Automatic monitoring and optimizing system for fine chemical production process

Abstract

The invention relates to the technical field of automation, in particular to an automatic monitoring and optimizing system for a fine chemical production process, which comprises the following steps of: extracting time-frequency domain fusion characteristic quantity of stirring torque power time sequence fluctuation data in real time through an incidence matrix construction module, dynamically inverting a thixotropic index by combining a deep neural network model, and optimizing the stirring torque power time sequence fluctuation data; the problem that a traditional method is difficult to perceive material rheological characteristics in real time is solved. The dynamic coupling analysis module analyzes the material viscosity change rate based on the thixotropic index, fuzzy PID control is adopted to generate a stirring speed adjusting instruction dynamically matched with the viscosity and a jacket temperature compensation value, and the defects of uneven mixing and local overheating caused by lagging adjustment of process parameters are overcome; the multi-target collaborative optimization module locks the mass optimization weight in the viscosity sudden change stage, rapidly stabilizes the reaction condition through a feed-forward compensation algorithm, dynamically balances the stirring power consumption and the heat transfer efficiency based on Pareto frontier search in the steady state stage, and solves the conflict between the mass and the energy efficiency target.

Description

Technical Field

[0001] The present invention relates to the field of automation technology, in particular to an automated monitoring and optimization system for a fine chemical production process. Background Art

[0002] During pesticide production, the rheological properties of materials directly impact the uniformity of reaction mixing, the dispersion of active ingredients, and the quality of the final product. Traditional pesticide production relies heavily on fixed process parameters or manual experience to adjust stirring speed and temperature, making it difficult to capture dynamic changes in viscosity caused by thixotropic material behavior (such as shear thinning or viscoelasticity mutations) in real time. Especially when synthesizing high-viscosity pesticide emulsions or suspensions, abnormal fluctuations in stirring torque can easily lead to problems such as uneven mixing and localized overheating, resulting in poor batch stability or increased side reactions. In existing technologies, offline viscosity testing suffers from lags, and single-device control strategies are unable to simultaneously adapt to viscosity mutations and energy efficiency optimization needs, resulting in energy waste or product quality fluctuations.

[0003] In addition, batch differences in pesticide raw materials and the presence of toxic substances further exacerbate the traditional system's insufficient response to dynamic working conditions. There is an urgent need for a precise control solution that can analyze thixotropic properties in real time and coordinate multi-objective optimization. Summary of the Invention

[0004] The purpose of the present invention is to provide an automated monitoring and optimization system for fine chemical production processes to solve the problems raised in the above-mentioned background technology. Specific technical problems include how to perceive the thixotropic properties of pesticide production materials in real time and quickly analyze viscosity change trends to solve the problem of coordinated lag between stirring and mixing efficiency and temperature control; and how to adaptively switch between quality priority and energy efficiency priority modes based on the dynamic behavior of viscosity to achieve balanced optimization of stability and energy consumption during the pesticide synthesis process.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an automated monitoring and optimization system for a fine chemical production process, comprising an association matrix construction module, a dynamic coupling analysis module, and a multi-objective collaborative optimization module, wherein: The correlation matrix construction module uses sliding window segmentation processing to segment the stirring torque power time series fluctuation data. In the time domain, the peak value and standard deviation of the torque fluctuation in each time window are extracted as basic features. At the same time, the main frequency band energy distribution characteristics are obtained through fast Fourier transform in the frequency domain. The two are normalized and integrated to form the fluctuation amplitude feature, which comprehensively characterizes the rheological properties of the pesticide material. The correlation matrix construction module constructs a nonlinear mapping model based on a deep neural network. The input layer receives real-time fluctuation amplitude characteristics. The hidden layer dynamically captures the correlation pattern between torque fluctuations and material thixotropic behavior through an adaptive activation function. The output layer generates a thixotropic index. The network weight parameters are continuously updated through an online incremental learning mechanism to dynamically adapt to the rheological property variations caused by differences in pesticide raw material batches.

[0006] The change rate calculation unit in the dynamic coupling analysis module uses a time series trend analysis algorithm to dynamically track the thixotropic index and accurately obtain the material viscosity change rate through polynomial fitting and first-order derivative calculation within a sliding time window; The equipment control parameter set generation unit in the dynamic coupling analysis module uses a fuzzy PID control algorithm to generate an equipment control parameter set including stirring speed adjustment instructions and jacket temperature compensation values based on the preset material viscosity change rate and process parameter mapping rules. When the material viscosity change rate increases positively, the gain coefficient of the stirring speed adjustment instruction is dynamically increased and the jacket temperature compensation value is increased. When the material viscosity change rate decreases negatively, the stirring speed is adjusted in the opposite direction and the temperature compensation amplitude is reduced to achieve precise control under dynamic viscosity changes.

[0007] The multi-objective collaborative optimization module executes a dynamic weight allocation strategy based on the device control parameter set, where: When the material viscosity change rate exceeds the preset mutation threshold, the quality optimization weight locking mechanism is activated, and a step increment of the jacket temperature compensation value is generated through the feedforward compensation algorithm. This increment is determined by the square term, linear term and material thermal conductivity constant of the viscosity change rate. At the same time, the equipment heat capacity constraint is integrated and a segmented limiting strategy is adopted to suppress temperature overshoot, forcibly locking the quality optimization weight to ensure the stability of pesticide synthesis.

[0008] When the material viscosity change rate returns to the steady-state range, a multi-objective optimization function is constructed based on the stirring speed adjustment instruction. With stirring power consumption and heat transfer efficiency as core variables, the feasible solution set is analyzed in real time through the Pareto front search mechanism. The constrained gradient projection method is used to determine the optimal weight distribution point, and the speed step size is dynamically adjusted in combination with the sensitivity matrix of the inverter speed adjustment. At the same time, a hysteresis attenuation factor is introduced into the jacket temperature compensation value. According to the second-order derivative direction of the material viscosity change rate and the normalized rate value, the distribution ratio of the quality weight and the energy efficiency weight is adjusted in real time to achieve dynamic balance under the optimal energy consumption mode.

[0009] Compared with the prior art, the present invention has the following beneficial effects: By analyzing the thixotropic properties and dynamic changes in viscosity of pesticide materials in real time, the coordinated response speed of stirring and mixing efficiency and temperature control is significantly improved, effectively avoiding product failure caused by local overheating or uneven mixing. The adaptive learning ability of deep neural networks enhances the system's robustness to toxic components and batch differences in pesticide raw materials, ensuring control accuracy under complex working conditions. The combination of fuzzy PID and multi-objective optimization algorithms prioritizes pesticide synthesis quality when viscosity changes suddenly, while reducing stirring energy consumption and heat transfer losses in the steady-state phase, achieving a dynamic balance between quality and energy efficiency. Through feedforward compensation and Pareto optimization mechanisms, energy waste and waste generation in pesticide production are reduced, providing an intelligent solution for the manufacture of pesticides with high toxicity and high stability requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a schematic diagram of the overall module of the present invention; Figure 2 Schematic diagram of the dynamic coupling analysis module unit of the present invention.

[0011] In the figure: 100, correlation matrix construction module; 200, dynamic coupling analysis module; 201, change rate calculation unit; 202, device control parameter set generation unit; 300, multi-objective collaborative optimization module. DETAILED DESCRIPTION

[0012] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0013] Unless otherwise defined, technical or scientific terms used in this application shall have the ordinary meanings as understood by persons of ordinary skill in the art to which this application belongs. The terms "a," "an," "the," "these," and similar expressions in this application do not denote limitations on quantity and may be singular or plural. The terms "comprise," "include," "have," and any variations thereof, as used in this application, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units) but may include unlisted steps or modules (units) or other steps or modules (units) inherent to the process, method, product, or device. The terms "connected," "connected," "coupled," and similar expressions used in this application are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. As used in this application, "plurality" means two or more. "And / or" describes an association between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone; A and B exist simultaneously; or B exists alone. Generally, the character " / " indicates that the objects in the preceding and following relationship are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0014] Next, see Figure 1 The present invention provides a technical solution: an automated monitoring and optimization system for a fine chemical production process, comprising a correlation matrix construction module 100, a dynamic coupling analysis module 200 and a multi-objective collaborative optimization module 300.

[0015] The correlation matrix construction module 100 uses a high-precision torque sensor to collect the stirring torque power time series fluctuation data during the operation of the stirring device in real time, and performs sliding window segmentation processing on the stirring torque power time series fluctuation data to divide it into continuous time window units. In the time domain dimension, the peak value and standard deviation of the torque fluctuation signal in each time window are calculated as the basic feature quantities representing the instantaneous impact intensity of the torque and the degree of fluctuation dispersion, respectively. At the same time, in the frequency domain dimension, the torque fluctuation data of each time window is subjected to fast Fourier transform, and the energy distribution characteristics of the main frequency band are extracted to quantify the energy proportion of different frequency components; the time domain basic characteristic quantity and the frequency domain main frequency band energy distribution characteristics are fused into multi-dimensional features through a normalization algorithm, and after eliminating the dimensional difference, a normalized torque fluctuation amplitude characteristic quantity is formed, thereby fully characterizing the comprehensive dynamic response of the material rheological characteristics in the time and frequency domain; comprehensive input parameters for characterizing the thixotropic behavior of the material are provided to the deep neural network model, supporting the accurate inversion of the thixotropic index. This technology effectively solves the problem of loss of frequency domain information of complex rheological characteristics in traditional time domain analysis, and enhances the system's ability to analyze the dynamic response of the rheological state of the pesticide mixture.

[0016] A deep neural network model is trained based on historical production data to establish a nonlinear mapping relationship between torque fluctuation amplitude characteristics and thixotropic index. The input layer of the deep neural network model receives the real-time extracted torque fluctuation amplitude characteristics, the hidden layer captures the dynamic correlation pattern between torque fluctuation and material thixotropic behavior through an adaptive activation function, and the output layer generates the thixotropic index at the current moment. The network weight parameters are continuously updated through an online incremental learning mechanism, allowing the deep neural network model to dynamically adapt to the rheological property variations brought about by different raw material batches, ultimately achieving the real-time analysis capability of inferring physical property parameters based on equipment operation data. Among them: The online incremental learning mechanism constructs a dynamic incremental training sample set by collecting the time-series fluctuation data of the stirring torque power and the corresponding measured values of the thixotropic index during the production of new raw material batches in real time; an elastic weight solidification algorithm is used to update the weights of the deep neural network model, and the importance of each network weight parameter to the learned rheological properties is quantified by calculating the diagonal element values of the Fisher information matrix of historical batch data. Regularization constraints are imposed during the training of new batches to retain key weight parameters, while allowing non-critical weights to be dynamically adjusted; combined with an adaptive learning rate scheduler, the model update amplitude is dynamically adjusted according to the degree of deviation between the raw material batch switching signal and the new sample feature distribution, so that the network can continuously integrate the nonlinear characteristics of the thixotropic behavior of the new batch of materials while avoiding catastrophic forgetting, thereby realizing dynamic tracking of cross-batch rheological property variations and enhancing the model generalization capability.

[0017] In pesticide production, the correlation matrix construction module 100 uses a high-precision torque sensor to monitor the torque fluctuation data during the stirring process of the reactor in real time. Combined with time-frequency domain feature fusion technology, it accurately analyzes the rheological properties of the pesticide mixture (such as the thixotropic index), dynamically tracks the viscosity changes caused by differences in raw material batches, and provides real-time inversion support for physical parameters for subsequent process optimization, ensuring the uniform dispersion and reaction stability of the active ingredients of different batches of pesticides.

[0018] See also Figure 2The change rate calculation unit 201 in the dynamic coupling analysis module 200 receives the thixotropic index output by the correlation matrix construction module 100 and uses a time series trend analysis algorithm to dynamically track the material viscosity change process, wherein: The thixotropic index is intercepted by a sliding time window mechanism, and the trend function of the thixotropic index changing with time is constructed through a second-order polynomial fitting algorithm, and its first-order derivative is calculated as the material viscosity change rate; among them, the sliding window length is dynamically adjusted according to the material batch switching signal and the rheological response delay characteristics. When the raw material batch switching is detected, the window length is automatically shortened to improve the trend tracking sensitivity; in the polynomial fitting process, the fitting coefficients are iteratively optimized based on the least squares principle, and abnormal data points caused by torque sensor noise or process disturbances are eliminated through residual analysis; at the same time, the window overlap factor is introduced to smooth the fitting results of adjacent windows to suppress the rate calculation fluctuations caused by sudden changes in window boundaries.

[0019] The change rate calculation unit 201 intercepts the thixotropic index time series data through a sliding time window mechanism, uses a second-order polynomial fitting algorithm to construct a trend function and calculate its first-order derivative, and accurately analyzes the material viscosity change rate; by dynamically adjusting the window length (such as shortening the window when switching raw material batches), the tracking sensitivity is improved, and the abnormal points caused by sensor noise and process disturbances are eliminated by combining residual analysis, and the window overlap factor is introduced to smooth the fitting results of adjacent windows, effectively suppressing rate calculation fluctuations. This technology solves the problems of traditional differential methods being sensitive to noise and hysteresis, and captures viscosity mutations in real time in pesticide production (such as shear thinning in the emulsification stage of herbicides), providing accurate trend basis for subsequent dynamic adjustment of equipment parameters, and ensuring the stability of the reaction process.

[0020] The equipment control parameter set generation unit 202 in the dynamic coupling analysis module 200 generates the equipment control parameter set using a fuzzy PID control algorithm based on the preset material viscosity change rate and process parameter mapping rules. When the viscosity change rate increases positively, the gain coefficient of the stirring speed adjustment instruction is dynamically increased according to the rate gradient to enhance the shear effect, and the jacket temperature compensation value is calculated based on the energy conservation equation to offset the viscous heating effect. When the viscosity change rate decays negatively, the stirring speed is adjusted in the opposite direction and the temperature compensation amplitude is reduced, thereby forming an equipment control parameter set of the stirring speed adjustment instruction and the jacket temperature compensation value that matches the material rheological state in real time, realizing closed-loop coordinated control of process parameters and physical property evolution.

[0021] Based on the material viscosity change rate, the device control parameter set generation unit 202 employs a fuzzy PID control algorithm to generate stirring speed adjustment instructions and jacket temperature compensation values that match the rheological state in real time. When the material viscosity change rate increases in a positive direction, the stirring speed gain coefficient is dynamically increased to enhance shear mixing, and a temperature compensation value is simultaneously calculated based on the energy conservation equation to offset viscous heating. When the material viscosity change rate decreases in a negative direction, the parameters are reversed to stabilize the system. This technology adaptively adjusts PID parameters through a fuzzy rule base, overcoming the hysteresis of traditional linear control for nonlinear rheological behavior. In pesticide synthesis (such as in the case of sudden viscosity changes during polycondensation of insecticides), closed-loop coordinated control of stirring intensity and temperature compensation is achieved, suppressing local overheating and uneven mixing, ensuring reaction efficiency and product consistency.

[0022] To address the problem of sudden changes in raw material viscosity during pesticide synthesis, the dynamic coupling analysis module 200 dynamically adjusts the stirring speed and jacket temperature compensation strategy by calculating the rate of change of the thixotropic index in real time. For example, it quickly increases the shear force during the herbicide emulsification stage to suppress phase separation, while compensating for local overheating caused by viscous heat generation, thereby achieving closed-loop coordinated control of reaction conditions and material rheological state, ensuring the synthesis efficiency of pesticide active ingredients and product quality consistency.

[0023] The multi-objective collaborative optimization module 300 implements process objective priority switching using a state-triggered dynamic weight allocation strategy based on the equipment control parameter set (including the stirring speed adjustment instruction and the jacket temperature compensation value) output by the equipment control parameter set generation unit 202, wherein: When the material viscosity change rate exceeds the preset mutation threshold, it is determined to be a stage of drastic rheological fluctuations, and the quality optimization weight locking mechanism is activated. The jacket temperature compensation value is used as the core control variable, and the temperature compensation amplitude and response speed are increased to the preset upper limit through the feedforward compensation algorithm. The first control instruction is generated to forcibly lock the quality optimization weight (for example, set to the range of 0.9-1.0), giving priority to maintaining material mixing uniformity and reaction stability. The feedforward compensation algorithm establishes a rapid response mechanism through pre-stored material viscosity mutation patterns and equipment thermal inertia parameters. According to the gradient direction and intensity of the viscosity change, the preset compensation coefficient matrix (including the compensation amplitude increment and response acceleration parameters corresponding to different viscosity mutation levels) is called to directly calculate the step increment of the jacket temperature compensation value. This increment is determined by the square term and linear term of the viscosity change rate and the material thermal conductivity constant, and the response time of the temperature control loop is compressed by the dynamic acceleration factor. The algorithm simultaneously integrates the equipment thermal capacity constraint, monitors the risk of jacket temperature overshoot in real time, and adopts a segmented limiting strategy to suppress temperature overshoot when generating the compensation value, ensuring the rapidity and stability of the compensation process.

[0024] When the viscosity change rate falls back to the steady-state range (±5% of the preset benchmark value), it switches to energy efficiency optimization mode. Based on the stirring speed adjustment command, a multi-objective optimization function is constructed. By calculating the Pareto front of stirring power consumption (proportional to the cube of the speed) and jacket heat transfer efficiency (linearly related to the temperature difference) in real time, the quality and energy efficiency weight distribution ratio is dynamically adjusted (in the range of 0.5-0.7). A second control command is generated to drive the inverter to perform speed fine-tuning. A hysteresis attenuation factor is introduced into the jacket temperature compensation value to achieve a dynamic balance between minimizing stirring energy consumption and maximizing heat transfer efficiency. Ultimately, a closed-loop optimization control chain is formed to adapt to the evolution of material state. The multi-objective optimization function takes stirring efficiency and heat transfer power as core variables, dynamically balances quality and energy consumption targets, and the distribution ratio of quality weight and energy efficiency weight is adjusted in real time according to the second-order derivative direction of the viscosity change rate and the normalized rate value: if the viscosity change shows an accelerating trend, the quality weight is prioritized; if it shows a decelerating trend, the energy efficiency weight ratio is enhanced; the Pareto frontier search mechanism is introduced in the optimization process, and the feasible solution set of stirring power and heat transfer efficiency is analyzed in real time. The constrained gradient projection method is used to determine the optimal weight distribution point, and the speed step size is dynamically adjusted in combination with the sensitivity matrix of the inverter speed regulation, ultimately achieving an adaptive balance between quality and energy consumption targets under time-varying working conditions.

[0025] In the continuous production of pesticides, the multi-objective collaborative optimization module 300 intelligently switches between quality priority and energy efficiency priority modes according to the viscosity change trend: when the insecticide condensation reaction is intense, the temperature compensation weight is locked to ensure a smooth reaction; in the steady-state stage, the stirring speed and heat transfer parameters are optimized to balance the reaction rate and energy consumption cost. For example, the energy consumption of fungicide production can be reduced by 15% while maintaining a 98% product yield, forming a dynamic control chain for dual-objective optimization of quality and energy efficiency.

[0026] From the above description, it can be seen that the fine chemical production process automation monitoring and optimization system provided in this embodiment has the following technical effects: Through the fusion of time-frequency domain features and online incremental learning of deep neural networks, high-precision real-time analysis of the rheological properties of materials in the pesticide production process is achieved, and the thixotropy variation caused by differences in raw material batches is dynamically tracked to ensure mixing uniformity and reaction stability; based on fuzzy PID control and adaptive viscosity change rate, the equipment parameters are dynamically adjusted, and the reaction conditions are quickly stabilized through feedforward compensation and segmented limiting strategies in the viscosity mutation stage, thereby suppressing the risks of local overheating and phase separation; combined with Pareto frontier search and multi-objective weight dynamic allocation mechanism, the stirring energy consumption and heat transfer efficiency are balanced in the steady-state stage, forming a seamless switch between quality priority and energy efficiency priority modes, and ultimately achieving closed-loop control with controllable product quality, optimized energy consumption and coordinated response of process parameters under complex working conditions, significantly improving the intelligence level and comprehensive benefits of pesticide production.

[0027] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely preferred examples of the present invention and are not intended to limit the present invention. Various changes and improvements may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and improvements fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A fine chemical production process automation monitoring and optimization system, characterized in that: It includes an association matrix construction module (100), a dynamic coupling analysis module (200) and a multi-objective collaborative optimization module (300), wherein: The correlation matrix construction module (100) extracts the fluctuation amplitude characteristic quantity characterizing the rheological characteristics of the material based on the online collected stirring torque power time series fluctuation data, and establishes a nonlinear mapping model between the fluctuation amplitude characteristic quantity and the thixotropic index, wherein the nonlinear mapping model is used to calculate the thixotropic index in real time according to the fluctuation amplitude characteristic quantity; The dynamic coupling analysis module (200) analyzes the material viscosity change trend according to the thixotropic index and obtains the material viscosity change rate; generates a device control parameter set including a stirring speed adjustment instruction and a jacket temperature compensation value according to the material viscosity change rate; The multi-objective collaborative optimization module (300) executes a dynamic weight allocation strategy according to the device control parameter set, wherein: When the material viscosity change rate exceeds a preset mutation threshold, a first control instruction is generated based on the jacket temperature compensation value to forcibly lock the quality optimization weight; When the material viscosity change rate returns to the steady-state range, a second control instruction is generated based on the stirring speed adjustment instruction in the same equipment control parameter set to switch to the energy efficiency optimization mode, dynamically balancing the stirring power consumption and heat transfer efficiency.

2. The fine chemical production process automation monitoring and optimization system according to claim 1 is characterized in that: The extraction process of the fluctuation amplitude feature quantity includes: The stirring torque power time series fluctuation data is segmented by sliding window segmentation, and the peak value and standard deviation of the torque fluctuation in each time window are extracted as the basic feature quantity in the time domain dimension; In the frequency domain dimension, the main frequency band energy distribution feature is obtained by fast Fourier transform, and the basic feature quantity and the main frequency band energy distribution feature are normalized and fused to form the fluctuation amplitude feature quantity.

3. The fine chemical production process automation monitoring and optimization system according to claim 1 is characterized in that: The nonlinear mapping model is a deep neural network model trained based on historical production data. Its input layer receives the real-time extracted fluctuation amplitude feature, the hidden layer captures the dynamic correlation pattern between torque fluctuation and material thixotropic behavior through an adaptive activation function, and the output layer generates a thixotropic index.

4. The fine chemical production process automation monitoring and optimization system according to claim 3 is characterized in that: The deep neural network model continuously updates the network weight parameters through an online incremental learning mechanism to dynamically adapt to the rheological property variations brought about by different raw material batches.

5. The fine chemical production process automation monitoring and optimization system according to claim 1 is characterized in that: The dynamic coupling analysis module (200) comprises a change rate calculation unit (201). The change rate calculation unit (201) obtains the material viscosity change rate by dynamically tracking the thixotropic index using a time series trend analysis algorithm, and obtains the thixotropic index through polynomial fitting and first-order derivative calculation within a sliding time window.

6. The fine chemical production process automation monitoring and optimization system according to claim 1, characterized in that: The dynamic coupling analysis module (200) comprises a device control parameter set generation unit (202), and the process of the device control parameter set generation unit (202) generating the device control parameter set comprises: According to the preset mapping rules between the material viscosity change rate and process parameters, the fuzzy PID control algorithm is used to generate the equipment control parameter set. When the viscosity change rate increases in a positive direction, the gain coefficient of the stirring speed adjustment instruction is dynamically increased and the jacket temperature compensation value is calculated; when the viscosity change rate decreases in a negative direction, the stirring speed is adjusted in the opposite direction and the temperature compensation amplitude is reduced.

7. The fine chemical production process automation monitoring and optimization system according to claim 1 is characterized in that: The multi-objective collaborative optimization module (300) includes: When the material viscosity change rate exceeds the preset mutation threshold, the quality optimization weight locking mechanism is activated, the compensation amplitude and response speed of the jacket temperature compensation value are increased to the preset upper limit, and the first control instruction is generated to forcibly lock the quality optimization weight; When the material viscosity change rate returns to the steady-state range, a multi-objective optimization function is constructed based on the stirring speed adjustment instruction, and the quality and energy efficiency weight distribution ratio is dynamically adjusted to generate the second control instruction and switch to the energy efficiency optimization mode.

8. The fine chemical production process automation monitoring and optimization system according to claim 7, characterized in that: The quality optimization weight locking mechanism generates a step increment of the jacket temperature compensation value through a feedforward compensation algorithm. The feedforward compensation algorithm integrates the equipment heat capacity constraint and adopts a segmented limiting strategy to suppress temperature overshoot, wherein the step increment is comprehensively determined by the square term and linear term of the viscosity change rate and the material thermal conductivity constant.

9. The fine chemical production process automation monitoring and optimization system according to claim 7, characterized in that: The multi-objective optimization function takes stirring power consumption and heat transfer efficiency as core variables, analyzes feasible solution sets in real time through the Pareto front search mechanism, and uses the constrained gradient projection method to determine the optimal weight distribution point. The speed step size is dynamically adjusted in combination with the sensitivity matrix of the inverter speed regulation.

10. The fine chemical production process automation monitoring and optimization system according to claim 7, characterized in that: The energy efficiency optimization mode introduces a hysteresis attenuation factor into the jacket temperature compensation value, and adjusts the distribution ratio of the quality weight and the energy efficiency weight in real time according to the second-order derivative direction of the material viscosity change rate and the normalized rate value.

Images