Temperature-sensing antifreeze formulation optimization device

Abstract

This application provides a temperature-sensing-based antifreeze formulation optimization device, belonging to the field of temperature measurement technology. The device includes: a temperature sensing module that collects real-time temperature data of the antifreeze and constructs an antifreeze operating temperature state vector; a temperature trend discrimination module that performs temperature evolution trend discrimination and generates temperature evolution category identifiers; a demand analysis module that performs target equivalent antifreeze capability range analysis; a formulation state control module that performs comparative analysis with the current formulation state parameters and generates formulation control instructions; and a cumulative optimization module that performs control and adaptive update optimization of the formulation control instructions. This application solves the problem of mismatch between antifreeze capability and operating conditions caused by the lack of an adaptive control mechanism, realizing intelligent sensing and dynamic control of antifreeze based on temperature state vectors and evolution categories, achieving the technical effects of accurately configuring antifreeze capability, reducing freezing risk, and improving system operation stability and efficiency.

Description

Technical Field

[0001] This application relates to the field of temperature measurement technology, and in particular to an antifreeze formulation optimization device based on temperature sensing. Background Technology

[0002] With the increasing application of industrial equipment, transportation systems, and complex environmental operating systems under conditions of low temperature, extreme cold, and frequent temperature fluctuations, antifreeze, as a crucial functional material for ensuring safe system operation and preventing media freezing failure, is widely used in power systems, pipeline systems, heat exchange systems, and various closed or semi-closed operating environments. The stability and adaptability of its antifreeze performance directly affect equipment reliability and system safety. Especially in application scenarios with variable climate conditions, frequent temperature fluctuations, and complex operating conditions, antifreeze not only needs to possess basic antifreeze capabilities but also needs to adapt to dynamic changes in ambient temperature to avoid freezing risks caused by sudden temperature drops, freeze-thaw cycles, or localized low-temperature concentrations. This places higher demands on the formulation design, control methods, and operational management of antifreeze.

[0003] Currently, most existing antifreeze technologies employ a fixed formulation or static ratio design approach. This involves pre-adding a certain proportion of antifreeze components to the antifreeze to cover the expected minimum operating temperature range. Such technologies prioritize meeting extreme low-temperature conditions, lacking the ability to perceive and respond to dynamic temperature changes during actual operation. In practical applications, there is often a significant difference between the ambient temperature of the antifreeze and the internal system temperature, with temperature changes exhibiting phased, sudden, or periodic characteristics. Existing technologies generally rely on single-point temperature monitoring or empirical threshold judgments, failing to comprehensively reflect the actual thermal conditions of the antifreeze. Furthermore, existing antifreeze formulation adjustments are mostly based on manual intervention or preset rule control, lacking a systematic analysis mechanism for temperature change trends, the evolution of freezing risk, and historical control effects. This results in antifreeze capacity configurations often being redundant or delayed, increasing resource consumption and operating costs, and potentially causing system performance fluctuations due to untimely or excessive adjustments.

[0004] In summary, existing technologies suffer from several technical problems. These include a lack of multi-dimensional and continuous sensing capabilities for ambient and internal system temperatures during antifreeze operation, a lack of refined judgment and prediction mechanisms for temperature evolution trends and freezing risks, and a lack of formulation control methods that can adaptively optimize formulations based on historical control behaviors. Consequently, the antifreeze capacity of antifreeze is difficult to dynamically match actual operating conditions, further affecting the antifreeze reliability, system operational stability, and overall efficiency of antifreeze in complex temperature environments. Summary of the Invention

[0005] The purpose of this application is to provide a temperature-sensing-based antifreeze formulation optimization device to solve the technical problems in the prior art. These problems stem from the lack of multi-dimensional and continuous sensing capabilities for ambient and internal system temperatures during antifreeze operation, the lack of a refined judgment and prediction mechanism for temperature evolution trends and freezing risks, and the lack of a formulation control method that can adaptively optimize formulations by incorporating historical control behaviors. Consequently, the antifreeze capacity of the antifreeze is difficult to dynamically match actual operating conditions, further affecting the antifreeze reliability, system operational stability, and overall efficiency of the antifreeze in complex temperature environments.

[0006] In view of the above problems, this application provides a temperature-sensing-based antifreeze formulation optimization device, comprising: a temperature sensing module, used to periodically collect real-time temperature data of the environment and system inside the antifreeze during antifreeze use, and construct an antifreeze operating temperature state vector based on the real-time temperature data; a temperature trend discrimination module, used to perform temperature evolution trend discrimination based on the antifreeze operating temperature state vector, and generate a temperature evolution category identifier, wherein the temperature evolution category identifier includes steady-state low temperature condition, rapid cooling condition, and freeze-thaw cycle condition; a demand analysis module, used to call the antifreeze formulation controller based on the temperature evolution category identifier, and perform analysis of the target equivalent antifreeze capacity range required by the antifreeze under the current operating condition; a formulation state control module, used to read the current formulation state parameters of the antifreeze, perform a comparative analysis of the current formulation state parameters and the target equivalent antifreeze capacity range, and generate a formulation control command; and a cumulative optimization module, used to perform control according to the formulation control command, and perform time series cumulative analysis on the operating temperature state vector, and perform adaptive update optimization of the formulation control command.

[0007] Preferably, the temperature-sensing-based antifreeze formulation optimization device further includes: a condition cognition unit that synchronously inputs the temperature evolution category identifier and the antifreeze operating temperature state vector into the antifreeze formulation controller; using the condition cognition unit to perform time-series feature decoupling processing on the antifreeze operating temperature state vector, and adaptively adjusting the weights of different features in conjunction with the temperature evolution category identifier to form a condition cognition feature set characterizing the freezing risk evolution rate and operating condition characteristics; based on the condition cognition feature set, calling the capability requirement reasoning unit to reason about the adaptation stability of different antifreeze capability response states under the current temperature evolution category identifier, generating a candidate equivalent antifreeze capability interval set; performing consistency and redundancy analysis on the candidate equivalent antifreeze capability interval set to construct the target equivalent antifreeze capability interval.

[0008] Preferably, the antifreeze formulation optimization device based on temperature sensing further includes: performing temporal decomposition and multi-scale dynamic feature extraction of the antifreeze operating temperature state vector to construct multi-scale dynamic features; performing correlation analysis and weighted evaluation on the multi-scale dynamic features for short-term rapid changes and long-term stable trends of temperature behavior at different time scales to construct an initial temperature evolution classification signal; and performing dual backtracking verification analysis on the initial temperature evolution classification signal to construct a temperature evolution category identifier.

[0009] Preferably, the antifreeze formulation optimization device based on temperature sensing further includes: performing reverse backtracking analysis on the antifreeze operating temperature state vector and initial temperature evolution classification signal collected during the current startup cycle along the time series to identify evolution consistency and abrupt change behavior, and establishing a backtracking correction signal for the current startup cycle; calling temperature evolution classification signals from multiple historical startup cycles, performing multiple rounds of startup verification based on the calling results, and generating a startup correction signal; and performing dual backtracking verification analysis using the backtracking correction signal and the startup correction signal to construct a temperature evolution category identifier.

[0010] Preferably, the antifreeze formulation optimization device based on temperature sensing further includes: adjusting the intensity or activation state of the adjustable parameters of the antifreeze according to the formulation control command, and simultaneously recording the current control action and the action temperature response characteristics; calculating the cumulative effect, trend evolution and response consistency of the formulation control command under different temperature conditions based on the current control action, action temperature response characteristics, antifreeze operating temperature state vector and historical data, forming a cumulative optimization feature set to complete the time series cumulative analysis.

[0011] Preferably, the antifreeze formulation optimization device based on temperature sensing further includes: performing multi-dimensional data analysis on the temperature response amplitude, temperature change rate, freezing risk evolution trend and historical control response deviation in the cumulative optimization feature set, calculating the response contribution and reliability index of the control action in different time windows; and performing adaptive correction and update based on the calculation results.

[0012] Preferably, the temperature-sensing-based antifreeze formulation optimization device further includes: a trend prediction module, used to perform evolution trend and freezing risk prediction of the antifreeze operating temperature state vector according to the cumulative optimization feature set, and establish prediction results; and a feedback module, used to configure the activation order, effect intensity and response priority of adjustable parameters according to the prediction results, and perform predictive optimization and update of formulation control instructions according to the configuration results.

[0013] Preferably, the antifreeze formulation optimization device based on temperature sensing further includes: the temperature sensing module adopts a multi-point temperature acquisition strategy to synchronously acquire temperature data of the environment where the antifreeze is located and key locations inside the system, so as to construct an antifreeze operating temperature state vector with consistent spatial distribution.

[0014] Preferably, the antifreeze formulation optimization device based on temperature sensing further includes: a temperature trend discrimination module that performs noise suppression and outlier filtering on the antifreeze operating temperature state vector when performing temperature evolution trend discrimination based on the antifreeze operating temperature state vector.

[0015] Preferably, the temperature-sensing-based antifreeze formulation optimization device further includes: when generating formulation control instructions, the formulation state control module invokes the rate of change constraint to perform formulation control generation constraint management.

[0016] The technical solution provided in this application has at least the following technical effects or advantages: by realizing the technical goal of dynamic sensing and intelligent control of antifreeze formulation based on operating temperature state vector and temperature evolution category identification, it achieves the technical effect of accurately configuring, responding in advance and continuously optimizing the antifreeze capability of antifreeze under different temperature evolution conditions, improving the stability of antifreeze performance, reducing the probability of freezing risk, and taking into account both system operation safety and resource utilization efficiency.

[0017] The above description is merely an overview of the technical solution of this application. To enable a clearer understanding of the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in this application 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 merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the antifreeze formulation optimization device based on temperature sensing according to this application.

[0020] Figure 2 This is a schematic diagram of the process by which the demand analysis module performs the target equivalent antifreeze capability range analysis in the temperature-sensing-based antifreeze formulation optimization device of this application.

[0021] Figure labeling: Temperature sensing module 1, Temperature trend judgment module 2, Demand analysis module 3, Formula status control module 4, Cumulative optimization module 5. Detailed Implementation

[0022] This application provides a temperature-sensing-based antifreeze formulation optimization device, addressing the technical problems in existing technologies. These problems stem from a lack of multi-dimensional, continuous sensing capabilities for ambient and internal system temperatures during antifreeze operation; a lack of refined mechanisms for judging and predicting temperature evolution trends and freezing risks; and a lack of adaptive optimization methods that incorporate historical control behavior. These shortcomings lead to difficulties in dynamically matching antifreeze performance to actual operating conditions, further impacting the reliability of antifreeze in complex temperature environments, system stability, and overall efficiency. The device achieves the technical goal of dynamic sensing and intelligent control of antifreeze formulations based on operating temperature state vectors and temperature evolution category identification. This results in precise configuration, early response, and continuous optimization of antifreeze performance under different temperature evolution conditions, improving the stability of antifreeze performance, reducing the probability of freezing risks, and balancing system operational safety and resource utilization efficiency.

[0023] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0024] Please see Figure 1 and Figure 2 This application provides a temperature-sensing-based antifreeze formulation optimization device, specifically including: Temperature sensing module 1 is used to periodically collect real-time temperature data of the environment where the antifreeze is located and inside the system during the use of antifreeze, and to construct an antifreeze operating temperature state vector based on the real-time temperature data.

[0025] Furthermore, this application also includes: the temperature sensing module 1 adopts a multi-point temperature acquisition strategy to synchronously acquire temperature data of the environment where the antifreeze is located and key locations inside the system, so as to construct an antifreeze operating temperature state vector with consistent spatial distribution.

[0026] Specifically, during antifreeze use, periodic data collection refers to continuous or intermittent temperature monitoring of the external environment surrounding the antifreeze and key locations within the system that come into contact with or are affected by it, according to preset time intervals or triggering conditions. This ensures that the acquired temperature data accurately reflects the thermal environment changes experienced by the antifreeze under actual operating conditions, thereby avoiding temperature information distortion caused by single-point or instantaneous sampling. The antifreeze environment refers to the external space or medium in which the antifreeze is exposed or operates, including but not limited to ambient air, surrounding media, or the external temperature field. This ambient temperature characterizes the impact of external climatic conditions or operating condition changes on the antifreeze performance. The system interior refers to the internal areas of equipment, pipelines, containers, or key functional components that directly or indirectly exchange heat with the antifreeze. Its internal temperature reflects the actual heat load and heat transfer state experienced by the antifreeze during system operation.

[0027] Furthermore, real-time temperature data refers to numerical temperature information acquired instantly by the temperature sensing unit during the use of antifreeze. Real-time temperature data has a timestamp and is continuously updated over time. It is used to describe the dynamic changes in the temperature of the antifreeze-related environment and the internal temperature of the system, thereby providing basic data support for subsequent temperature trend analysis and status judgment.

[0028] Furthermore, constructing an antifreeze operating temperature state vector based on real-time temperature data involves uniformly formatting, aligning, and combining features of collected multi-source, multi-time temperature data. Temperature information from different acquisition locations and time scales is mapped into a vectorized data structure according to predetermined dimensions, forming a state vector that comprehensively characterizes the current and historical operating temperature states of the antifreeze. Thus, the antifreeze operating temperature state vector can reflect the spatial temperature distribution characteristics, temporal evolution characteristics, and the correlation between environmental and internal system temperatures during antifreeze use within the same data representation framework. This provides a unified and computable basic state description for subsequent temperature evolution trend judgment, antifreeze capacity requirement analysis, and formulation control decisions.

[0029] Furthermore, the multi-point temperature acquisition strategy adopted in the antifreeze temperature monitoring process refers to setting up multiple temperature acquisition nodes distributed in different locations within the environment where the antifreeze is located and within the system where heat exchange occurs with the antifreeze, so as to simultaneously acquire temperature information from multiple acquisition points. This avoids the problem that a single acquisition location cannot fully reflect the actual thermal conditions of the antifreeze, thereby improving the completeness and representativeness of the temperature sensing results.

[0030] Furthermore, synchronous acquisition of temperature data of the environment where the antifreeze is located and key locations within the system refers to the simultaneous acquisition of external ambient temperature and temperature data of key locations within the system under a unified time reference. The time synchronization mechanism ensures that temperature data from different acquisition points correspond at the same time, thereby eliminating the impact of time deviation on the analysis of temperature spatial distribution and enabling the acquired temperature data to accurately reflect the overall thermal state of the antifreeze at the same time cross section.

[0031] Subsequently, constructing a spatially consistent antifreeze operating temperature state vector refers to integrating synchronously collected multi-point temperature data according to a preset spatial mapping relationship and data structure, and uniformly encoding the temperature information of different spatial locations into a vectorized expression form, so that the temperature state vector can simultaneously characterize the temperature distribution characteristics of the antifreeze in the spatial dimension and the consistency of its overall operating state.

[0032] Temperature trend discrimination module 2 is used to perform temperature evolution trend discrimination based on the antifreeze operating temperature state vector and generate temperature evolution category identifiers, including steady-state low temperature conditions, rapid cooling conditions, and freeze-thaw cycle conditions.

[0033] Furthermore, this application also includes: performing temporal decomposition and multi-scale dynamic feature extraction of the antifreeze operating temperature state vector to construct multi-scale dynamic features; performing correlation analysis and weighted evaluation on the multi-scale dynamic features for short-term rapid changes and long-term stable trends of temperature behavior at different time scales to construct an initial temperature evolution classification signal; and performing dual backtracking verification analysis on the initial temperature evolution classification signal to construct a temperature evolution category identifier.

[0034] Furthermore, this application also includes: performing reverse backtracking analysis on the antifreeze operating temperature state vector and initial temperature evolution classification signal collected during the current startup cycle along the time series to identify evolution consistency and abrupt change behavior, and establishing a backtracking correction signal for the current startup cycle; calling temperature evolution classification signals from multiple historical startup cycles, performing multiple rounds of startup verification based on the calling results, and generating a startup correction signal; and performing dual backtracking verification analysis using the backtracking correction signal and the startup correction signal to construct a temperature evolution category identifier.

[0035] Furthermore, this application also includes: when the temperature trend discrimination module 2 performs temperature evolution trend discrimination based on the antifreeze operating temperature state vector, it performs noise suppression and outlier filtering processing on the antifreeze operating temperature state vector.

[0036] Specifically, performing temporal decomposition and multi-scale dynamic feature extraction of the antifreeze operating temperature state vector refers to expanding the antifreeze operating temperature state vector in chronological order and decomposing the continuous temperature sequence into multiple subsequences with different time resolutions based on preset time scale division rules. This allows for the extraction of dynamic features reflecting transient temperature fluctuations, rapid change amplitudes, and change rates at short time scales, while simultaneously extracting dynamic features characterizing temperature change trends, periodicity, and stability at longer time scales. This constructs a multi-scale dynamic feature set that can simultaneously reflect temperature behavior characteristics at different time scales.

[0037] Furthermore, the correlation analysis and weighted evaluation of the short-term rapid changes and long-term stable trends of temperature behavior at different time scales for multi-scale dynamic features refers to the correlation calculation and consistency comparison of the rapid change features extracted from the short time scale and the stable trend features extracted from the long time scale under a unified analysis framework. Based on the contribution and reliability of various features in the identification of different working conditions, corresponding weights are assigned. The interaction between transient changes and long-term trends in the current temperature behavior is comprehensively measured through weighted evaluation, thereby forming an initial temperature evolution classification signal that can reflect the overall characteristics of temperature evolution.

[0038] Subsequently, the antifreeze operating temperature state vector and initial temperature evolution classification signal collected during the current startup cycle are analyzed in reverse chronological order. This means that the time period from the initial startup of the antifreeze to its stable operation is taken as a startup cycle. The antifreeze operating temperature state vector and the initial temperature evolution classification signal generated based on the vector are processed in reverse chronological order. By comparing and analyzing the correspondence between the early temperature state and the subsequent temperature change results, it is possible to identify whether the temperature evolution process maintains a continuous and consistent change pattern, or whether there are abrupt changes caused by external interference, transient load changes, or other factors. This establishes a retrospective correction signal to correct the temperature evolution judgment results during the current startup cycle.

[0039] Furthermore, calling the temperature evolution classification signals from multiple historical startup cycles refers to reading the temperature evolution classification results formed by the antifreeze during previous startup operations from the storage unit, using the read historical classification signals as a reference benchmark, and performing multiple rounds of startup verification analysis based on the operating characteristics of the current startup cycle. By comparing the similarity, consistency, and degree of deviation of the temperature evolution patterns between different startup cycles, a startup correction signal is generated to reflect the difference between the current startup behavior and the typical historical startup behavior.

[0040] Subsequently, a dual backtracking verification analysis is performed using backtracking correction signals and start-up correction signals. This means that during the temperature evolution discrimination process, the backtracking correction results within the current start-up cycle and the historical start-up correction results across multiple start-up cycles are introduced simultaneously to jointly verify and comprehensively correct the initial temperature evolution classification conclusion. The dual verification mechanism eliminates the risk of misjudgment caused by single-time-dimension analysis, thereby constructing a temperature evolution category identifier with higher stability and reliability.

[0041] Temperature evolution categories include steady-state low-temperature conditions, rapid cooling conditions, and freeze-thaw cycle conditions. Among them, steady-state low-temperature conditions indicate a state in which the temperature fluctuates within a low range with a relatively stable trend. Rapid cooling conditions indicate a state in which the temperature drops significantly in a short period of time with a large rate of change. Freeze-thaw cycle conditions indicate a state in which the temperature fluctuates repeatedly around the freezing threshold and exhibits periodic freezing and thawing characteristics.

[0042] Furthermore, when performing temperature evolution trend discrimination based on the antifreeze operating temperature state vector, the temperature trend discrimination module preprocesses the input antifreeze operating temperature state vector before analyzing and classifying the antifreeze temperature change pattern. This ensures that the data used for trend discrimination has sufficient stability and reliability, thereby avoiding the adverse effects of interference factors in the original temperature data on the discrimination results.

[0043] Furthermore, noise suppression and outlier filtering of the antifreeze operating temperature state vector refers to weakening or smoothing random noise introduced by sensor jitter, environmental interference, or communication errors in the temperature state vector through preset data processing rules or algorithms. At the same time, it identifies and removes abnormal temperature data points that deviate significantly from the normal range of change, so that the processed temperature state vector can more realistically reflect the actual temperature change behavior of the antifreeze.

[0044] Subsequently, the antifreeze operating temperature state vector, after noise suppression and outlier filtering, is used to perform temperature evolution trend discrimination. This enables the temperature trend discrimination module to identify the evolution direction, rate of change, and stability characteristics of temperature changes based on relatively clean and continuous data, thereby improving the accuracy and robustness of temperature evolution trend discrimination.

[0045] The requirements analysis module 3 is used to call the antifreeze formulation controller based on the temperature evolution category identifier to perform the target equivalent antifreeze capacity range analysis required by the antifreeze under the current operating conditions.

[0046] Furthermore, this application also includes: synchronously inputting the temperature evolution category identifier and the antifreeze operating temperature state vector into the operating condition recognition unit of the antifreeze formulation controller; using the operating condition recognition unit to perform time-series feature decoupling processing on the antifreeze operating temperature state vector, and adaptively adjusting the weights of different features in conjunction with the temperature evolution category identifier to form an operating condition recognition feature set characterizing the freezing risk evolution rate and operating condition characteristics; based on the operating condition recognition feature set, calling the capability requirement reasoning unit to reason about the adaptation stability of different antifreeze capability response states under the current temperature evolution category identifier, generating a candidate equivalent antifreeze capability interval set; performing consistency and redundancy analysis on the candidate equivalent antifreeze capability interval set to construct the target equivalent antifreeze capability interval.

[0047] Specifically, synchronously inputting the temperature evolution category identifier and the antifreeze operating temperature state vector into the operating condition cognition unit of the antifreeze formulation controller means that during the antifreeze formulation control process, the temperature evolution category identifier, which is used to characterize the current temperature change pattern, and the operating temperature state vector, which is used to describe the real-time and historical temperature status of the antifreeze, are aligned in the time dimension and simultaneously transmitted to the operating condition cognition unit inside the antifreeze formulation controller. This allows the operating condition cognition unit to comprehensively perceive the temperature evolution background and specific temperature operating status of the antifreeze in a unified data context.

[0048] Furthermore, the use of the operating condition cognitive unit to decouple the antifreeze operating temperature state vector by time series features refers to separating and independently modeling the temperature features with different time scales and different change frequencies in the operating temperature state vector to distinguish short-term temperature disturbances, phased change trends and long-term stable features. In addition, the importance of various time series features in the current operating condition judgment is adaptively adjusted by combining the temperature evolution category label, thereby forming a set of operating condition cognitive features that can simultaneously characterize the freezing risk evolution rate, temperature change sensitivity and overall operating condition characteristics.

[0049] Subsequently, based on the set of operating condition cognitive features, the capability requirement reasoning unit is invoked to reason about the adaptation stability of different antifreeze capability response states under the current temperature evolution category. This means that the formed operating condition cognitive features are used as input conditions, and the capability requirement reasoning unit is introduced to compare and analyze multiple preset antifreeze capability response states. By evaluating the suppression effect, response persistence, and operational stability of each antifreeze capability response state on the freezing risk under the current temperature evolution mode, multiple candidate equivalent antifreeze capability intervals that meet the current operating condition requirements are inferred, thereby constructing a set of candidate equivalent antifreeze capability intervals.

[0050] Furthermore, the consistency and redundancy analysis of the candidate equivalent antifreeze capability range set refers to the comprehensive judgment of the coverage relationship, overlap degree and boundary rationality between different candidate equivalent antifreeze capability ranges. By eliminating redundant ranges with functional overlap or similar control effects, and retaining ranges that show stable adaptability under different operating conditions, the target equivalent antifreeze capability range that can accurately reflect the actual needs of the current antifreeze is finally constructed.

[0051] Formula status control module 4 is used to read the current formula status parameters of the antifreeze, perform a comparative analysis between the current formula status parameters and the target equivalent antifreeze capacity range, and generate formula control instructions.

[0052] Furthermore, this application also includes: when generating formula control instructions, the formula state control module 4 calls the change rate limit constraint to perform formula control generation constraint management.

[0053] Specifically, reading the current formulation status parameters of the antifreeze refers to obtaining parameter information from the antifreeze formulation management unit or storage unit to characterize the current compositional state and effectiveness of the antifreeze. The formulation status parameters include the proportioning information of various antifreeze components, the activation state of adjustable functional components, their effectiveness and corresponding control variables, thereby forming a formulation status description that reflects the actual level of the antifreeze's current antifreeze capability.

[0054] Furthermore, the comparative analysis of the current formulation state parameters and the target equivalent antifreeze capability range involves mapping the actual equivalent antifreeze capability corresponding to the formulation state parameters to a pre-constructed capability evaluation space and comparing it with the target equivalent antifreeze capability range determined based on the current temperature conditions. By judging whether the current antifreeze capability is within the target range and whether there is insufficient or excessive configuration, the degree and direction of deviation between the antifreeze formulation state and the target requirement are identified. Based on the deviation results obtained from the comparative analysis, the specific content that needs to be adjusted in the antifreeze formulation is determined, and formulation control instructions are generated and output in the form of instructions to drive the formulation control execution unit. The formulation control instructions are used to indicate the adjustment direction, adjustment range, or activation state change of each adjustable parameter, so that the actual equivalent antifreeze capability of the antifreeze gradually approaches and is stably maintained within the target equivalent antifreeze capability range.

[0055] Furthermore, when generating formula control instructions, calling the rate of change constraint means introducing constraint rules for the rate of change of formula parameters. This is used to limit the maximum allowable change range or adjustment rate of each adjustable parameter per unit time, so as to prevent excessive fluctuations in antifreeze performance, abnormal temperature response, or unstable system operation due to excessive control range or rapid change.

[0056] Subsequently, the implementation of formula regulation generation constraint management refers to the unified management and verification of the formula regulation instruction generation process under the constraint of change rate limitation, so that the final output formula regulation instruction meets the target antifreeze capability requirements while conforming to the preset change rate, safety and stability requirements, thereby realizing the controlled generation of formula regulation behavior.

[0057] The cumulative optimization module 5 is used to execute control according to the formula control instructions, perform time series cumulative analysis on the operating temperature state vector, and perform adaptive update optimization of the formula control instructions.

[0058] Furthermore, this application also includes: adjusting the intensity or activation state of the adjustable parameters of the antifreeze according to the formulation control instructions, and simultaneously recording the current control action and the action temperature response characteristics; based on the current control action, action temperature response characteristics, antifreeze operating temperature state vector and historical data, calculating the cumulative effect, trend evolution and response consistency of the formulation control instructions under different temperature conditions, forming a cumulative optimization feature set to complete the time series cumulative analysis.

[0059] Furthermore, this application also includes: performing multi-dimensional data analysis on the temperature response amplitude, temperature change rate, freezing risk evolution trend, and historical control response deviation in the cumulative optimized feature set, calculating the response contribution and reliability index of the control action in different time windows; and performing adaptive correction and update based on the calculation results.

[0060] Furthermore, this application also includes: a trend prediction module, used to perform evolution trend and freezing risk prediction of the antifreeze operating temperature state vector based on the cumulative optimized feature set, and establish prediction results; and a feedback module, used to configure the activation order, effect intensity and response priority of adjustable parameters based on the prediction results, and to perform prediction optimization and update of the formula control instructions based on the configuration results.

[0061] Specifically, executing control according to formulation adjustment instructions refers to receiving formulation adjustment instructions during the antifreeze formulation optimization process, parsing them into specific control operation parameters, and driving the corresponding actuators or control units to control the adjustable component parameters in the antifreeze formulation. Control includes activating or inhibiting adjustable functional components, adjusting their intensity, controlling release rhythm, and configuring response priorities, thereby causing the actual antifreeze performance of the antifreeze to change in the direction indicated by the adjustment instructions. Furthermore, control is performed under the premise of meeting system safety constraints and operational stability requirements. Through refined management of control variables during the adjustment process, the antifreeze formulation state can smoothly transition to the target equivalent antifreeze capability range, avoiding abnormal temperature response or system operational risks caused by abrupt adjustments.

[0062] Adjusting the intensity or activation state of adjustable parameters of antifreeze according to the formula control instructions refers to performing corresponding control operations on the functional parameters with adjustable characteristics in antifreeze after receiving the formula control instructions. Adjustable parameters include the release ratio of antifreeze enhancement components, duration of action, activation or inhibition state, and response level. By changing their intensity or activation state, the actual antifreeze capability of antifreeze under the current operating conditions is adjusted in the expected direction.

[0063] Simultaneously recording the current control action and its temperature response characteristics means that during the execution of the formula control instructions, the execution time, control amplitude, target, and temperature change after each control operation are recorded in real time. The temperature response characteristics are used to describe the correspondence between the control action and the change in the antifreeze operating temperature, so as to analyze the impact of the control behavior on temperature evolution.

[0064] Furthermore, based on current control actions, temperature response characteristics, antifreeze operating temperature state vector, and historical data, the cumulative effect, trend evolution, and response consistency of formulation control commands under different temperature conditions are calculated. This involves comprehensively considering current control behavior and historical control records in the time series dimension, performing correlation analysis between the temperature response triggered by the control action and the antifreeze operating temperature state vector, and calculating the superposition effect, trend, and stability of multiple control results under different temperature conditions to evaluate the overall effectiveness and reliability of formulation control commands in long-term operation. Subsequently, a cumulative optimization feature set is formed to complete the time series cumulative analysis. This involves unifying and characterizing the calculated cumulative effect indicators, trend evolution characteristics, and response consistency results to construct a cumulative optimization feature set to characterize the comprehensive performance of formulation control behavior in the time dimension, thereby achieving a systematic time series cumulative analysis of the antifreeze formulation control effect.

[0065] Multidimensional data analysis of temperature response amplitude, temperature change rate, freezing risk evolution trend, and historical control response deviation in the cumulative optimization feature set refers to the joint analysis of multiple key indicators used to characterize the control effect in the cumulative optimization feature set after completing the time series cumulative analysis. Among them, temperature response amplitude describes the degree of temperature change caused by the control action, temperature change rate reflects the speed of temperature change over time, freezing risk evolution trend describes the direction and evolution law of freezing risk changes during operation, and historical control response deviation characterizes the deviation between historical control results and expected control effects. By analyzing the above indicators in the multidimensional feature space, the correlation and influence weight between different dimensions are extracted.

[0066] Furthermore, calculating the response contribution and reliability index of control actions in different time windows refers to dividing the effects of control actions into different time windows based on multidimensional data analysis, evaluating the actual contribution of each control action to temperature change and freezing risk suppression on short-term, medium-term and long-term time scales, and calculating the reliability index of each control action in the corresponding time window by combining historical response deviation and consistency performance, so as to measure the stability and reliability of control behavior under different operating conditions and time scales.

[0067] Subsequently, adaptive correction and update are performed based on the calculation results. This means that the generation rules, parameter weights, or control strategies of subsequent formula control instructions are dynamically adjusted based on the obtained response contribution and reliability indicators. By strengthening control methods with high contribution and high reliability and suppressing control methods with low contribution or insufficient reliability, the formula control mechanism can be continuously optimized during operation to adapt to changes in different temperature conditions and freezing risk evolution characteristics.

[0068] The device also includes a trend prediction module, which is a functional module for forward-looking analysis further incorporated into the overall structure of the antifreeze formulation optimization device. The trend prediction module uses a cumulative optimized feature set as input, which comprehensively reflects the antifreeze's regulation history, response characteristics, and freezing risk evolution under different temperature conditions. By modeling and extrapolating this feature set, it performs evolution trend analysis and freezing risk prediction of the antifreeze operating temperature state vector, thereby generating prediction results characterizing the temperature change trend and potential freezing risk level over a future period.

[0069] Furthermore, the feedback module refers to the control feedback unit that forms a linkage with the trend prediction module. Based on the prediction results, the feedback module pre-configures the control strategies for each adjustable parameter in the antifreeze formulation. The configuration includes the activation order, intensity of action, and response priority of different adjustable parameters in the multi-parameter coordinated control process. This configuration enables the antifreeze formulation to have the corresponding control preparation capability before the predicted temperature evolution and freezing risk changes arrive. Subsequently, the prediction optimization update of the formulation control instructions based on the configuration results refers to converting the parameter configuration scheme generated by the feedback module into a forward-looking formulation control instruction, and optimizing and correcting the original control instruction generation rules before actual execution. This ensures that the formulation control instructions can not only respond to the current operating conditions, but also adjust in advance for predicted temperature change trends and freezing risk evolution, thereby improving the timeliness and overall stability of antifreeze formulation control.

[0070] In summary, the temperature-sensing-based antifreeze formulation optimization device provided in this application has the following technical effects: by achieving the technical goal of dynamic sensing and intelligent control of antifreeze formulation based on operating temperature state vector and temperature evolution category identification, it achieves the technical effects of accurately configuring, responding in advance and continuously optimizing the antifreeze capability of antifreeze under different temperature evolution conditions, improving the stability of antifreeze performance, reducing the probability of freezing risk, and taking into account both system operation safety and resource utilization efficiency.

[0071] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0072] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A device for optimizing antifreeze formulations based on temperature sensing, characterized in that, The device includes: The temperature sensing module is used to periodically collect real-time temperature data of the environment where the antifreeze is located and the system inside during the use of the antifreeze, and to construct an antifreeze operating temperature state vector based on the real-time temperature data. The temperature trend discrimination module is used to perform temperature evolution trend discrimination based on the antifreeze operating temperature state vector and generate temperature evolution category identifiers, including steady-state low temperature conditions, rapid cooling conditions, and freeze-thaw cycle conditions. The requirements analysis module is used to call the antifreeze formulation controller based on the temperature evolution category identifier to perform the target equivalent antifreeze capacity range analysis required by the antifreeze under the current operating conditions. The formulation status control module is used to read the current formulation status parameters of the antifreeze, perform a comparative analysis between the current formulation status parameters and the target equivalent antifreeze capacity range, and generate formulation control instructions. The cumulative optimization module is used to execute control according to the formula control instructions, perform time series cumulative analysis on the operating temperature state vector, and perform adaptive update optimization of the formula control instructions.

2. The antifreeze formulation optimization device based on temperature sensing as described in claim 1, characterized in that, In the requirements analysis module, based on the temperature evolution category identifier, the antifreeze formulation controller is invoked to perform an analysis of the target equivalent antifreeze capacity range required by the antifreeze under the current operating conditions, including: The temperature evolution category identifier and the antifreeze operating temperature state vector are synchronously input into the operating condition recognition unit of the antifreeze formulation controller; The operating condition cognition unit is used to decouple the antifreeze operating temperature state vector from time-series features, and the weights of different features are adaptively adjusted in combination with the temperature evolution category identifier to form a set of operating condition cognition features that characterize the freezing risk evolution rate and operating condition characteristics. Based on the set of working condition cognitive features, the capability requirement reasoning unit is invoked to reason about the adaptation stability of different antifreeze capability response states under the current temperature evolution category identifier, and to generate a set of candidate equivalent antifreeze capability intervals. Consistency and redundancy analysis are performed on the candidate equivalent antifreeze capability interval set to construct the target equivalent antifreeze capability interval.

3. The antifreeze formulation optimization device based on temperature sensing as described in claim 1, characterized in that, In the temperature trend determination module, the temperature evolution trend determination based on the antifreeze operating temperature state vector includes: Perform temporal decomposition and multi-scale dynamic feature extraction of the antifreeze operating temperature state vector to construct multi-scale dynamic features; The multi-scale dynamic features are subjected to correlation analysis and weighted evaluation of short-term rapid changes and long-term stable trends of temperature behavior at different time scales to construct an initial temperature evolution classification signal. A dual backtracking verification analysis is performed on the initial temperature evolution classification signal to construct a temperature evolution category identifier.

4. The antifreeze formulation optimization device based on temperature sensing as described in claim 3, characterized in that, In the temperature trend discrimination module, a dual backtracking verification analysis is performed on the initial temperature evolution classification signal to construct a temperature evolution category identifier, including: The antifreeze operating temperature state vector and initial temperature evolution classification signal collected during the current startup cycle are analyzed in reverse along the time series to identify evolution consistency and abrupt behavior, and to establish the backtracking correction signal for the current startup cycle. The system calls upon temperature evolution classification signals from multiple historical startup cycles, performs multiple rounds of startup verification based on the call results, and generates startup correction signals. The backtracking correction signal and the activation correction signal are used to perform dual backtracking verification analysis to construct a temperature evolution category identifier.

5. The antifreeze formulation optimization device based on temperature sensing as described in claim 1, characterized in that, In the cumulative optimization module, the time series cumulative analysis of the operating temperature state vector includes: The intensity or activation state of the adjustable parameters of the antifreeze is adjusted according to the formula control instructions, and the current control action and the temperature response characteristics of the action are recorded simultaneously. Based on the current control actions, action temperature response characteristics, antifreeze operating temperature state vector, and historical data, the cumulative effect, trend evolution, and response consistency of the formulation control commands under different temperature conditions are calculated to form a cumulative optimization feature set to complete the time series cumulative analysis.

6. The antifreeze formulation optimization device based on temperature sensing as described in claim 5, characterized in that, In the cumulative optimization module, the adaptive update optimization of executing formula control instructions includes: Multidimensional data analysis is performed on the temperature response amplitude, temperature change rate, freezing risk evolution trend, and historical control response deviation in the cumulative optimization feature set to calculate the response contribution and reliability index of the control action in different time windows. Perform adaptive correction updates based on the calculation results.

7. The antifreeze formulation optimization device based on temperature sensing as described in claim 6, characterized in that, The device further includes: The trend prediction module is used to predict the evolution trend and freezing risk of the antifreeze operating temperature state vector based on the cumulative optimized feature set, and to establish the prediction results. The feedback module is used to configure the activation order, effect intensity, and response priority of adjustable parameters based on the prediction results, and to predict, optimize, and update the formula control instructions based on the configuration results.

8. The antifreeze formulation optimization device based on temperature sensing as described in claim 1, characterized in that, The temperature sensing module adopts a multi-point temperature acquisition strategy to synchronously collect temperature data of the environment where the antifreeze is located and key locations inside the system, so as to construct a spatially consistent antifreeze operating temperature state vector.

9. The antifreeze formulation optimization device based on temperature sensing as described in claim 1, characterized in that, When the temperature trend discrimination module performs temperature evolution trend discrimination based on the antifreeze operating temperature state vector, it performs noise suppression and outlier filtering on the antifreeze operating temperature state vector.

10. The antifreeze formulation optimization device based on temperature sensing as described in claim 1, characterized in that, When generating formula control instructions, the formula state control module invokes the change rate limit constraint to perform formula control generation constraint management.

Images