention evaluation values ​​between the larger and the maximum values ​​are marked as anomaly monitoring indicators.

[0009] In some embodiments, calculating the ventilation adjustment factor within a preset time window based on the fluctuation of the attention evaluation value corresponding to the abnormal monitoring indicator and the number of abnormal monitoring indicators includes: Establish a time window with the current time as the endpoint, and extract the attention evaluation sequence of anomaly monitoring indicators within the time window; Calculate the volatility deviation based on the attention evaluation sequence; The ventilation adjustment factor is calculated by combining the ratio of the number of abnormal monitoring indicators to the total number of monitoring indicators within the statistical time window with the fluctuation deviation.

[0010] In some embodiments, calculating the volatility deviation based on the attention evaluation sequence includes: Calculate the mean and standard deviation of the attention evaluation sequence; Compare the difference between the attention evaluation value and the mean, and determine the standardized deviation value in combination with the standard deviation; The degree of volatility deviation is determined based on the standardized deviation value.

[0011] In some embodiments, constructing a historical sequence of ventilation adjustment factors and calculating the effective state factor of multi-source monitoring data based on the changing trend of the historical sequence of ventilation adjustment factors includes: Construct a ventilation adjustment factor sequence for each monitoring data point over a historical time period; Calculate the difference values ​​between adjacent time points in the ventilation adjustment factor sequence, mark the fluctuation positions where the signs of the difference values ​​change as dividing nodes, and obtain at least one dividing node; Based on each dividing node, the ventilation adjustment factor sequence is divided into two subsequences; each dividing node has its own two corresponding subsequences. Calculate the monitoring fluctuation amplitude of each subsequence separately, and determine the difference in monitoring fluctuation amplitude between the two subsequences corresponding to each dividing node; The node corresponding to the maximum difference in the monitored fluctuation amplitude is used as the target node. For the target division node, the length ratio of the subsequence corresponding to the maximum value of the two monitoring fluctuation amplitudes in the ventilation adjustment factor sequence is taken as the effective state factor of the monitoring data.

[0012] In some embodiments, the determination of the degree of abnormality of the current ventilation environment by integrating the effective state factors of various monitoring data includes: Obtain the effective state factors of each monitoring data; Calculate the percentage of the maximum difference in the current monitoring data's fluctuation range to the sum of the maximum differences in the monitoring fluctuation ranges of all monitoring data, and use this percentage as the abnormality rate of the current monitoring data. Based on the effective state factor and the anomaly ratio of the current monitoring data, determine the degree of a single anomaly in the current ventilation environment. The degree of anomaly in the current ventilation environment is determined by combining the degree of a single anomaly from all monitoring data under the current ventilation environment.

[0013] In some embodiments, the step of weighting the current ventilation volume based on the degree of abnormality of the current ventilation environment to generate a target ventilation volume, and determining the control signal level based on the current ventilation volume and the target ventilation volume, includes: The abnormality value of the current ventilation environment is normalized, and the normalized abnormality value is used to weight the current ventilation volume. The weighted result is used as the target ventilation volume. The current ventilation rate and the target ventilation rate are input into a preset PID controller. The PID controller outputs a control signal level, and the operating parameters of the ventilation actuator are adjusted according to the control signal level.

[0014] In a second aspect, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, it implements the various possible implementations of the first aspect.

[0015] Thirdly, embodiments of the present invention provide a computer program product comprising: computer program code, which, when run on a computer, causes the computer to perform the method described in the first aspect or any possible implementation thereof.

[0016] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the various possible implementations of the first aspect.

[0017] The embodiments of the present invention have at least the following beneficial effects: This system synchronously collects multi-source monitoring data of the reactant gases using multiple sensors and calculates the attention evaluation value of each monitoring indicator to achieve dynamic identification of abnormal indicators. By analyzing the temporal fluctuation characteristics and global anomaly ratio of abnormal indicators, the system calculates a ventilation adjustment factor reflecting the current cleanliness requirements. Furthermore, based on the historical sequence analysis of the adjustment factor, the system assesses the stability of the measurement environment of each sensor to comprehensively evaluate the overall degree of anomaly in the current ventilation environment. Finally, the system intelligently adjusts the target ventilation rate according to this degree of anomaly, precisely driving the actuator through closed-loop control. This achieves high-precision, adaptive, and stable control of the moisture content in the polycarbodiimide reaction system, effectively avoiding moisture control failures caused by sensor contamination or incompatible measurement environments. Attached Figure Description

[0018] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a system block diagram of a precise moisture content control system for a polycarbodiimide reaction process provided in one embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of a computer device provided in one embodiment of the present invention. Detailed Implementation

[0020] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a precise moisture content control system for the polycarbodiimide reaction process proposed in accordance with the present invention.

[0021] In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments may be combined in any suitable form.

[0022] In the description of the embodiments of the present invention, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present invention, "multiple" means two or more.

[0023] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0025] The embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided by the embodiments of the present invention are equally applicable to similar technical problems.

[0026] The following description, in conjunction with the accompanying drawings, details a specific scheme for a precise control system for moisture content during the polycarbodiimide reaction process provided by the present invention.

[0027] Example 1: Please see Figure 1 The diagram illustrates a system block diagram of a precise moisture content control system for the polycarbodiimide reaction process according to an embodiment of the present invention. The system includes the following modules: The data acquisition module 10 is used to collect multi-source monitoring data through sensors. Specifically, in practical applications, polycarbodiimide typically undergoes the reaction in a reactor. The system can deploy an air quality detector in the integrated gas duct of the reactor, and integrate multiple sensors for different monitoring data on the air quality detector. A sampling frequency can be set for each sensor; for example, all sensors can be configured to collect data at a fixed frequency of 10Hz. Furthermore, to achieve synchronization of monitoring data, a central control unit can generate and broadcast a synchronization clock pulse to all sensors, forcing all sensors to sample at the same microsecond. The collected monitoring data includes, but is not limited to, temperature, humidity, and pH. Each reading of each type of monitoring data is associated with a precise timestamp, thereby constructing a time series data for each type of monitoring data, forming a sample curve for subsequent analysis.

[0028] It should be noted that the methods for collecting multi-source monitoring data and the specific types of monitoring data collected are not unique and can be adjusted according to actual needs.

[0029] Attention evaluation calculation module 11 is used to calculate the attention evaluation value corresponding to each monitoring data based on the real-time data of each monitoring data.

[0030] The degree of abnormality of a monitoring indicator, i.e., its level of attention, depends not only on its absolute concentration but also on the current ventilation conditions. At low wind speeds, even high concentrations may only indicate localized accumulation rather than a systemic problem; however, persistently high concentrations at already high wind speeds indicate a serious problem requiring close attention. Specifically, while collecting monitoring data, the current wind speed can be monitored using air quality detectors deployed within the system, and the maximum wind speed can be obtained.

[0031] Furthermore, the attention evaluation of any monitoring data 'a' within the current time 't' is calculated using the following formula. :

[0032] in, This refers to the monitoring value measured at time t based on the current monitoring data; This represents the maximum permissible value for the current monitoring data; The wind speed at the current moment. This represents the maximum wind speed. The larger the value, the more attention the corresponding monitoring data requires. Furthermore, it iterates through all monitoring data 'a' at the current moment to obtain the attention evaluation value, thus completing a real-time description of each air quality monitoring indicator at the current moment.

[0033] The anomaly monitoring indicator screening module 12 is used to sort the attention evaluation values ​​of all monitoring data at the current time to obtain the attention evaluation sequence, and to screen out the anomaly monitoring indicators based on the attention evaluation sequence.

[0034] Because the measurement principles and response characteristics of the various sensors within the integrated airway differ, under conditions of poor airflow, components such as aerosols, volatiles, and particulate matter in the airflow are prone to differential deposition on different sensor surfaces, contaminating the sensing interface and causing baseline drift and response distortion in the monitoring data, thus significantly interfering with the reliability of the test results. To eliminate such deposition interference, it is necessary to dynamically adjust the airflow to achieve periodic purging and self-cleaning of the sensor surfaces. Therefore, to identify the conditions most in need of cleaning intervention, it is necessary to screen the monitoring indicators most significantly affected by deposition and exhibiting the most severe data anomalies from all monitoring data, i.e., to assess the significance of attentional anomalies in each monitoring data at the current moment.

[0035] Specifically, the attention level corresponding to each monitoring data 'a' at the current moment is evaluated first. The system extracts and sorts all attention evaluations in ascending order, resulting in an ascending attention evaluation sequence. High-significance results are placed at the end of the sequence, while low-significance results are placed at the beginning. A first-order difference is then performed on the attention evaluation sequence to obtain a first-order difference significance sequence. The maximum difference value is extracted from this first-order difference significance sequence, and the maximum value is extracted from the ascending attention evaluation sequence. The system then extracts the larger of the two adjacent attention evaluation values ​​corresponding to this maximum difference value; the monitoring data corresponding to the attention evaluation values ​​within the interval formed by the larger and maximum values ​​are marked as anomaly monitoring indicators.

[0036] The ventilation adjustment factor calculation module 13 is used to calculate the ventilation adjustment factor within a preset time window based on the fluctuation of the attention evaluation value corresponding to the abnormal monitoring indicator and the number of abnormal monitoring indicators.

[0037] After identifying the abnormal monitoring indicator, the system needs to determine the severity and trend of the anomaly. A momentary high reading may only be a temporary disturbance, while a persistent or worsening anomaly truly requires intervention. Therefore, this embodiment further calculates the fluctuation deviation based on the attention evaluation sequence. The core purpose of the fluctuation deviation is to assess the dynamic behavior of the abnormal monitoring indicator within a recent time window. By analyzing the deviation of the abnormal monitoring indicator's reading from its own historical average level and normal fluctuation range, it determines whether the anomaly is worsening, persisting, or has begun to alleviate.

[0038] After obtaining the dynamic risk of each anomaly monitoring indicator, to upgrade control decisions from single anomaly judgment to comprehensive state assessment, it is necessary to construct an indicator that can quantitatively characterize the overall abnormal state and cleaning requirements of the system. This involves calculating the ventilation adjustment factor. The ventilation adjustment factor introduces fluctuation deviation to characterize the dynamic risk intensity of a single anomaly monitoring indicator, thereby distinguishing between different operating conditions such as instantaneous disturbances and continuous deterioration; and integrates the statistical proportions of anomaly monitoring indicators to assess the prevalence of the abnormal state, thus distinguishing between local contamination and systemic mismatch. This allows the system to automatically generate differentiated adjustment commands when facing different scenarios such as significant local anomalies or mild global anomalies, thereby ensuring self-cleaning effectiveness while avoiding control oscillations or insufficient response, ultimately achieving intelligent and optimized ventilation strategies.

[0039] Specifically, firstly, the monitoring data 'a' corresponding to the abnormal monitoring indicators at the current time 't' is extracted, and a time window 'w' ending at the current time is established. Then, the ventilation adjustment factor is calculated using the following formula. :

[0040] in, To evaluate the attention level of the current data source type a at time t. , Evaluation of attention level for current monitoring data 'a' within time window 'w'. The mean, Evaluation of attention level for current monitoring data 'a' within time window 'w'. The standard deviation. This represents the number of anomaly detection indicators a' within the current time window. This represents the total number of all indicators 'a' within the current time window.

[0041] Furthermore, Evaluation of attentional level of current monitoring data a over time. The degree of fluctuation deviation, when the relative mean deviation generated in the monitoring data a is... The larger the value, the more significant the numerical change in the environmental perception characteristics represented by the current monitoring data 'a'. This indicates a more pronounced temporal change in the data value, requiring closer attention to determine if an anomaly has occurred in the environment. Furthermore, since data values ​​from various data sources remain within a certain range in the actual environment, representing the physical limits of environmental indicator changes, processing the fraction by cubes amplifies small numerical differences while retaining the sign information representing the direction of numerical change in the current data source—the direction of data fluctuation. This allows for a more intelligent reflection of anomalies in the actual environmental characteristics represented by the data source. Further analysis of the anomaly scale of the current data source reveals that with a greater number of anomalies, there are more types of abnormal air monitoring data 'a'. This indicates that the values ​​from the current data source have deviated significantly at the current moment in the current time series, necessitating adjustments to the airflow at the current moment to achieve sensor self-cleaning.

[0042] The ventilation environment anomaly analysis module 14 is used to construct a historical sequence of ventilation adjustment factors, calculate the effective state factors of multi-source monitoring data based on the changing trends of the historical sequence of ventilation adjustment factors, and determine the current anomaly level of the ventilation environment by combining the effective state factors of each monitoring data.

[0043] First, for the current time t, all ventilation adjustment factors for each monitoring data a are placed in the time-series ventilation adjustment factor sample space, thereby constructing the ventilation adjustment factor sequence corresponding to each monitoring data at each time.

[0044] For any given monitoring data point, taking the current time t as an example, the difference value of the ventilation adjustment factor sequence at the current time t is calculated using the following formula. :

[0045] in, This represents the ventilation adjustment factor at the current time t. This represents the ventilation adjustment factor at the previous time t-1. Further, the fluctuation positions where the sign of the difference value changes are marked, and these positions are used as dividing nodes to obtain at least one dividing node. If no dividing node exists in the ventilation adjustment factor sequence, it indicates that the adjustment requirement for the corresponding monitoring data changes unidirectionally within the evaluation period, without any transition characteristics between a suitable and unsuitable state. In this case, the system assigns the effective state factor of the monitoring data... Set it to a preset minimum value, such as 0, and determine that the monitoring data has not reached the adaptation state within the current time period.

[0046] Based on each partition node, the ventilation adjustment factor sequence is divided into two subsequences; each partition node has its own two subsequences, meaning that for any partition node, the ventilation adjustment factor sequence can be divided into two subsequences using the partition node. and .

[0047] Furthermore, for each subsequence, the following formula is used: For example, calculate its monitored fluctuation range. :

[0048] in, It is the absolute value of the ventilation adjustment factor difference at position b' in subsequence B'; The standard deviation of the ventilation adjustment factor in subsequence B' is given by [the number of positions b' in subsequence B']. This results in the ventilation adjustment factor fluctuations under abnormal ventilation conditions exhibiting more pronounced small-amplitude oscillations. In this case, the fluctuation amplitude at each point in the sequence... Fluctuation level of the entire sequence The results will be very close, which indicates that the ventilation state represented by the current sequence in the current time period is closer to the required ventilation state of the attribute. In other words, the current sliding position b is more likely to be used as the distinguishing position between abnormal ventilation state and adaptive ventilation state.

[0049] Furthermore, the monitoring fluctuation amplitude of each subsequence is calculated separately, and the difference in monitoring fluctuation amplitude between the two subsequences corresponding to each dividing node is determined. Specifically, the monitoring fluctuation amplitude of the two subsequences at each dividing node is extracted. Calculate the maximum difference in the monitored fluctuation amplitude. :

[0050] After obtaining the difference in the monitored fluctuation amplitude between the two subsequences corresponding to each dividing node, the dividing node corresponding to the maximum value of the monitored fluctuation amplitude difference is taken as the target dividing node.

[0051] In the two subsequences extracted from the target division node, the proportion of the length of the subsequence corresponding to the maximum value of the two monitored fluctuation amplitudes in the ventilation adjustment factor sequence is taken as the effective state factor of the monitoring data. .

[0052] In essence, for current monitoring data, finding target delineation nodes is about identifying the "inflection point" where ventilation status undergoes a significant change. Effective state factor. This can quantify the persistence of the monitoring data in a "good state" in the near term. Effective state factor. The smaller the value, the longer the monitoring data has been in a suitable ventilation environment.

[0053] Furthermore, after splitting the sequence into two corresponding sub-sequences by the target partitioning node, the degree of single anomaly of monitoring data a in the current ventilation environment is determined. Based on the effective state factor and the anomaly ratio of the current monitoring data, the degree of a single anomaly in the current ventilation environment is determined.

[0054] The degree of a single anomaly in the current ventilation environment is indicated by this single monitoring data point 'a'. The calculation formula is:

[0055] in, This represents the number of elements in the sequence that, at the current moment, a single monitoring data point 'a' conforms to the preset high fluctuation range, i.e., the number of elements in the sequence with the maximum monitored fluctuation range. This represents the number of element values ​​in the ventilation adjustment factor sequence for a single monitoring data point 'a'. The data indicates that the current fluctuation range is more stable, suggesting that the wind speed in the current result is more suitable for data detection of more attributes. This refers to the effective state factor of a single monitoring data point 'a'. It should be noted that the length of the sequence is the same as the number of elements in the sequence.

[0056] This represents the maximum difference in the monitoring fluctuation amplitude corresponding to a single monitoring data point 'a' at the current moment. This is the sum of the maximum differences in monitoring fluctuation amplitudes across all monitoring data at the current moment. A greater degree of anomaly indicates a larger "misfit group" than a "fit group," signifying poorer current ventilation measurements, less pronounced fit advantage, and a more significant anomaly. Conversely, a smaller degree of anomaly indicates a more pronounced stability advantage for the fit group. Let 'a' represent the percentage of abnormal data in the monitoring data. The degree of abnormality in the current ventilation environment is determined by considering the individual abnormality levels of all monitoring data under the current ventilation environment. More specifically, the average of the individual abnormality levels of all monitoring data under the current ventilation environment is taken as the degree of abnormality S of the current ventilation environment.

[0057] The ventilation volume dynamic adjustment module 15 is used to weight the current ventilation volume based on the degree of abnormality of the current ventilation environment, generate a target ventilation volume, determine the control signal level based on the current ventilation volume and the target ventilation volume, and adjust the operating parameters of the ventilation actuator based on the control signal level.

[0058] After determining the degree of abnormality in the current ventilation environment, the ventilation results need to be judged based on the real-time progress of the reaction to accurately control the moisture content in the polycarbodiimide reaction process. Therefore, the introduction of dry gas is achieved by combining real-time fan speed adjustment: First, use the normalized version For the current ventilation Weighted averages are used to generate the target ventilation rate. :

[0059] Where V is the ventilation volume at the current moment. This indicates normalization processing, such as the Z-score normalization method. When the value of norm(S) is greater than 1, the value of norm(S) is set to 1; when the value of norm(S) is less than -1, the value of norm(S) is set to -1, so that the range of norm(S) is maintained between [-1, 1]. Finally, the current ventilation rate is... and target ventilation Simultaneously, a PID controller is input. The PID controller calculates the deviation between the two and outputs a control signal level based on the proportional, integral, and derivative operation rules. This control signal level drives the ventilation actuator, such as a variable frequency fan, to precisely adjust its speed, thereby achieving closed-loop precise control of the moisture content.

[0060] It should be noted that the device provided in the above embodiments is only an example of the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device can be divided into different functional modules to complete all or part of the functions described above.

[0061] Figure 2 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. For example, as shown... Figure 2 As shown, the computer device 20 includes: a memory 21, a processor 22, and a computer program 23 stored in the memory 21 and running on the processor 22, wherein when the processor 22 executes the computer program 23, the computer device can execute any of the aforementioned precise control systems for the moisture content in the polycarbodiimide reaction process.

[0062] Furthermore, embodiments of the present invention also protect an apparatus that may include a memory and a processor, wherein the memory stores executable program code, and the processor is used to call and execute the executable program code to execute a precise moisture content control system for the polycarbodiimide reaction process provided in embodiments of the present invention.

[0063] In this embodiment of the invention, the device can be divided into functional modules according to the above method example. For example, each module can correspond to a separate function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and is only a logical functional division. In actual implementation, there may be other division methods.

[0064] It should be understood that the device provided in this embodiment of the invention is used to implement the above-described precise control system for moisture content during the polycarbodiimide reaction process, and thus can achieve the same effect as the above-described implementation method.

[0065] When using integrated units, the device may include a processing module and a storage module. When applied to a device, the processing module can be used to control and manage the device's operations. The storage module can be used to support the device in executing program code, etc. The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits as described in this disclosure. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of Digital Signal Processing (DSP) and a microprocessor, etc., and the storage module may be a memory.

[0066] In addition, the device provided in the embodiments of the present invention may specifically be a chip, component or module. The chip may include a connected processor and a memory. The memory is used to store instructions. When the processor calls and executes the instructions, the chip can execute a precise moisture content control system for the polycarbodiimide reaction process provided in the above embodiments.

[0067] This invention also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the aforementioned method steps to implement a precise moisture content control system for the polycarbodiimide reaction process provided in the above embodiments.

[0068] This invention also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned steps to achieve a precise control system for moisture content during the polycarbodiimide reaction process provided in the above embodiments.

[0069] In this invention, the apparatus, computer-readable storage medium, computer program product, or chip provided in the embodiments are all used to execute the corresponding methods described above. Therefore, the beneficial effects they achieve can be referred to the beneficial effects in the corresponding methods described above, and will not be repeated here. Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In the embodiments provided by this invention, it should be understood that the disclosed apparatus and method can be implemented in other ways.

[0070] The device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0071] It should also be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0072] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0073] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0074] The above content is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the protection scope of the present invention.

Claims

1. A precise control system for moisture content during the reaction of polycarbodiimide, characterized in that, For use in systems comprising at least two sensors, the system includes the following modules: The data acquisition module is used to collect multi-source monitoring data during the polycarbodiimide reaction process via sensors; The attention evaluation calculation module is used to calculate the attention evaluation value corresponding to each monitoring data based on the real-time data of each monitoring data. The anomaly monitoring indicator filtering module is used to sort the attention evaluation values ​​of all monitoring data at the current time to obtain the attention evaluation sequence, and to filter out anomaly monitoring indicators based on the attention evaluation sequence. The ventilation adjustment factor calculation module is used to calculate the ventilation adjustment factor within a preset time window based on the fluctuation of the attention evaluation value corresponding to the abnormal monitoring indicator and the number of abnormal monitoring indicators. The ventilation environment anomaly analysis module is used to construct a historical sequence of ventilation adjustment factors, calculate the effective state factors of multi-source monitoring data based on the changing trends of the historical sequence of ventilation adjustment factors, and determine the current anomaly level of the ventilation environment by combining the effective state factors of each monitoring data. The ventilation volume dynamic adjustment module is used to weight the current ventilation volume based on the degree of abnormality of the current ventilation environment, generate a target ventilation volume, determine the control signal level based on the current ventilation volume and the target ventilation volume, and adjust the operating parameters of the ventilation actuator based on the control signal level.

2. The precise moisture content control system for the polycarbodiimide reaction process according to claim 1, characterized in that, The collected multi-source monitoring data includes: Set the acquisition frequency for each sensor and broadcast a synchronization clock pulse to each sensor; Real-time data is collected by various sensors at the same time from multiple monitoring data. By associating the real-time data of each monitoring data point with the time of data collection, a time-series data of the monitoring data is formed.

3. The precise moisture content control system for the polycarbodiimide reaction process according to claim 1, characterized in that, The calculation of the attention evaluation value corresponding to each monitoring data point based on real-time data includes: Obtain the monitoring values ​​and maximum allowable values ​​of each monitoring data at the time of collection; Calculate the first ratio between the monitored value and the maximum permissible value; The current wind speed and the maximum wind speed that the sensor can collect are obtained at the time of data acquisition. Calculate the second ratio of the current wind speed to the maximum wind speed; The attention evaluation value corresponding to each monitoring data is calculated based on the first ratio and the second ratio.

4. The precise moisture content control system for the polycarbodiimide reaction process according to claim 1, characterized in that, The attention evaluation values ​​of all monitoring data at the current moment are sorted to obtain an attention evaluation sequence. Anomaly monitoring indicators are then selected based on the attention evaluation sequence, including: Extract the attention evaluation value corresponding to all monitoring data at the current moment; The attention scores are sorted in ascending order of numerical value to obtain the attention score sequence; Calculate the first-order difference sequence of the attention evaluation sequence, and extract the maximum difference value from the first-order difference sequence; Anomaly monitoring indicators are determined based on the maximum difference value.

5. The precise moisture content control system for the polycarbodiimide reaction process according to claim 4, characterized in that, The method for determining anomaly monitoring indicators based on the maximum difference value includes: Obtain the adjacent attention evaluation value corresponding to the maximum difference value; Compare the adjacent attention scores corresponding to the largest difference value and determine the larger value; obtain the maximum value in the attention score sequence. The monitoring data corresponding to the attention evaluation values ​​between the larger and the maximum values ​​are marked as anomaly monitoring indicators.

6. The precise moisture content control system for the polycarbodiimide reaction process according to claim 1, characterized in that, Within a preset time window, the ventilation adjustment factor is calculated based on the fluctuation of the attention evaluation value corresponding to the abnormal monitoring indicator and the number of abnormal monitoring indicators, including: Establish a time window with the current time as the endpoint, and extract the attention evaluation sequence of anomaly monitoring indicators within the time window; Calculate the volatility deviation based on the attention evaluation sequence; The ventilation adjustment factor is calculated by combining the ratio of the number of abnormal monitoring indicators to the total number of monitoring indicators within the statistical time window with the fluctuation deviation.

7. The precise moisture content control system for the polycarbodiimide reaction process according to claim 6, characterized in that, The calculation of volatility deviation based on the attention evaluation sequence includes: Calculate the mean and standard deviation of the attention evaluation sequence; Compare the difference between the attention evaluation value and the mean, and determine the standardized deviation value in combination with the standard deviation; The degree of volatility deviation is determined based on the standardized deviation value.

8. The precise moisture content control system for the polycarbodiimide reaction process according to claim 1, characterized in that, The construction of the ventilation adjustment factor historical sequence and the calculation of the effective state factor of multi-source monitoring data based on the changing trend of the ventilation adjustment factor historical sequence include: Construct a ventilation adjustment factor sequence for each monitoring data point over a historical time period; Calculate the difference values ​​between adjacent time points in the ventilation adjustment factor sequence, mark the fluctuation positions where the signs of the difference values ​​change as dividing nodes, and obtain at least one dividing node; Based on each dividing node, the ventilation adjustment factor sequence is divided into two subsequences; each dividing node has its own two corresponding subsequences. Calculate the monitoring fluctuation amplitude of each subsequence separately, and determine the difference in monitoring fluctuation amplitude between the two subsequences corresponding to each dividing node; The node corresponding to the maximum difference in the monitored fluctuation amplitude is used as the target node. For the target division node, the length ratio of the subsequence corresponding to the maximum value of the two monitoring fluctuation amplitudes in the ventilation adjustment factor sequence is taken as the effective state factor of the monitoring data.

9. A precise moisture content control system for the polycarbodiimide reaction process according to claim 8, characterized in that, The effective state factors, which integrate various monitoring data, determine the degree of anomaly in the current ventilation environment, including: Obtain the effective state factors of each monitoring data; Calculate the percentage of the maximum difference in the current monitoring data's fluctuation range to the sum of the maximum differences in the monitoring fluctuation ranges of all monitoring data, and use this percentage as the abnormality rate of the current monitoring data. Based on the effective state factor and the anomaly ratio of the current monitoring data, determine the degree of a single anomaly in the current ventilation environment. The degree of anomaly in the current ventilation environment is determined by combining the degree of a single anomaly from all monitoring data under the current ventilation environment.

10. A precise moisture content control system for the polycarbodiimide reaction process according to claim 1, characterized in that, The process of weighting the current ventilation volume based on the degree of abnormality of the current ventilation environment to generate a target ventilation volume, and determining the control signal level based on the current ventilation volume and the target ventilation volume, includes: The abnormality value of the current ventilation environment is normalized, and the normalized abnormality value is used to weight the current ventilation volume. The weighted result is used as the target ventilation volume. The current ventilation rate and the target ventilation rate are input into a preset PID controller. The PID controller outputs a control signal level, and the operating parameters of the ventilation actuator are adjusted according to the control signal level.

Images