A steam crosslinking room intelligent control method, device, equipment and medium

Abstract

The application provides a steam crosslinking room intelligent control method, device, equipment and medium, and relates to the technical field of intelligent control. The method comprises the following steps: the method forms a time-synchronized multi-parameter observation vector by collecting temperature, steam and humidity parameters in real time, and establishes a dynamic heat conduction model describing the nonlinear coupling relationship between temperature, steam flow and thermal inertia; the PID parameter output control quantity is adaptively adjusted based on the temperature deviation and the error change rate, and the future temperature trajectory is predicted by using the model, and the optimal control increment is obtained by optimizing the objective function under the constraint condition; the multi-objective optimization function is constructed by combining the temperature deviation energy integral, steam energy consumption and temperature fluctuation variance to dynamically adjust the weight and output the target control signal. The application can solve the problems of lack of nonlinear modeling and prediction compensation ability in the traditional control mode, easy to cause temperature fluctuation, uneven heat field and unstable material performance.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, specifically to an intelligent control method, device, equipment, and medium for a steam cross-linking chamber. Background Technology

[0002] A steam cross-linking chamber is a closed, heated space used in the production of wires and cables to achieve the cross-linking reaction of polymer materials such as polyethylene. It uses a high-temperature steam environment to promote cross-linking between the molecular chains of the materials, thereby improving the heat resistance, mechanical strength, and electrical performance of the cables. The cross-linking process typically lasts for a considerable period under specific temperature and pressure conditions; therefore, precise control of temperature, humidity, and steam flow rate is crucial for product quality.

[0003] The steam crosslinking process is a strongly coupled, nonlinear, and significantly thermally inertial dynamic system, which traditional proportional control and piecewise setpoint control cannot adapt to its time-varying characteristics. Proportional control relies solely on the current error for linear adjustment, ignoring the error change rate and cumulative deviation, leading to overshoot or undershoot during the heating phase. Piecewise setpoint control relies on switching the setpoint with a fixed threshold, failing to reflect the dynamic changes in system heat capacity, steam condensation, and heat dissipation, often resulting in temperature oscillations during threshold switching. Since the opening degree of the steam valve is nonlinearly related to the flow rate, the response is sluggish in the small opening range and tends to saturate in the large opening range, making it difficult for simple linear control to accurately correspond to temperature changes. Furthermore, the temperature in the steam crosslinking chamber exhibits integral characteristics; the current temperature is affected by accumulated heat input, and traditional control methods cannot compensate for historical errors, resulting in persistent steady-state deviations. In summary, traditional control methods lack nonlinear modeling and predictive compensation capabilities, easily leading to temperature fluctuations, uneven thermal fields, and unstable material properties. Summary of the Invention

[0004] This invention provides an intelligent control method, device, equipment, and medium for a steam crosslinking chamber, which can solve the problems of traditional control methods lacking nonlinear modeling and prediction compensation capabilities, and easily causing temperature fluctuations, uneven thermal fields, and unstable material properties.

[0005] A first aspect of the present invention provides a method for intelligent control of a steam crosslinking chamber, the method comprising: Real-time acquisition of temperature, steam, and ambient humidity parameters inside the steam crosslinking chamber to form a time-synchronized multi-parameter observation vector; Based on the multi-parameter observation vector, a dynamic heat conduction model of the cross-linking chamber is established. The dynamic heat conduction model is used to describe the nonlinear coupling relationship between temperature, steam flow rate and thermal inertia. Calculate the temperature deviation and error rate of change based on the set temperature and the real-time detected temperature, and adjust the PID parameters in real time based on the temperature deviation and the error rate of change to output the control quantity. Based on the control quantity, the temperature trajectory within multiple future sampling periods is predicted using the dynamic heat conduction model, and the objective function is calculated with the target temperature as a reference. The objective function is then optimized under the constraint of control quantity changes to determine the current optimal control increment. The optimal control increment is constructed based on the temperature deviation energy integral, steam energy consumption index and temperature fluctuation variance to build a multi-objective optimization function, and the weights of each objective function are adjusted in real time to output the target control signal. According to the target control signal, the control actuator adjusts the opening of the steam valve. The opening of the steam valve is linearized and compensated by the valve characteristic correction function, so that the nonlinear response of the valve is converted into a steam flow output proportional to the target control signal.

[0006] Based on the above technical solutions, preferably, the step of establishing a dynamic heat conduction model of the cross-linked chamber based on the multi-parameter observation vector specifically includes: For the temperature distribution characteristics, steam flow characteristics, steam pressure characteristics and humidity characteristics in the observation vector, the correspondence between the temperature change rate and the steam flow change within the sampling period is calculated by the least squares algorithm and the recursive parameter identification algorithm. The thermal response coefficient, thermal inertia time constant and time delay parameters are extracted to generate an intermediate parameter matrix describing the nonlinear coupling relationship between steam input and temperature change. Substitute the intermediate parameter matrix into the structured heat conduction equations to establish a multivariate coupled dynamic heat conduction model. The input variables of the dynamic heat conduction model are steam flow rate and steam pressure, and the output variable is the temperature response of the cross-linking chamber. Time delay units and nonlinear correction terms are introduced into the model structure of the dynamic heat conduction model to compensate for the energy transfer deviation caused by changes in the heat capacity of the chamber and steam condensation. During the crosslinking process, the model parameters of the dynamic heat conduction model are continuously updated. Based on the updated temperature response and steam flow deviation, a recursive least squares algorithm is executed to correct the thermal response coefficient and time delay parameters, thereby achieving adaptive learning of thermal characteristics under different loads, different steam pressures and different external environments.

[0007] Based on the above technical solution, preferably, the step of calculating the temperature deviation and error change rate based on the set temperature and the real-time detected temperature, and adjusting the PID parameters in real time based on the temperature deviation and the error change rate to output a control quantity specifically includes: Real-time temperature data detected inside the steam crosslinking chamber is received during each sampling period; The real-time temperature data is compared with the set temperature to calculate the first temperature deviation value of the current sampling period, and the second temperature deviation value of the previous sampling period is recorded at the same time. The rate of change of temperature error between the first temperature deviation value and the second temperature deviation value is calculated using a differential method. The temperature deviation and the rate of change of temperature error are fuzzified according to a preset membership function. The proportional coefficient adjustment, integral coefficient adjustment and differential coefficient adjustment are output according to the control semantic rules defined in the rule base to obtain the fuzzy inference output result. The original PID parameters are corrected in real time based on the fuzzy inference output to obtain updated proportional coefficient, integral coefficient and derivative coefficient. The proportional coefficient is used to adjust the temperature response rate, the integral coefficient is used to eliminate steady-state error, and the derivative coefficient is used to suppress temperature overshoot. The PID parameter correction results are then corrected a second time based on the temperature response characteristics output by the dynamic heat conduction model to keep the PID control process dynamically coupled with the steam flow rate change. The control system will perform control calculations using the updated PID parameters, and calculate the output control quantity based on the temperature deviation, error integral, and error change rate within the current sampling period.

[0008] Based on the above technical solutions, preferably, the step of predicting the temperature trajectory within multiple sampling periods using the dynamic heat conduction model based on the control quantity, calculating the objective function with the target temperature as a reference, and optimizing the objective function under the constraint of control quantity changes to determine the current optimal control increment specifically includes: Within the current sampling period, acquire the historical control quantities and corresponding multi-parameter observation vectors from the previous sampling period; The historical control quantity and the multi-parameter observation vector are used to calculate the dynamic response relationship between steam input and temperature change based on thermal response coefficient, thermal inertia time constant and time delay parameter, and a temperature prediction sequence corresponding to multiple future sampling periods is generated. An objective function is established based on the temperature prediction sequence. The objective function uses the sum of squared deviations between the predicted temperature values ​​and the target temperature over multiple future sampling periods as the optimization objective. A control variable constraint term is introduced to constrain the steam valve regulation rate. The objective function obtains a balanced control strategy by dynamically adjusting the weights of the temperature deviation term and the control smoothing term. The objective function is optimized based on valve opening limits, control increment constraints, and system response delay constraints. A sequential quadratic programming algorithm is used to perform iterative calculations in the prediction time domain to obtain the optimal control increment that minimizes the objective function. The optimal control increment is used to correct the steam valve opening to compensate for future predicted temperature deviations. The optimal control increment is superimposed with the historical control quantity to generate a corrected control quantity sequence. The dynamic heat conduction model is called again to re-predict the temperature of the control quantity sequence. If the predicted temperature still has a deviation that exceeds the preset tolerance threshold, the optimization weight is automatically adjusted or the prediction time domain is extended and the optimization calculation is repeated until the predicted temperature stabilizes within the target temperature range.

[0009] Based on the above technical solutions, preferably, the step of constructing a multi-objective optimization function based on the temperature deviation energy integral, steam energy consumption index, and temperature fluctuation variance, adjusting the weights of each objective function in real time, and outputting the target control signal specifically includes: The optimal control increment is superimposed with the historical control quantity to form a control quantity change sequence; The temperature deviation energy integral of the steam crosslinking chamber within a preset time window is calculated based on the control quantity change sequence. The temperature deviation energy integral is obtained by integrating the square of the temperature deviation with the temperature correction value under the action of the optimal control increment, and is used to characterize the contribution of the optimal control increment to the steady-state temperature performance. The steam energy consumption index is calculated based on the change in steam valve opening caused by the optimal control increment. The steam energy consumption index is determined by a combination of steam flow rate, steam pressure difference and valve dynamic response rate, and is used to reflect the impact of the optimal control increment on steam energy utilization efficiency. Calculate the temperature fluctuation variance of the temperature sequence before and after applying the optimal control increment, and use the temperature fluctuation variance to quantify the degree of improvement of temperature stability by the optimal control increment; A multi-objective optimization function is constructed, wherein the common optimization objective is to minimize the temperature deviation energy integral, the steam energy consumption index, and the temperature fluctuation variance, and dynamic weight coefficients are set for each objective. When the optimal control increment is detected to cause an increase in the temperature deviation energy integral, the weight of temperature control accuracy is automatically increased; when the steam energy consumption index is detected to increase, the weight of energy consumption optimization is automatically increased; when the temperature fluctuation variance is detected to increase, the weight of temperature stability is automatically increased. The optimal control increment is used as the initial search point and input into the particle swarm optimization algorithm. Global search and local convergence are performed in the multi-objective optimization function space. The target control signal with the best comprehensive performance is obtained by iterative evaluation of different combinations of optimal control increments.

[0010] Based on the above technical solution, preferably, the step of controlling the actuator to adjust the opening of the steam valve according to the target control signal, wherein the opening of the steam valve is linearized and compensated by a valve characteristic correction function, so that the nonlinear response of the valve is converted into a steam flow output proportional to the target control signal, specifically includes: The target control signal is used as the input basis for the ideal flow adjustment of the steam valve, and the expected opening adjustment amount of the valve is determined according to the amplitude and direction of change of the target control signal. The displacement of the steam valve stem is adjusted by a stepper motor according to the expected opening degree, so that the valve core performs corresponding opening and closing actions along the flow channel, thereby forming dynamic regulation of steam flow. A flow characteristic model of a steam valve was established. The actual steam flow response curves of the valve at different opening degrees were obtained through experimental calibration. The nonlinear relationship function between valve opening degree and steam flow rate was established by least squares fitting. The nonlinear relationship function is inversely transformed to generate a valve characteristic correction function, which is used to convert the target control signal into an equivalent opening command that is linearly corresponding to the steam flow rate, thereby compensating for the nonlinear response of the valve in the small and large opening ranges. During valve regulation, the valve characteristic correction function is called in real time to calculate the linearized corrected valve opening command based on the current target control signal, and interpolation compensation is performed in combination with the mechanical transmission characteristics and response inertia of the actuator. The real-time feedback signal from the valve position sensor is obtained and compared with the calculated theoretical opening. When the valve position deviation exceeds the set threshold, the execution current or step pulse is adjusted through a closed-loop correction algorithm to achieve dynamic tracking of the actual valve opening to the target opening command. The real-time output value of steam flow is calculated based on the valve opening after linearization correction. The real-time output value of steam flow is collected by a flow sensor and compared with the theoretical steam flow for error. When the flow deviation is detected to exceed the preset range, the coefficients of the valve characteristic correction function are updated. During the continuous operation of the cross-linking chamber, the steam flow is dynamically adjusted based on the linearized valve characteristic model. When the temperature deviation decreases, the valve opening gradually decreases at a linear rate to reduce the steam input. When the temperature deviation increases, the valve opening gradually increases at a linear rate to increase the steam input, so that the steam flow output maintains a linear proportional relationship with the target control signal.

[0011] Based on the above technical solutions, preferably, the real-time acquisition of temperature parameters, steam parameters, and ambient humidity parameters inside the steam crosslinking chamber to form a time-synchronized multi-parameter observation vector specifically includes: The collected temperature, steam flow, steam pressure, and humidity signals are converted into timestamped data frames. The data frames are cached and sorted according to their timestamps. Data with time deviations are synchronously corrected using linear interpolation to obtain a corrected data sequence. The corrected data sequence is normalized, and a structured data matrix is ​​generated based on the spatial deployment location of each sensor, so that each column corresponds to a physical quantity and each row corresponds to the multi-source measurement value at the same time. The structured data matrix is ​​transformed into a multi-parameter observation vector, where each element of the multi-parameter observation vector corresponds to the temperature distribution feature, steam flow feature, steam pressure feature, and humidity feature, respectively, and an observation vector sequence is formed within a continuous sampling period.

[0012] In a second aspect of the invention, a smart control device for a steam crosslinking chamber is provided. The device is used to execute a smart control method for a steam crosslinking chamber as described in any of the above embodiments. The device includes an acquisition module, a processing module, and an output module, wherein: The acquisition module is used to collect temperature parameters, steam parameters and ambient humidity parameters inside the steam crosslinking chamber in real time, forming a time-synchronized multi-parameter observation vector. The processing module is used to establish a dynamic heat conduction model of the cross-linking chamber based on the multi-parameter observation vector. The dynamic heat conduction model is used to describe the nonlinear coupling relationship between temperature, steam flow rate and thermal inertia. The processing module is used to calculate the temperature deviation and error change rate based on the set temperature and the real-time detected temperature, adjust the PID parameters in real time based on the temperature deviation and the error change rate, and output the control quantity. The processing module is used to predict the temperature trajectory within multiple future sampling periods based on the control quantity using the dynamic heat conduction model, and to calculate the objective function with the target temperature as a reference. Under the condition of constraining the change of the control quantity, the objective function is optimized to determine the current optimal control increment. The processing module is used to construct a multi-objective optimization function based on the temperature deviation energy integral, steam energy consumption index and temperature fluctuation variance of the optimal control increment, adjust the weight of each objective function in real time, and output the target control signal. The output module is used to control the actuator to adjust the opening of the steam valve according to the target control signal. The opening of the steam valve is linearized and compensated by the valve characteristic correction function, so that the nonlinear response of the valve is converted into a steam flow output proportional to the target control signal.

[0013] In a third aspect of the invention, an electronic device is provided, including a processor, a memory, a user interface, and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any of the preceding embodiments.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium storing instructions that, when executed, perform the method as described in any of the preceding claims.

[0015] In summary, one or more technical solutions provided in the embodiments of the present invention have at least the following technical effects or advantages: 1. This invention establishes a self-learning nonlinear temperature control closed-loop system by introducing a collaborative mechanism of dynamic heat conduction model, fuzzy adaptive PID control, model predictive control, and multi-objective optimization control. The dynamic heat conduction model realizes real-time coupled modeling of temperature, steam flow rate, and thermal inertia. The fuzzy adaptive PID automatically corrects control parameters based on temperature deviation and rate of change, avoiding overshoot and hysteresis of traditional PID control. Model predictive control uses thermal inertia trends to feedforward compensate for future temperature trajectories, while the multi-objective optimization function achieves an adaptive balance between temperature accuracy, energy consumption, and fluctuation stability. The valve characteristic correction function further eliminates nonlinear distortion in steam flow output. Therefore, the continuity, stability, and uniformity of temperature regulation can be maintained under dynamic operating conditions, fundamentally solving the problems of thermal field fluctuations and material performance instability in traditional control.

[0016] 2. Dynamic modeling of the internal thermodynamic characteristics of the steam crosslinking chamber was achieved using the least squares algorithm and recursive parameter identification algorithm. Thermal response coefficients, thermal inertia time constants, and time delay parameters were extracted to establish a dynamic heat conduction model that reflects the nonlinear coupling relationship between steam flow rate, pressure, and temperature in real time. This model enables the system to accurately describe the inertia and hysteresis characteristics during heat transfer, achieving precise prediction and adaptive learning of the thermal state under different operating conditions, thereby improving the dynamic response accuracy and modeling robustness of temperature control.

[0017] 3. By employing fuzzy adaptive PID control based on temperature deviation and error change rate, online dynamic correction of PID parameters is achieved, enabling the control system to automatically adjust the proportional, integral, and derivative coefficients according to temperature fluctuation characteristics. This approach avoids the overshoot and steady-state deviation problems that occur in traditional PID control in nonlinear and time-varying systems. After secondary correction using a dynamic heat transfer model, the temperature regulation process can maintain consistency with the steam flow response, thereby achieving high-precision, fast-converging, and stable temperature control.

[0018] 4. By combining the control input with a dynamic heat transfer model, model predictive control is used to perform feedforward prediction and dynamic optimization of the temperature trajectory over multiple sampling periods, solving for the optimal control increment under constraints. This technique enables the prediction and proactive compensation of future temperature change trends, effectively reducing temperature deviations caused by hysteresis, and achieving a balance between control smoothness and response speed, thereby significantly improving the predictability and control stability of the system.

[0019] 5. By constructing a multi-objective optimization function with temperature deviation energy integral, steam energy consumption index, and temperature fluctuation variance as optimization targets, and dynamically adjusting the weights of each target based on the particle swarm optimization algorithm, a synergistic optimization among temperature accuracy, energy efficiency, and stability is achieved. This method can automatically reallocate control priorities according to the system state at different operating stages, enabling the control process to take into account both steady-state performance and energy efficiency, thereby realizing intelligent, multi-objective adaptive optimization of temperature control.

[0020] 6. By introducing a valve characteristic correction function to compensate for the nonlinear characteristics of the steam valve, the valve opening change maintains a linear correspondence with the target control signal. Combined with precise stepper motor control, valve position closed-loop feedback, and online self-correction of the characteristic function, continuous controllability and high-precision linearization of steam flow output are achieved. This eliminates the regulation hysteresis and fluctuations caused by valve nonlinearity, enabling dynamic matching between steam input and thermal response, and significantly improving the stability and consistency of temperature regulation. Attached Figure Description

[0021] Figure 1 This is a schematic flowchart of an intelligent control method for a steam crosslinking chamber disclosed in an embodiment of the present invention; Figure 2 This is a schematic diagram of a module of an intelligent control device for a steam crosslinking chamber disclosed in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present invention.

[0022] Explanation of reference numerals in the attached drawings: 201, acquisition module; 202, processing module; 203, output module; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. Detailed Implementation

[0023] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0024] In the description of the embodiments of the present invention, words such as "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "for example" or "for instance" in the embodiments of the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Rather, the use of words such as "for example" or "for instance" is intended to present the relevant concepts in a specific manner.

[0025] In the description of the embodiments of the present invention, the term "multiple" means two or more. For example, multiple systems means two or more systems, and multiple screen terminals means two or more screen terminals. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0026] The steam crosslinking chamber is a sealed heating environment used in the manufacture of wires and cables to achieve the crosslinking reaction of polymer chains in materials such as polyethylene. The stable control of its temperature, humidity, and steam flow directly determines the electrical and mechanical properties of the product. This process is characterized by strong coupling, nonlinearity, and significant thermal inertia. Traditional proportional control adjusts linearly based only on the current error, failing to reflect the trend of error changes and easily leading to overshoot or undershoot during the heating phase. Segmented setpoint control switches the setpoint with a fixed threshold, ignoring changes in system heat capacity and steam condensation characteristics, easily causing temperature oscillations during switching. Because the steam valve opening and flow rate have a nonlinear relationship, small openings result in sluggish response, while large openings tend to saturate, making it difficult for traditional linear control to accurately match temperature changes. Furthermore, the crosslinking temperature exhibits an integral effect due to the cumulative heat input, and traditional algorithms cannot compensate for historical deviations, leading to persistent steady-state errors and uneven thermal fields. Therefore, temperature fluctuations, localized overheating, and unstable material properties during the crosslinking process become inherent defects of traditional control methods.

[0027] This embodiment discloses an intelligent control method for a steam crosslinking chamber, referring to... Figure 1 This includes the following steps S110-S160: S110 collects temperature, steam, and ambient humidity parameters inside the steam crosslinking chamber in real time, forming a time-synchronized multi-parameter observation vector.

[0028] This invention discloses an intelligent control method for a steam crosslinking chamber, which is applied to a server. The server includes, but is not limited to, electronic devices such as mobile phones, tablets, wearable devices, and PCs (Personal Computers), and can also be a backend server running the intelligent control method for the steam crosslinking chamber. The server can be implemented using a standalone server or a server cluster composed of multiple servers.

[0029] In one possible implementation, temperature, steam, and ambient humidity parameters inside the steam crosslinking chamber are acquired in real time to form a time-synchronized multi-parameter observation vector. Specifically, this includes: converting the acquired temperature, steam flow, steam pressure, and humidity signals into timestamped data frames; caching and sorting the data frames according to the timestamps; synchronously correcting data with time deviations using linear interpolation to obtain a corrected data sequence; normalizing the corrected data sequence and generating a structured data matrix based on the spatial deployment of each sensor, such that each column corresponds to a physical quantity and each row corresponds to multi-source measurements at the same time; and converting the structured data matrix into a multi-parameter observation vector, where each element of the multi-parameter observation vector corresponds to temperature distribution characteristics, steam flow characteristics, steam pressure characteristics, and humidity characteristics, forming an observation vector sequence within a continuous sampling period.

[0030] Specifically, firstly, the analog signals collected by temperature sensors, steam flow sensors, steam pressure sensors, and humidity sensors installed at different locations inside the steam crosslinking chamber are filtered and amplified by the signal conditioning module before being input to the analog-to-digital conversion unit. The analog-to-digital conversion unit converts the analog signals into digital signals according to a uniform sampling frequency and assigns a timestamp generated by a high-precision clock source to each set of sampled data, thereby forming a raw data frame containing the sampling time, sensor number, and measured value. The timestamp is used to identify the sampling time, enabling the data from multiple sensors to be aligned and compared under the same time reference, ensuring the temporal consistency of information from different measurement points.

[0031] Secondly, the data frames output by each sensor are stored in a buffer and sorted according to their timestamps to eliminate time misalignment caused by transmission delays or communication jitter. For data with timestamp differences less than the sampling period but not fully aligned, a linear interpolation method is used to perform time synchronization correction. Assuming that two adjacent samples within the time interval Δt are respectively... and Then the correction value at the intermediate time t can be expressed as:

[0032]

[0033] Where v(t) is the synchronization correction value at the target time point. This is the time of the last sampling. This correction method can eliminate sampling phase shift, ensuring strict synchronization of multi-source signals in the time domain.

[0034] Then, the data after time synchronization correction is normalized to map the value ranges of different physical quantities to a unified interval [0,1], preventing computational distortion caused by differences in magnitude during subsequent model calculations. The normalization formula is:

[0035]

[0036] in For the normalized result, and These represent the minimum and maximum values ​​of the corresponding physical quantities. After normalization, a structured data matrix is ​​generated based on the spatial layout coordinates of each sensor within the cross-linking room. Each column corresponds to a physical quantity, including temperature, steam flow rate, steam pressure, or humidity, and each row corresponds to multi-source measurement values ​​from the same sampling point at the same time, forming a data structure with both spatial and temporal characteristics.

[0037] Finally, the structured data matrix is ​​transformed into a multi-parameter observation vector in the control calculation module. Each element of the observation vector represents the temperature distribution characteristics, steam flow characteristics, steam pressure characteristics, and humidity characteristics inside the cross-linking chamber, respectively. By stacking the multi-parameter observation vectors in chronological order within a continuous sampling period, a time-series observation vector set is formed. This observation vector set serves as the input basis for the dynamic heat conduction model and subsequent control algorithms, enabling synchronous modeling, real-time feedback, and dynamic correlation control of multi-dimensional parameters within the cross-linking chamber.

[0038] S120, based on multi-parameter observation vectors, establishes a dynamic heat conduction model for the cross-linking chamber. The dynamic heat conduction model is used to describe the nonlinear coupling relationship between temperature, steam flow rate and thermal inertia.

[0039] In one possible implementation, a dynamic heat conduction model of the cross-linking chamber is established based on a multi-parameter observation vector. Specifically, this includes: calculating the correspondence between the rate of temperature change and the change in steam flow rate within the sampling period using the least squares algorithm and a recursive parameter identification algorithm, based on the temperature distribution characteristics, steam flow rate characteristics, steam pressure characteristics, and humidity characteristics in the observation vector; extracting the thermal response coefficient, thermal inertia time constant, and time delay parameters to generate an intermediate parameter matrix describing the nonlinear coupling relationship between steam input and temperature change; substituting the intermediate parameter matrix into the structured heat conduction equations to establish a multivariate coupled dynamic heat conduction model. The input variables of the dynamic heat conduction model are steam flow rate and steam pressure, and the output variable is the temperature response of the cross-linking chamber. A time delay unit and a nonlinear correction term are introduced into the model structure of the dynamic heat conduction model to compensate for energy transfer deviations caused by changes in chamber heat capacity and steam condensation; continuously updating the model parameters of the dynamic heat conduction model during the cross-linking process; and executing a recursive least squares algorithm based on the updated temperature response and steam flow rate deviation to correct the thermal response coefficient and time delay parameters, thereby achieving adaptive learning of thermal characteristics under different loads, different steam pressures, and different external environments.

[0040] Specifically, when processing the temperature distribution characteristics, steam flow rate characteristics, steam pressure characteristics, and humidity characteristics in the observation vector, it is first necessary to extract the time series data of each physical quantity and use them as input samples in the parameter identification process. The optimal linear fit between the temperature change rate and the steam flow rate change is calculated using the least squares algorithm to obtain the initial thermal response coefficient reflecting the heat transfer efficiency. The goal of the least squares algorithm is to minimize the sum of squared errors between the predicted and measured temperatures. Let the temperature response value be y, the steam flow rate input be u, and the model coefficient vector be... Then the least squares optimization problem can be expressed as:

[0041]

[0042] This optimization process yields the temperature response to steam input within the current sampling period. To enable online model updates, a recursive least squares (RLS) algorithm is introduced to dynamically adjust parameter estimates based on the latest observation data in each new sampling period. Its recursive form is as follows:

[0043]

[0044] in Estimate parameters for the current time step. Here is the gain matrix. This represents the actual temperature response at the current sampling point. The input vector is the steam flow rate. Through continuous sampling and iterative calculation, the thermal response coefficient, thermal inertia time constant, and time delay parameter can be extracted. The thermal response coefficient characterizes the intensity of the effect of unit steam flow rate on temperature rise; the thermal inertia time constant reflects the heat storage capacity and response hysteresis characteristics of the cross-linking chamber system; and the time delay parameter describes the transmission delay between steam entering the pipeline and the manifestation of the thermal effect. This yields an intermediate parameter matrix describing the nonlinear coupling relationship between steam input and temperature change.

[0045] Substituting the intermediate parameter matrix into the structured heat conduction equations, a multivariable coupled dynamic heat conduction model is established. This equation set is based on energy conservation and comprehensively considers steam flow rate, steam pressure, material heat conduction, and heat dissipation. The model's input variables are steam flow rate q(t) and steam pressure p(t), and the output variable is the temperature response T(t). The basic form of the model is as follows:

[0046]

[0047] Where K is the thermal response coefficient, L is the time delay, α is the vapor pressure coupling coefficient, and β is the thermal inertia decay coefficient. This is a nonlinear correction term. The nonlinear correction term compensates for the changes in the heat capacity of the cross-linked chamber structural materials and the energy distribution errors caused by the condensation and heat release of steam under high pressure, thus enabling the model to more accurately reflect the heat transfer patterns in time and space. The time-delay unit within the model delays the input signal, maintaining physical consistency between the temperature response and the steam input, ensuring that the model's predictions are synchronized with the actual process.

[0048] During the continuous operation of the crosslinking process, the parameters of the dynamic heat transfer model need to be updated in real time according to the actual thermal state. Whenever new temperature response and steam flow observation data are collected, the model parameters are updated using a recursive least squares algorithm, correcting the thermal response coefficient and time delay parameters, enabling the model to adaptively track the changing trends of the system's thermal characteristics. When load fluctuations, steam pressure changes, or changes in ambient temperature are detected, the algorithm automatically adjusts the model parameters, ensuring that the model's temperature prediction remains consistent with the measured temperature. Through this online self-learning mechanism, the dynamic heat transfer model can adaptively update under different operating conditions, maintaining a high-precision nonlinear thermal response description over the long term, thus providing a basis for accurate temperature prediction and dynamic compensation for subsequent control strategies.

[0049] S130 calculates the temperature deviation and error change rate based on the set temperature and the real-time detected temperature, adjusts the PID parameters in real time based on the temperature deviation and error change rate, and outputs the control quantity.

[0050] In one possible implementation, the temperature deviation and error rate of change are calculated based on the set temperature and the real-time detected temperature. The PID parameters are then adjusted in real-time based on the temperature deviation and error rate of change, and a control quantity is output. Specifically, this includes: receiving real-time temperature data detected inside the steam cross-linking chamber in each sampling period; comparing the real-time temperature data with the set temperature to calculate the first temperature deviation value for the current sampling period, and simultaneously recording the second temperature deviation value from the previous sampling period; calculating the temperature error rate of change between the first temperature deviation value and the aforementioned second temperature deviation value using a differential method; fuzzifying the input signal based on the temperature deviation and temperature error rate of change according to a preset membership function, and outputting the control quantity according to the control semantic rules defined in the rule base. The proportional, integral, and derivative coefficients are adjusted to obtain the fuzzy inference output. Based on the fuzzy inference output, the original PID parameters are corrected in real time to obtain updated proportional, integral, and derivative coefficients. The proportional coefficient is used to adjust the temperature response rate, the integral coefficient is used to eliminate steady-state error, and the derivative coefficient is used to suppress temperature overshoot. The PID parameter correction results are then further corrected based on the temperature response characteristics output by the dynamic heat conduction model to maintain dynamic coupling between the PID control process and the steam flow rate change. The control system executes control calculations using the updated PID parameters and calculates the output control quantity based on the temperature deviation, error integral, and error change rate within the current sampling period.

[0051] Specifically, during each sampling period, while receiving real-time temperature data detected inside the steam cross-linking chamber, the temperature sensor continuously samples the internal gas temperature of the chamber. The sampling period is set to a fixed interval based on the thermal inertia response to ensure that the system reflects dynamic thermal changes without introducing data delay. The analog signal acquired by the sensor undergoes signal conditioning and analog-to-digital conversion to generate a digital real-time temperature data stream. This data stream is transmitted to the control unit's memory buffer via an industrial bus or Ethernet for subsequent processing modules to read. The sampling period is defined as the time interval between two adjacent data acquisitions, symbolically represented as Δt, and is an important parameter for calculating the rate of change of temperature error.

[0052] When comparing real-time temperature data with the set temperature, the control system reads the current temperature observation value. With the preset target temperature Perform the difference calculation to obtain the first temperature deviation value of the current sampling period. At the same time, the system retrieves the temperature observation values ​​from the previous sampling period. Calculate the second temperature deviation value corresponding to the previous cycle. Temperature deviation e(t) reflects the degree of deviation between the current temperature state and the target temperature, and is defined as:

[0053]

[0054] in, Indicates the set temperature. This indicates real-time temperature measurement. By recording the deviation between two consecutive cycles, the system can obtain the transient trend of temperature changes.

[0055] When calculating the rate of change of temperature error using a differential method, the finite difference method is employed to discretize the rate of change of temperature deviation, thereby obtaining dynamic response information on the temperature change trend. The discrete expression for the rate of change of error, de / dt, is:

[0056]

[0057] in The rate of change of temperature deviation reflects the dynamic trend of temperature rise or fall. The error rate of change is a crucial input parameter for the derivative element of a PID controller, as it anticipates the acceleration trend of temperature fluctuations, providing a basis for the adjustment direction of the fuzzy inference system.

[0058] In the fuzzy inference stage, the temperature deviation and the rate of change of temperature error are input into the fuzzy inference module and fuzzified according to the preset membership function. The membership function is a mathematical description that transforms continuous quantities into fuzzy linguistic variables, generally using a triangular or trapezoidal distribution. For example, the fuzzy set of temperature deviation can be defined as {large negative, small negative, zero, small positive, large positive}. The fuzzified input variables are then logically inferred through the fuzzy inference rule base, which is based on control semantic rules, such as: "If the temperature deviation is large positive and the rate of change of error is large positive, then decrease the proportional coefficient and increase the differential coefficient." The proportional coefficient adjustment amount is output through the inference process. Integral coefficient adjustment and differential coefficient adjustment amount This generates fuzzy inference output results.

[0059] When real-time correction of the original PID parameters based on the fuzzy inference output, the inference results are superimposed on the original PID parameters to update the PID parameter set. The calculation relationship is as follows:

[0060]

[0061]

[0062] in , , These are the initial proportional, integral, and derivative coefficients, respectively. The corrected parameter set reflects the control dynamics under the current thermal inertia state. (Proportional coefficient) Used to adjust the temperature response rate, integral coefficient Used to eliminate steady-state deviations, differential coefficients This is used to suppress overshoot. To further improve the correction accuracy, the PID parameter update results also need to be corrected a second time based on the temperature response characteristics output by the dynamic heat conduction model. The thermal response coefficient and time delay parameter are used to compensate for the thermal inertia of the PID parameters, so that the response of the control algorithm remains dynamically consistent with the change in steam flow.

[0063] During the control operation phase, the updated PID parameter set is used to perform closed-loop calculations on the real-time temperature data. The expression for calculating the PID controller output control quantity u(t) is as follows:

[0064] Where u(t) is the control output signal, used to drive the actuator of the steam valve to achieve dynamic regulation of the steam flow. Integral term Historical quantities used to accumulate temperature deviations to ensure the elimination of steady-state errors; differential terms It reflects the rate of temperature change to suppress overshoot and oscillation in advance. The final output control quantity achieves precise control of steam flow within the current sampling period, thereby gradually stabilizing the internal temperature of the cross-linking chamber and bringing it close to the target temperature, achieving fast response, low overshoot, and high stability temperature control performance.

[0065] S140, based on the control quantity, uses a dynamic heat conduction model to predict the temperature trajectory within multiple future sampling periods, and calculates the objective function with the target temperature as a reference. Under the condition of constraining the change of the control quantity, the objective function is optimized to determine the current optimal control increment.

[0066] In one possible implementation, based on the control quantity, a dynamic heat conduction model is used to predict the temperature trajectory over multiple future sampling periods. An objective function is calculated using the target temperature as a reference. The objective function is optimized under constraints on the control quantity's variation to determine the current optimal control increment. Specifically, this includes: acquiring the historical control quantity and corresponding multi-parameter observation vector from the previous sampling period within the current sampling period; calculating the dynamic response relationship between steam input and temperature change based on the historical control quantity and multi-parameter observation vector using the thermal response coefficient, thermal inertia time constant, and time delay parameters, generating a temperature prediction sequence for multiple future sampling periods; establishing an objective function based on the temperature prediction sequence, where the objective function uses the sum of squared deviations between the predicted temperature values ​​and the target temperature over multiple future sampling periods as the optimization objective, and introducing the variation of the control quantity... The constraint term is used to constrain the steam valve regulation rate. The objective function obtains a balanced control strategy by dynamically adjusting the weights of the temperature deviation term and the control smoothing term. The objective function is optimized based on the valve opening limit, control increment constraint, and system response delay constraint. A sequential quadratic programming algorithm is used to perform iterative calculations in the prediction time domain to obtain the optimal control increment that minimizes the objective function. The optimal control increment is used to correct the steam valve opening to compensate for future predicted temperature deviations. The optimal control increment is superimposed with historical control values ​​to generate a corrected control value sequence. The dynamic heat conduction model is called again to re-predict the temperature of the control value sequence. If the predicted temperature still has a deviation exceeding the preset tolerance threshold, the optimization weights are automatically adjusted or the prediction time domain is extended and the optimization calculation is repeated until the predicted temperature stabilizes within the target temperature range.

[0067] Specifically, when acquiring the historical control quantity and corresponding multi-parameter observation vector from the previous sampling period within the current sampling period, it is necessary to read the control output signal from the previous period and the real-time sampling data from multiple sensors from the control system's storage unit. The historical control quantity u(t-1) represents the control command applied to the steam valve in the previous sampling period and is an input variable reflecting the dynamic behavior of the control system. The corresponding multi-parameter observation vector X(t-1) includes temperature distribution characteristics, steam flow characteristics, steam pressure characteristics, and ambient humidity characteristics, used to describe the thermal state of the cross-linking chamber in the previous period. The sampling period is set by the system to a fixed time interval Δt, ensuring strict synchronization between the historical control quantity and the observation vector in the time series. By using these two quantities as initial conditions for the dynamic heat conduction model, historical input boundaries can be provided for future temperature prediction, thereby maintaining the continuity and computational accuracy of the model.

[0068] When calculating the dynamic response relationship between steam input and temperature change based on the historical control quantity and multi-parameter observation vector using the thermal response coefficient, thermal inertia time constant, and time delay parameters, the parameter set of the dynamic heat conduction model is first invoked, including the thermal response coefficient K, thermal inertia time constant T, and time delay L, to establish the dynamic functional relationship between input and output. The nonlinear coupling between steam input q(t) and temperature change ΔT(t) can be expressed in differential form as follows:

[0069]

[0070] Where K represents the amplification effect of unit steam flow rate on temperature rise, T represents the time inertia of system response, and L represents the steam transport delay. By recursively extrapolating this relationship over multiple future sampling periods, a temperature prediction sequence can be generated. This refers to the predicted temperature values ​​at each point in the future prediction time domain. The prediction sequence reflects the cumulative impact of steam input dynamics on the thermal response and is the core foundation of model predictive control calculations.

[0071] When establishing the objective function based on the generated temperature prediction sequence, the sum of squared deviations between the predicted temperature values ​​and the target temperature over multiple future sampling periods is used as the optimization objective. A control variable variation constraint term is introduced to balance temperature accuracy and valve regulation stability. The objective function can be expressed as follows:

[0072]

[0073] Where T(t+i) is the predicted temperature value for the i-th sampling period. Let Δu(t+i-1) be the target temperature, and Δu(t+i-1) be the increment of the control variable. The smoothing weighting factor is used to control the system. The temperature deviation term reflects the control accuracy requirements, while the smoothing term reflects the system energy consumption and the dynamic constraints of the actuator. By dynamically adjusting the weights of these two terms, a balance can be achieved between rapid response and stable control. When the temperature deviation is too large, the temperature accuracy weight is increased; when the valve adjustment frequency is too high, the smoothing weight is increased to suppress mechanical fatigue and steam impact.

[0074] When performing optimization on the objective function under constraints, valve opening limits, control increment limits, and system response delay constraints are introduced to ensure that the control quantity adjustment does not exceed the physical limits of the actuator. The constraints can be expressed as:

[0075] ,

[0076] To solve the optimization problem, a Sequential Quadratic Programming (SQP) algorithm is employed. This algorithm transforms the nonlinear optimization problem into a series of constrained quadratic subproblems, which are then solved iteratively to gradually approach the minimum value of the objective function. This is achieved through prediction in the time domain. Inner iteration operation can obtain the objective function. Minimum optimal control increment Its physical meaning is the most reasonable steam flow adjustment amount under the current sampling period, which is used to compensate for the temperature deviation predicted in the future.

[0077] After obtaining the optimal control increment, it is superimposed with the historical control values ​​to generate the corrected control value sequence. The dynamic heat conduction model is then invoked again to re-predict the temperature, in order to verify the adjustment effect. If the temperature deviation obtained from the re-prediction still exceeds the preset tolerance threshold... Then, a secondary optimization operation is automatically performed: on the one hand, the weighting factors of the temperature deviation term and the smoothing term in the objective function are adjusted. On the other hand, it extends the prediction time domain length. To enhance the predictability of control, a closed-loop optimization mechanism is formed. The system repeatedly executes a prediction-optimization-correction cycle in each sampling period until the predicted temperature sequence stabilizes within the target temperature range. The final output control command drives the steam valve to perform regulation at the optimal rate, achieving continuous dynamic compensation and precise control of the temperature inside the cross-linking chamber.

[0078] S150 constructs a multi-objective optimization function based on the temperature deviation energy integral, steam energy consumption index, and temperature fluctuation variance to optimize the control increment. It then adjusts the weights of each objective function in real time and outputs the target control signal.

[0079] In one possible implementation, the optimal control increment is constructed based on the temperature deviation energy integral, steam energy consumption index, and temperature fluctuation variance to create a multi-objective optimization function. The weights of each objective function are adjusted in real time, and a target control signal is output. Specifically, this includes: superimposing the optimal control increment with historical control values ​​to form a control quantity change sequence; calculating the temperature deviation energy integral of the steam cross-linking chamber within a preset time window based on the control quantity change sequence. The temperature deviation energy integral is obtained by integrating the square of the temperature correction value under the action of the temperature deviation and the optimal control increment, and is used to characterize the contribution of the optimal control increment to the steady-state temperature performance; calculating the steam energy consumption index based on the steam valve opening change caused by the optimal control increment. The steam energy consumption index is determined comprehensively by steam flow rate, steam pressure difference, and valve dynamic response rate, and is used to reflect the impact of the optimal control increment on steam energy utilization efficiency; and calculating the optimal control increment application... The temperature fluctuation variance of the temperature sequence before and after the control increment is used to quantify the degree of improvement in temperature stability brought about by the optimal control increment. A multi-objective optimization function is constructed, with the common optimization objectives being the minimization of temperature deviation energy integral, steam energy consumption index, and temperature fluctuation variance, and dynamic weight coefficients corresponding to each objective are set. When the optimal control increment is detected to cause an increase in temperature deviation energy integral, the weight of temperature control accuracy is automatically increased; when the steam energy consumption index is detected to increase, the weight of energy consumption optimization is automatically increased; and when the temperature fluctuation variance is detected to increase, the weight of temperature stability is automatically increased. The optimal control increment is used as the initial search point and input into the particle swarm optimization algorithm. Global search and local convergence are performed in the multi-objective optimization function space. The target control signal with the best comprehensive performance is obtained through iterative evaluation of different combinations of optimal control increments.

[0080] Specifically, when superimposing the optimal control increment with the historical control quantity to form a control quantity change sequence, the historical control quantity u(t-1) of the previous sampling period is first read and compared with the optimal control increment obtained in the current period. The corrected control quantity u(t) is obtained by superposition operation, and its calculation formula is as follows:

[0081] Where u(t) represents the strength of the control signal acting on the actuator during the current sampling period. This represents the optimal increment calculated by the optimization algorithm, used to correct the steam flow control command from the previous cycle. A sequence of control quantity changes is formed by superimposing consecutive sampling periods. It can reflect the changing trend of the control signal over time, providing basic data for subsequent energy integration and dynamic performance evaluation.

[0082] When calculating the temperature deviation energy integral of the steam cross-linking chamber within a preset time window based on the control quantity change sequence, the difference between the set temperature and the measured temperature is used as the temperature deviation input to calculate its value within the time window. The integral of the square within the time frame. The temperature deviation energy integral is used to measure the total energy intensity of temperature fluctuations, and its calculation formula is:

[0083]

[0084] in, This represents the energy integral of the temperature deviation. To set the temperature, This represents the temperature correction value under optimal control increment. A smaller energy integral value indicates that the system temperature is closer to steady state. This is achieved by comparing values ​​under different optimal control increments. The changes can be quantified to determine their contribution to steady-state performance, thus providing a basis for subsequent optimization and weight adjustment.

[0085] When calculating steam energy consumption indicators based on the change in steam valve opening caused by the optimal control increment, the valve dynamic response rate, steam flow rate change, and pressure difference must be considered simultaneously. Steam energy consumption indicators The efficiency of the control strategy in utilizing steam energy is reflected by the following formula:

[0086]

[0087] in, For steam flow rate, The pressure difference across the valve is represented by γ, which is a weighting coefficient. This represents the square of the rate of change of the valve's dynamic opening. A higher value indicates higher energy loss. Statistical analysis of energy consumption indicators across different control cycles allows for the dynamic evaluation of the energy-saving effect of the optimal control increment.

[0088] When calculating the temperature fluctuation variance of the temperature series before and after applying the optimal control increment, the temperature measurement data within the sampling period is used as input, and the temperature series before applying the control is analyzed. Temperature sequence after control is applied The variance differences are calculated separately to quantify the degree of improvement in system stability. The calculation formula is as follows:

[0089]

[0090] in, For temperature fluctuation variance, and These represent the average values ​​of the temperature series. A decrease in variance indicates that the temperature is more stable after control, suggesting that the optimal control increment has a more significant effect on improving the dynamic stability of the system.

[0091] When constructing the multi-objective optimization function, the temperature deviation energy integral is used. Steam energy consumption index and temperature fluctuation variance Minimizing is the common objective. The multi-objective optimization function expression is:

[0092]

[0093] in, , , These are dynamic weighting coefficients, corresponding to steady-state performance, energy consumption performance, and temperature stability, respectively. The dynamic adjustment mechanism of the weights is based on real-time performance monitoring results. When the optimal control increment is detected to cause a temperature deviation, the energy integral is adjusted accordingly. When it increases, it automatically rises. To enhance temperature accuracy; when steam energy consumption indicators When rising, automatically increase To enhance energy consumption optimization; when temperature fluctuation variance When it increases, it automatically rises. This enhances stability control. The mechanism ensures that the system automatically switches control priorities under different operating conditions, achieving an adaptive balance between temperature accuracy, energy efficiency, and stability.

[0094] When the optimal control increment is used as the initial search point in the particle swarm optimization algorithm, the aforementioned multi-objective optimization function J is used as the fitness function. Global search and local convergence are achieved using the particle swarm optimization (PSO) algorithm. Each particle in the swarm represents a candidate optimal control increment combination; its position vector represents the current increment value, and its velocity vector represents the search step size. The iterative update formula is:

[0095]

[0096]

[0097] in, Let be the velocity of the i-th particle in the k-th iteration. The position of the particle, i.e., the candidate control increment. This represents the optimal position in the history of an individual particle. The optimal position for the entire group. For inertial weights, and As a learning factor, , The coefficients are random. Through continuous iteration, the particle swarm converges to the optimal region in the search space, obtaining the target control signal with the best overall performance. This target control signal achieves global optimization in energy utilization, temperature accuracy, and dynamic stability, providing a highly stable and energy-efficient intelligent control output for the steam crosslinking chamber.

[0098] S160, based on the target control signal, controls the actuator to adjust the opening of the steam valve. The opening of the steam valve is linearized and compensated by the valve characteristic correction function, so that the nonlinear response of the valve is converted into a steam flow output proportional to the target control signal.

[0099] In one possible implementation, based on the target control signal, the actuator adjusts the opening of the steam valve. The opening of the steam valve is linearized and compensated by a valve characteristic correction function, so that the nonlinear response of the valve is converted into a steam flow output proportional to the target control signal. Specifically, this includes: using the target control signal as the input basis for the ideal flow adjustment of the steam valve; determining the expected opening adjustment amount of the valve based on the amplitude and direction of change of the target control signal; adjusting the displacement of the valve stem of the steam valve according to the expected opening by a stepper motor, so that the valve core performs corresponding opening and closing actions along the flow path, thereby forming dynamic regulation of the steam flow; establishing a flow characteristic model of the steam valve; obtaining the actual steam flow response curve of the valve at different openings through experimental calibration; and establishing a nonlinear relationship function between the valve opening and the steam flow using a least-squares fitting method; generating a valve characteristic correction function after inverse functionalizing the nonlinear relationship function, which is used to convert the target control signal into an equivalent opening command linearly corresponding to the steam flow, thereby compensating for the nonlinear response of the valve in the small and large opening ranges; and in the execution... During valve regulation, the valve characteristic correction function is invoked in real time to calculate the linearized corrected valve opening command based on the current target control signal. Interpolation compensation is then performed, taking into account the mechanical transmission characteristics and response inertia of the actuator. Real-time feedback signals from the valve position sensor are acquired and compared with the calculated theoretical opening. When the valve position deviation exceeds a set threshold, the execution current or step pulse is adjusted using a closed-loop correction algorithm to dynamically track the target opening command. The real-time steam flow output is calculated based on the linearized corrected valve opening. This real-time steam flow output is collected by a flow sensor and compared with the theoretical steam flow. When a flow deviation exceeds a preset range, the coefficients of the valve characteristic correction function are updated. During continuous operation of the cross-linking chamber, dynamic steam flow adjustment is performed based on the linearized valve characteristic model. When the temperature deviation decreases, the valve opening gradually decreases at a linear rate to reduce steam input; when the temperature deviation increases, the valve opening gradually increases at a linear rate to increase steam input, ensuring a linear proportional relationship between the steam flow output and the target control signal.

[0100] Specifically, when the target control signal is used as the input for the ideal flow adjustment of the steam valve, the target control signal is output by the multi-objective optimization module, representing the expected steam flow adjustment trend in the current sampling period. This signal has two components: amplitude and direction of change. The amplitude corresponds to the magnitude of the steam valve opening adjustment, and the direction indicates the increasing or decreasing trend of the valve opening. The expected opening or closing direction of the valve is determined based on the sign of the target control signal, and the opening change step size is determined based on the amplitude. The opening adjustment amount can be obtained through proportional conversion:

[0101]

[0102] in, This represents the expected valve opening adjustment amount, where u(t) is the target control signal. This is the control gain coefficient. This relationship allows for a direct mapping between the target control signal and valve action, enabling the control system to adjust the steam input promptly according to changes in heat load.

[0103] When a stepper motor adjusts the valve stem displacement of a steam valve according to the expected opening degree, the actuator converts the calculated opening adjustment amount into a change in the stepper motor's rotation angle Δθ. This change is then transmitted via a mechanical transmission device, causing the valve stem to move axially, thereby controlling the opening area of ​​the valve core relative to the flow channel.

[0104]

[0105] Where Δx is the valve stem displacement. This is the motor step angle conversion factor. The pitch of the threaded drive. By precisely controlling the stepping pulse signal, fine-grained adjustment of the valve core's opening and closing action can be achieved, making the steam flow rate change continuous, smooth, and controllable.

[0106] When establishing a flow characteristic model for a steam valve, it is necessary to obtain actual flow response data under different valve openings through experimental calibration. In the experiment, the steam pressure is kept constant, and the valve opening is gradually changed. Record the corresponding traffic value This yields a set of discrete sampling points. The least squares method is used for nonlinear fitting to obtain the function describing the valve characteristics:

[0107]

[0108] Where q represents the steam flow rate. Indicates the valve opening degree. The coefficients are the fitting coefficients. This model reveals the nonlinear relationship between valve opening and flow rate, typically exhibiting sluggish response in the small opening region, sensitivity to changes in the intermediate range, and saturation in the large opening region.

[0109] When generating the valve characteristic correction function after inverse-functioning the nonlinear relationship function, the inverse function of the above-mentioned fitted relationship is taken. Used to calculate linear equivalent opening degree ,in The target flow rate is defined by the correction function, which converts the target control signal output by the control system into a valve opening command that is linearly corresponding to the flow rate, thereby compensating for the inherent nonlinear characteristics of the valve. In this way, when the target control signal changes linearly, the actual steam flow rate also maintains a linear response, ensuring the stability and proportional consistency of temperature regulation.

[0110] During valve regulation, when the valve characteristic correction function is invoked in real time, the linearized corrected valve opening command is calculated based on the current target control signal in each sampling period. To avoid mechanical shock or delay caused by the step response, an interpolation compensation algorithm is introduced to smooth the opening command. The interpolation function can be expressed as:

[0111]

[0112] in, This refers to the previous actual opening degree. For the current target opening degree, The sampling period is specified. Interpolation compensation ensures that the valve adjusts at a continuous rate of change within the sampling period, avoiding mechanical oscillations and improving response accuracy.

[0113] After acquiring the real-time feedback signal from the valve position sensor, it is compared with the theoretical opening command. When the two deviate... Exceeding the set threshold At this time, the closed-loop correction algorithm is triggered to adjust the stepper motor drive current or pulse frequency, so that the actual opening degree quickly approaches the target opening degree. The closed-loop correction follows the proportional correction principle:

[0114]

[0115] in, To correct the current, This is the feedback correction coefficient. Real-time feedback and correction ensure that the valve's execution accuracy remains consistent with the control system output.

[0116] When calculating the real-time output value of steam flow based on the valve opening after linearization correction, a flow sensor is used to detect the current steam velocity and total flow rate, and compared with the theoretical flow rate. Perform an error comparison. If the flow rate deviation... Exceeding the permitted range Then the coefficient set of the valve characteristic correction function is dynamically adjusted. This enables online self-calibration, thereby compensating for characteristic drift caused by factors such as steam pressure fluctuations and valve body wear.

[0117] During continuous operation of the cross-linking chamber, dynamic steam flow regulation is performed based on the linearized valve characteristic model. When a decrease in temperature deviation is detected, the control system slowly reduces the valve opening at a linear rate, thereby reducing the steam input and preventing overheating. When the temperature deviation increases, the valve opening steadily increases at a linear rate to increase the heat input rate. The linearization characteristic ensures a strict proportional relationship between valve action and the target control signal, making the steam flow output completely synchronized with the temperature regulation process, thus achieving high-precision, low-fluctuation, and predictable thermal energy control.

[0118] This embodiment also discloses an intelligent control device for a steam crosslinking chamber, as described above. Figure 2 The device includes an acquisition module 201, a processing module 202, and an output module 203. It is used to execute any of the above-described intelligent control methods for a steam cross-linking chamber, wherein: The acquisition module 201 is used to collect temperature parameters, steam parameters and ambient humidity parameters inside the steam crosslinking chamber in real time, and form a time-synchronized multi-parameter observation vector. Processing module 202 is used to establish a dynamic heat conduction model of the cross-linking chamber based on multi-parameter observation vectors. The dynamic heat conduction model is used to describe the nonlinear coupling relationship between temperature, steam flow rate and thermal inertia. Processing module 202 is used to calculate the temperature deviation and error change rate based on the set temperature and the real-time detected temperature, adjust the PID parameters in real time based on the temperature deviation and error change rate, and output control quantity; The processing module 202 is used to predict the temperature trajectory within multiple sampling periods in the future based on the control quantity using a dynamic heat conduction model, and to calculate the objective function with the target temperature as a reference. Under the condition of constraining the change of the control quantity, the objective function is optimized to determine the current optimal control increment. Processing module 202 is used to construct a multi-objective optimization function based on temperature deviation energy integral, steam energy consumption index and temperature fluctuation variance of the optimal control increment, adjust the weight of each objective function in real time, and output the target control signal. The output module 203 is used to control the actuator to adjust the opening of the steam valve according to the target control signal. The opening of the steam valve is linearized and compensated by the valve characteristic correction function, so that the nonlinear response of the valve is converted into a steam flow output proportional to the target control signal.

[0119] It should be noted that the above embodiments of the apparatus are only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0120] This embodiment also discloses an electronic device, as shown in the reference. Figure 3 The electronic device may include: at least one processor 301, at least one communication bus 302, user interface 303, network interface 304, and at least one memory 305.

[0121] The communication bus 302 is used to enable communication between these components.

[0122] The user interface 303 may include a display screen and a camera. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0123] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0124] The processor 301 may include one or more processing cores. The processor 301 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 305, and by calling data stored in memory 305. Optionally, the processor 301 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 301 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 301 and may be implemented as a separate chip.

[0125] The memory 305 may include random access memory (RAM) or read-only memory. Optionally, the memory may include a non-transitory computer-readable storage medium. The memory 305 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), instructions for implementing the various method embodiments described above, etc.; the data storage area may store data involved in the various method embodiments described above, etc. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned processor 301. As a computer storage medium, the memory 305 may include an operating system, a network communication module, a user interface 303 module, and an application program for an intelligent control method for a steam crosslinking chamber.

[0126] exist Figure 3 In the electronic device shown, the user interface 303 is mainly used to provide an input interface for the user and to obtain the user input data; while the processor 301 can be used to call the application program of a steam crosslinking chamber intelligent control method stored in the memory 305. When executed by one or more processors 301, the electronic device performs one or more methods as described in the above embodiments.

[0127] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, as some steps can be performed in other orders or simultaneously according to the present invention. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0128] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0129] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between apparatuses or units may be electrical or other forms.

[0130] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0131] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0132] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory 305 and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned memory 305 includes various media capable of storing program code, such as a USB flash drive, external hard drive, magnetic disk, or optical disk.

[0133] The present invention also discloses a computer-readable storage medium storing instructions. When executed by one or more processors 301, these instructions cause an electronic device to perform one or more methods as described in the above embodiments.

Claims

1. A method for intelligent control of a steam cross-linking chamber, characterized in that, The method includes: Real-time acquisition of temperature, steam, and ambient humidity parameters inside the steam crosslinking chamber to form a time-synchronized multi-parameter observation vector; Based on the multi-parameter observation vector, a dynamic heat conduction model of the cross-linking chamber is established. The dynamic heat conduction model is used to describe the nonlinear coupling relationship between temperature, steam flow rate and thermal inertia. Calculate the temperature deviation and error rate of change based on the set temperature and the real-time detected temperature, and adjust the PID parameters in real time based on the temperature deviation and the error rate of change to output the control quantity. Based on the control quantity, the temperature trajectory within multiple future sampling periods is predicted using the dynamic heat conduction model, and the objective function is calculated with the target temperature as a reference. The objective function is then optimized under the constraint of control quantity changes to determine the current optimal control increment. The optimal control increment is constructed based on the temperature deviation energy integral, steam energy consumption index and temperature fluctuation variance to build a multi-objective optimization function, and the weights of each objective function are adjusted in real time to output the target control signal. According to the target control signal, the control actuator adjusts the opening of the steam valve. The opening of the steam valve is linearized and compensated by the valve characteristic correction function, so that the nonlinear response of the valve is converted into a steam flow output proportional to the target control signal. The establishment of a dynamic heat conduction model for the cross-linked chamber based on the multi-parameter observation vector specifically includes: For the temperature distribution characteristics, steam flow characteristics, steam pressure characteristics and humidity characteristics in the observation vector, the correspondence between the temperature change rate and the steam flow change within the sampling period is calculated by the least squares algorithm and the recursive parameter identification algorithm. The thermal response coefficient, thermal inertia time constant and time delay parameters are extracted to generate an intermediate parameter matrix describing the nonlinear coupling relationship between steam input and temperature change. Substitute the intermediate parameter matrix into the structured heat conduction equations to establish a multivariate coupled dynamic heat conduction model. The input variables of the dynamic heat conduction model are steam flow rate and steam pressure, and the output variable is the temperature response of the cross-linking chamber. Time delay units and nonlinear correction terms are introduced into the model structure of the dynamic heat conduction model to compensate for the energy transfer deviation caused by changes in the heat capacity of the chamber and steam condensation. During the crosslinking process, the model parameters of the dynamic heat conduction model are continuously updated. Based on the updated temperature response and steam flow deviation, a recursive least squares algorithm is executed to correct the thermal response coefficient and time delay parameters, thereby achieving adaptive learning of thermal characteristics under different loads, different steam pressures and different external environments.

2. The intelligent control method for a steam cross-linking chamber according to claim 1, characterized in that, The process of calculating the temperature deviation and error rate of change based on the set temperature and the real-time detected temperature, adjusting the PID parameters in real time based on the temperature deviation and the error rate of change, and outputting a control quantity specifically includes: Real-time temperature data detected inside the steam crosslinking chamber is received during each sampling period; The real-time temperature data is compared with the set temperature to calculate the first temperature deviation value of the current sampling period, and the second temperature deviation value of the previous sampling period is recorded at the same time. The rate of change of temperature error between the first temperature deviation value and the second temperature deviation value is calculated using a differential method. The temperature deviation and the rate of change of temperature error are fuzzified according to a preset membership function. The proportional coefficient adjustment, integral coefficient adjustment and differential coefficient adjustment are output according to the control semantic rules defined in the rule base to obtain the fuzzy inference output result. The original PID parameters are corrected in real time based on the fuzzy inference output to obtain updated proportional coefficient, integral coefficient and derivative coefficient. The proportional coefficient is used to adjust the temperature response rate, the integral coefficient is used to eliminate steady-state error, and the derivative coefficient is used to suppress temperature overshoot. The PID parameter correction results are then corrected a second time based on the temperature response characteristics output by the dynamic heat conduction model to keep the PID control process dynamically coupled with the steam flow rate change. The control system will perform control calculations using the updated PID parameters, and calculate the output control quantity based on the temperature deviation, error integral, and error change rate within the current sampling period.

3. The intelligent control method for a steam cross-linking chamber according to claim 1, characterized in that, Based on the control quantity, the dynamic heat conduction model is used to predict the temperature trajectory over multiple future sampling periods. An objective function is calculated using the target temperature as a reference. The objective function is then optimized under constraints on the control quantity to determine the current optimal control increment. Specifically, this includes: Within the current sampling period, acquire the historical control quantities and corresponding multi-parameter observation vectors from the previous sampling period; The historical control quantity and the multi-parameter observation vector are used to calculate the dynamic response relationship between steam input and temperature change based on thermal response coefficient, thermal inertia time constant and time delay parameter, and a temperature prediction sequence corresponding to multiple future sampling periods is generated. An objective function is established based on the temperature prediction sequence. The objective function uses the sum of squared deviations between the predicted temperature values ​​and the target temperature over multiple future sampling periods as the optimization objective. A control variable constraint term is introduced to constrain the steam valve regulation rate. The objective function obtains a balanced control strategy by dynamically adjusting the weights of the temperature deviation term and the control smoothing term. The objective function is optimized based on valve opening limits, control increment constraints, and system response delay constraints. A sequential quadratic programming algorithm is used to perform iterative calculations in the prediction time domain to obtain the optimal control increment that minimizes the objective function. The optimal control increment is used to correct the steam valve opening to compensate for future predicted temperature deviations. The optimal control increment is superimposed with the historical control quantity to generate a corrected control quantity sequence. The dynamic heat conduction model is called again to re-predict the temperature of the control quantity sequence. If the predicted temperature still has a deviation that exceeds the preset tolerance threshold, the optimization weight is automatically adjusted or the prediction time domain is extended and the optimization calculation is repeated until the predicted temperature stabilizes within the target temperature range.

4. The intelligent control method for a steam cross-linking chamber according to claim 1, characterized in that, The process of constructing a multi-objective optimization function based on the temperature deviation energy integral, steam energy consumption index, and temperature fluctuation variance, adjusting the weights of each objective function in real time, and outputting the objective control signal specifically includes: The optimal control increment is superimposed with the historical control quantity to form a control quantity change sequence; The temperature deviation energy integral of the steam crosslinking chamber within a preset time window is calculated based on the control quantity change sequence. The temperature deviation energy integral is obtained by integrating the square of the temperature deviation with the temperature correction value under the action of the optimal control increment, and is used to characterize the contribution of the optimal control increment to the steady-state temperature performance. The steam energy consumption index is calculated based on the change in steam valve opening caused by the optimal control increment. The steam energy consumption index is determined by a combination of steam flow rate, steam pressure difference and valve dynamic response rate, and is used to reflect the impact of the optimal control increment on steam energy utilization efficiency. Calculate the temperature fluctuation variance of the temperature sequence before and after applying the optimal control increment, and use the temperature fluctuation variance to quantify the degree of improvement of temperature stability by the optimal control increment; A multi-objective optimization function is constructed, wherein the common optimization objective is to minimize the temperature deviation energy integral, the steam energy consumption index, and the temperature fluctuation variance, and dynamic weight coefficients are set for each objective. When the optimal control increment is detected to cause an increase in the temperature deviation energy integral, the weight of temperature control accuracy is automatically increased; when the steam energy consumption index is detected to increase, the weight of energy consumption optimization is automatically increased; when the temperature fluctuation variance is detected to increase, the weight of temperature stability is automatically increased. The optimal control increment is used as the initial search point and input into the particle swarm optimization algorithm. Global search and local convergence are performed in the multi-objective optimization function space. The target control signal with the best comprehensive performance is obtained by iterative evaluation of different combinations of optimal control increments.

5. The intelligent control method for a steam cross-linking chamber according to claim 1, characterized in that, The step of controlling the actuator to adjust the opening of the steam valve according to the target control signal, wherein the opening of the steam valve is linearized and compensated by a valve characteristic correction function, so that the nonlinear response of the valve is converted into a steam flow output proportional to the target control signal, specifically including: The target control signal is used as the input basis for the ideal flow adjustment of the steam valve, and the expected opening adjustment amount of the valve is determined according to the amplitude and direction of change of the target control signal. The displacement of the steam valve stem is adjusted by a stepper motor according to the expected opening degree, so that the valve core performs corresponding opening and closing actions along the flow channel, thereby forming dynamic regulation of steam flow. A flow characteristic model of a steam valve was established. The actual steam flow response curves of the valve at different opening degrees were obtained through experimental calibration. The nonlinear relationship function between valve opening degree and steam flow rate was established by least squares fitting. The nonlinear relationship function is inversely transformed to generate a valve characteristic correction function, which is used to convert the target control signal into an equivalent opening command that is linearly corresponding to the steam flow rate, thereby compensating for the nonlinear response of the valve in the small and large opening ranges. During valve regulation, the valve characteristic correction function is called in real time to calculate the linearized corrected valve opening command based on the current target control signal, and interpolation compensation is performed in combination with the mechanical transmission characteristics and response inertia of the actuator. The real-time feedback signal from the valve position sensor is obtained and compared with the calculated theoretical opening. When the valve position deviation exceeds the set threshold, the execution current or step pulse is adjusted through a closed-loop correction algorithm to achieve dynamic tracking of the actual valve opening to the target opening command. The real-time output value of steam flow is calculated based on the valve opening after linearization correction. The real-time output value of steam flow is collected by a flow sensor and compared with the theoretical steam flow for error. When the flow deviation is detected to exceed the preset range, the coefficients of the valve characteristic correction function are updated. During the continuous operation of the cross-linking chamber, the steam flow is dynamically adjusted based on the linearized valve characteristic model. When the temperature deviation decreases, the valve opening gradually decreases at a linear rate to reduce the steam input. When the temperature deviation increases, the valve opening gradually increases at a linear rate to increase the steam input, so that the steam flow output maintains a linear proportional relationship with the target control signal.

6. The intelligent control method for a steam cross-linking chamber according to claim 1, characterized in that, The real-time acquisition of temperature, steam, and ambient humidity parameters inside the steam crosslinking chamber forms a time-synchronized multi-parameter observation vector, specifically including: The collected temperature, steam flow, steam pressure, and humidity signals are converted into timestamped data frames. The data frames are cached and sorted according to their timestamps. Data with time deviations are synchronously corrected using linear interpolation to obtain a corrected data sequence. The corrected data sequence is normalized, and a structured data matrix is ​​generated based on the spatial deployment location of each sensor, so that each column corresponds to a physical quantity and each row corresponds to the multi-source measurement value at the same time. The structured data matrix is ​​transformed into a multi-parameter observation vector, where each element of the multi-parameter observation vector corresponds to the temperature distribution feature, steam flow feature, steam pressure feature, and humidity feature, respectively, and an observation vector sequence is formed within a continuous sampling period.

7. A smart control device for a steam cross-linking chamber, characterized in that, The device is used to execute a smart control method for a steam crosslinking chamber as described in any one of claims 1-6, the device comprising an acquisition module, a processing module, and an output module, wherein: The acquisition module is used to collect temperature parameters, steam parameters and ambient humidity parameters inside the steam crosslinking chamber in real time, forming a time-synchronized multi-parameter observation vector. The processing module is used to establish a dynamic heat conduction model of the cross-linking chamber based on the multi-parameter observation vector. The dynamic heat conduction model is used to describe the nonlinear coupling relationship between temperature, steam flow rate and thermal inertia. The processing module is used to calculate the temperature deviation and error change rate based on the set temperature and the real-time detected temperature, adjust the PID parameters in real time based on the temperature deviation and the error change rate, and output the control quantity. The processing module is used to predict the temperature trajectory within multiple future sampling periods based on the control quantity using the dynamic heat conduction model, and to calculate the objective function with the target temperature as a reference. Under the condition of constraining the change of the control quantity, the objective function is optimized to determine the current optimal control increment. The processing module is used to construct a multi-objective optimization function based on the temperature deviation energy integral, steam energy consumption index and temperature fluctuation variance of the optimal control increment, adjust the weight of each objective function in real time, and output the target control signal. The output module is used to control the actuator to adjust the opening of the steam valve according to the target control signal. The opening of the steam valve is linearized and compensated by the valve characteristic correction function, so that the nonlinear response of the valve is converted into a steam flow output proportional to the target control signal.

8. An electronic device, characterized in that, The device includes a processor, a communication bus, a user interface, a network interface, and a memory. The memory is used to store instructions. The user interface and the network interface are both used to communicate with other devices. The communication bus is used to enable communication between the components within the electronic device. The processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed, perform the method as described in any one of claims 1-6.

Images