Method, device, medium and electronic equipment for increasing waste heat recovery steam generation

Abstract

This application discloses a method, apparatus, medium, and electronic device for increasing the steam generation capacity of waste heat recovery. The method includes: updating the current control parameters of the steam drum pressure control module based on a target parameter combination; and during the online operation of the target parameter combination, statistically analyzing the steam generation capacity of the steam drum using a preset sliding window to obtain the variance and mean of the steam generation capacity; wherein the target parameter combination is composed of the optimization result value of the proportional coefficient and the integral time; if the variance of the steam generation capacity exceeds a preset variance threshold within the preset sliding window or the increase in the mean of the steam generation capacity for a consecutive preset number of windows is lower than a preset increase threshold, a step disturbance test is triggered; in response to the step disturbance test, the control parameter optimization operation is re-executed to obtain a new parameter combination, and the current control parameters are updated based on the new parameter combination. Implementing the technical solution of this application can improve the steam generation capacity and its stability.

Description

Technical Field

[0001] This application relates to the field of industrial waste heat recovery and process control technology, and in particular to a method, apparatus, readable storage medium and electronic device for increasing the amount of waste heat recovery steam generated. Background Technology

[0002] In industrial waste heat recovery systems, generating steam by recovering the waste heat carried by high-temperature waste gas and waste liquid is an important means to improve energy utilization efficiency and reduce dependence on external fuels. In this process, the stable control of the steam drum pressure directly affects the amount of steam generated.

[0003] The relevant technologies generally rely on manual experience to tune the proportional coefficient and integral time. The tuned parameters remain fixed for a long time, making it difficult to adapt to changes in operating conditions such as heat exchanger scaling and production load fluctuations. When the operating conditions deviate, the fixed control parameters can easily cause the steam drum pressure regulating valve to oscillate and overshoot, increasing the fluctuation range of the steam drum liquid level. This not only restricts the increase in steam generation but also accelerates the wear of the regulating valve. Summary of the Invention

[0004] This application provides a method, apparatus, readable storage medium, and electronic device for increasing the steam generation capacity of waste heat recovery, which effectively improves the steam generation capacity and its stability.

[0005] According to a first aspect of this application, a method for increasing the steam generation capacity for waste heat recovery is provided, the method comprising: The current control parameters of the steam drum pressure control module are updated based on the target parameter combination. During the online operation of the target parameter combination, the steam generation of the steam drum is statistically analyzed using a preset sliding window to obtain the variance and mean of the gas production. The target parameter combination consists of the optimization result value of the proportional coefficient and the integral time. If the variance of gas production exceeds a preset variance threshold within the preset sliding window, or if the average increase in gas production for a consecutive preset number of windows is lower than a preset increase threshold, a step disturbance test is triggered. In response to the step disturbance test, the control parameter optimization operation is re-executed to obtain a new parameter combination, and the current control parameters are updated based on the new parameter combination.

[0006] According to a second aspect of this application, a waste heat recovery steam generation boosting device is provided, the device comprising: The data statistics module is used to update the current control parameters of the steam drum pressure control module based on the target parameter combination, and to statistically analyze the steam generation of the steam drum using a preset sliding window during the online operation of the target parameter combination to obtain the variance and mean of the gas production; wherein, the target parameter combination is composed of the optimization result value of the proportional coefficient and the integral time. The disturbance triggering module is used to trigger a step disturbance test if the variance of gas production exceeds a preset variance threshold within the preset sliding window or if the average increase of gas production in a consecutive preset number of windows is lower than a preset increase threshold. The optimization execution module is used to respond to the step disturbance test by re-executing the control parameter optimization operation to obtain a new parameter combination, and updating the current control parameters based on the new parameter combination.

[0007] According to a third aspect of the present invention, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the waste heat recovery steam generation increase method as described in embodiments of this application.

[0008] According to a fourth aspect of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the waste heat recovery steam generation increase method as described in the embodiments of the present application.

[0009] According to a fifth aspect of this application, an embodiment of this application provides a computer program product, including a computer program that, when executed by a processor, implements the waste heat recovery steam generation increase method as described in the embodiment of this application.

[0010] The technical solution of this application continuously statistically analyzes the steam generation during the online operation of the target parameter combination using a preset sliding window, obtaining the variance and mean of the steam generation, thus achieving data-driven monitoring of the actual performance of the control parameters. When the variance of the steam generation exceeds the threshold or the increase in the mean of the steam generation is consistently insufficient, a step disturbance test is automatically triggered and the control parameter optimization operation is re-executed to obtain a new parameter combination. This ensures that the proportional coefficient and integral time can be matched with the current operating conditions in real time, effectively suppressing steam drum pressure fluctuations caused by parameter mismatch and improving the steam generation and its stability.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of the waste heat recovery steam generation method provided in Example 1; Figure 2 This is a flowchart of the waste heat recovery steam generation method provided in Example 2; Figure 3 This is a schematic diagram of the waste heat recovery steam generation boosting device provided in Embodiment 3 of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of this application. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0015] It should be noted that the terms "first," "second," "target," and "candidate," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] Example 1 Figure 1 This is a flowchart of the waste heat recovery steam generation increase method provided in Embodiment 1. This embodiment is applicable to the business scenario of increasing steam generation through adaptive control of steam drum pressure in industrial waste heat recovery process. This method can be executed by a waste heat recovery steam generation increase device, which is implemented in hardware and / or software and can be integrated into the electronic equipment running this system.

[0017] like Figure 1 As shown, the method includes: S110. Update the current control parameters of the steam drum pressure control module based on the target parameter combination, and during the online operation of the target parameter combination, statistically analyze the steam generation of the steam drum using a preset sliding window to obtain the variance and mean of the gas production; wherein, the target parameter combination consists of the optimization result value of the proportional coefficient and the integral time.

[0018] S120. If the variance of gas production exceeds a preset variance threshold within the preset sliding window, or if the average increase in gas production for a consecutive preset number of windows is lower than a preset increase threshold, then a step disturbance test is triggered.

[0019] S130. In response to the step disturbance test, re-execute the control parameter optimization operation to obtain a new parameter combination, and update the current control parameters based on the new parameter combination.

[0020] The target parameter combination is a set of optimized values ​​consisting of a proportional coefficient and an integral time, used to replace the current control parameters to control the steam drum pressure. First, this target parameter combination is written into the steam drum pressure control module to complete the online update of the current control parameters. After the update, during online operation, a preset sliding window is immediately started to continuously count the steam generation from the steam drum. The preset sliding window is a data interval that slides forward at a fixed time length, such as 1 hour, as the statistical unit, with a set step size, such as every 10 minutes. Let the steam generation data point within the current window be... , ,…, ,in n This refers to the number of sampling points within the window, such as sampling once per minute. n =60, Calculate the average steam production rate within the steam generation window. and gas production variance .use Calculate the average gas production ;use Calculate the variance of gas production .

[0021] The average steam production reflects the overall level of steam generation under the target parameter combination, while the variance of steam production reflects the degree of fluctuation in steam generation. Using the variance and average steam production as the basis for judging whether the target parameter combination is still suitable for the operating conditions is because when the control parameters are mismatched with the dynamic characteristics of the steam drum pressure, the steam drum pressure will fluctuate more, directly resulting in an increase in the variance of steam generation. Simultaneously, if the parameters have lost their optimization effect, the steam generation will stagnate at a certain level for a long period without further improvement, manifested as a persistently low increase in the average steam production.

[0022] Based on the above statistical results, determine whether a step disturbance test has been triggered. Define the increase in the average gas production rate. The average gas production rate for the current window Compared to the baseline value of average gas production during the stable period before optimization Relative changes: .

[0023] When the gas production variance Exceeding the preset variance threshold This indicates that the system has entered an unstable state, and the current combination of target parameters cannot maintain stable control of the steam drum pressure. The preset variance threshold can be three times the variance of the gas production during the normal production period before optimization. Alternatively, it can be the average increase in gas production over a consecutive preset number of windows, such as three consecutive sliding windows. All were below the preset increase threshold for average gas production increase. ,like This indicates that the target parameter combination can no longer increase steam generation, and the optimization potential of the control parameters has been exhausted. If either of the above two conditions is met, a step disturbance test is automatically triggered.

[0024] A step disturbance test involves applying a sudden step disturbance signal to the steam drum pressure setpoint, such as stepping the setpoint from 1.0 MPa to 1.1 MPa. The step amplitude is taken as 5% to 10% of the rated pressure. The characteristic data of the controlled object are obtained through the dynamic response of the active excitation system, which provides an information basis for subsequent control parameter optimization operations.

[0025] In response to the triggered step disturbance test, the control parameter optimization operation is re-executed. This operation uses the proportional coefficient P and integral time I as decision variables, and minimizes the integral deviation value as the objective function. The integral deviation value is obtained by calculating the integral absolute error (IAE) from the steam drum liquid level response curve recorded from the step disturbance test. Its discrete calculation formula is as follows: ;in For the first i Measured values ​​of steam drum liquid level at each sampling time. This is the steady-state final value, i.e., the setpoint. The sampling period is 1 second. The smaller the IAE value, the closer the steam drum liquid level response curve is to the ideal step response, and the better the control performance. The control parameter optimization operation searches in the parameter space using a particle swarm optimization algorithm, outputs a new parameter combination, namely the new optimized values ​​of the proportional coefficient and integral time, and updates the current control parameters based on this new parameter combination, completing a full online adaptive adjustment.

[0026] Since the new parameter combination is obtained by re-optimizing based on the actual response data of the step disturbance test under the current actual operating conditions, it is more suitable for the dynamic characteristics of the controlled object that have changed compared with the original parameter combination. Therefore, it can restore or increase the steam generation and maintain stable control of the steam drum pressure. The entire closed-loop process allows the proportional coefficient and integral time to be continuously updated with changes in operating conditions, achieving adaptive improvement of the steam generation of the waste heat recovery system without manual intervention.

[0027] The technical solution of this application continuously statistically analyzes the steam generation during the online operation of the target parameter combination using a preset sliding window, obtaining the variance and mean of the steam generation, thus achieving data-driven monitoring of the actual performance of the control parameters. When the variance of the steam generation exceeds the threshold or the increase in the mean of the steam generation is consistently insufficient, a step disturbance test is automatically triggered and the control parameter optimization operation is re-executed to obtain a new parameter combination. This ensures that the proportional coefficient and integral time can be matched with the current operating conditions in real time, effectively suppressing steam drum pressure fluctuations caused by parameter mismatch and improving the steam generation and its stability.

[0028] In an optional embodiment, the method further includes: monitoring the opening signal of the steam drum pressure regulating valve during the online operation of the target parameter combination; if the opening signal shows two consecutive extreme points in opposite directions, and the amplitude difference between the two extreme points exceeds a preset amplitude, then it is determined that the steam drum pressure regulating valve is oscillating; if the steam drum pressure regulating valve is oscillating or the average gas production indicates a decrease in steam generation, then the current control parameters are rolled back to effective control parameters.

[0029] After the target parameter combination is deployed online and put into operation, online safety monitoring of the steam drum pressure regulating valve is initiated simultaneously. This monitoring mechanism is independent of the statistical analysis of steam generation and is an event-driven, real-time protection measure. Its core logic is: when the newly deployed target parameter combination becomes unsuitable under the current operating conditions, it can automatically restore the control parameters to effective control parameters before causing more serious consequences. Effective control parameters refer to the set of proportional coefficients and integral times that have been running online in the steam drum pressure control module before this parameter update and have not triggered rollback conditions. Effective control parameters are the control parameter combination that has been most recently verified as safe and effective during all parameter updates, meaning that there has been no oscillation after deployment and no decrease in steam generation; this is the safety baseline for parameter updates.

[0030] The monitored object is the opening signal of the steam drum pressure regulating valve, which directly reflects the output behavior of the PID control module. Within a complete regulation cycle, i.e., the regulation cycle refers to the time interval from the start of one fluctuation in the steam drum pressure to the start of the next fluctuation in the same direction, typically taken as the critical oscillation period. The amplitude difference between the two extreme points is 1 to 2 times that of the maximum value. The opening signal is continuously acquired and its local extreme points are detected. If two consecutive extreme points in opposite directions occur within this period (i.e., a maximum value appears first followed by a minimum value, or a minimum value appears first followed by a maximum value), and the amplitude difference between these two extreme points is significant... Exceeding the preset amplitude If this occurs, it is determined that the steam drum pressure regulating valve is experiencing reciprocating oscillation. (Preset amplitude) Take 5% of the rated stroke of the steam drum pressure regulating valve, that is: ,in This refers to the rated stroke of the steam drum pressure regulating valve. Reciprocating oscillation is a typical manifestation of severe mismatch in control parameters, meaning that the setting of the proportional coefficient or integral time causes the controller output to continuously overshoot. The steam drum pressure regulating valve moves violently back and forth in opposite directions, which not only fails to maintain the stability of the steam drum pressure, but also drastically accelerates the mechanical wear of the regulating valve.

[0031] At the same time, it also monitors whether the steam generation rate is decreasing, based on the average gas production rate during the current cycle. Baseline gas production under the same operating conditions as before optimization Comparison of baseline gas production. The average gas production was taken from the previous 24 hours before optimization. If the average gas production rate decreases instead of increasing, it is determined that the average gas production rate represents a decrease in steam generation. This means that the newly deployed target parameter combination not only failed to increase steam generation but also lowered it than before, resulting in a substantial decline in control performance.

[0032] If either of the above two conditions—reciprocating oscillation or a decrease in steam generation—is met, a rollback operation is immediately executed. The rollback operation restores the proportional gain and integral time in the steam drum pressure control module to their values ​​before this optimization, i.e., the previous set of control parameters, via a communication protocol. Simultaneously, the current timestamp, the parameter combination attempted, and the reason for failure are recorded in the optimization log. This parameter update is marked as an invalid iteration, and a cooling timer is started. During the subsequent preset cooling period (e.g., 60 minutes), any new parameter optimization or write operations are prohibited until the cooling time ends.

[0033] The above technical solution monitors the extreme points and amplitude differences of the steam drum pressure regulating valve opening signal online. It uses two consecutive extreme points with opposite directions and an amplitude difference exceeding a preset value as the criterion for oscillation. Simultaneously, it uses the average steam production rate to characterize whether steam generation has decreased, thus achieving real-time identification of abnormal states after the deployment of target parameter combinations. Once oscillation or a decrease in steam generation is detected, the current control parameters are automatically rolled back to effective control parameters. This provides a reliable safety barrier for the system during parameter adaptive updates, avoiding continuous fluctuations in steam drum pressure and steam generation loss due to parameter mismatch. It achieves adaptive optimization of control parameters while ensuring safety.

[0034] In an optional embodiment, the target parameter combination is determined as follows: a step disturbance signal is applied to the steam drum pressure setpoint, and dynamic response data of the steam drum pressure value changing with the step disturbance signal is collected; the dynamic response data is subjected to signal filtering and time series analysis to extract pressure overshoot, oscillation period, and steady-state error characteristics, and a set of characteristic parameters reflecting the dynamic characteristics of the system is constructed; the change in the opening of the regulating valve is used as input and the change in the steam drum pressure is used as output, and a first-order inertial plus pure lag model is used to fit the steam drum pressure object, and the model gain, time constant, and lag time are calculated by the least squares identification algorithm to obtain the controlled object model; the proportional coefficient and integral time are used as decision variables, the minimization of the integral value of the deviation is used as the objective function, and the controlled object model is used as the performance evaluation model in the optimization process, and the target parameter combination is obtained by searching through the particle swarm optimization algorithm.

[0035] First, a step disturbance signal is applied to the steam drum pressure setpoint, and dynamic response data of the steam drum pressure value as a function of this step disturbance signal is collected. The step disturbance signal refers to a sudden change in the steam drum pressure setpoint from one steady-state value to another, for example, a jump from 1.0 MPa to 1.1 MPa, with the step amplitude ranging from 5% to 10% of the rated pressure. Dynamic response data refers to the complete transient process data sequence of the controlled variable, i.e., the steam drum pressure value, over time after the sudden change in the steam drum pressure setpoint; that is, the pressure change curve from the original steady state, through dynamic adjustment, to the final reaching of the new steady state.

[0036] After acquiring the dynamic response data, signal filtering and time-series analysis are performed. Signal filtering employs a first-order low-pass digital filter for smoothing to remove high-frequency noise interference. The filter transfer function is... Its discretization iterative formula is: ;in, This is the current sampled value. This is the output value from the previous filter. The filter coefficients are set to values ​​from 0.1 to 0.3. After filtering, three types of features reflecting the system's dynamic characteristics are extracted from the response curve: pressure overshoot, which refers to the difference between the peak value and the steady-state final value of the response curve, i.e. The overshoot reflects the magnitude by which the response exceeds the target value; the oscillation period, the time interval between two consecutive crossings of the steady-state value in the same direction, reflects the system's damping characteristics; and the steady-state error characteristic refers to the deviation between the system's final stable value and the set value. By aligning the overshoot and oscillation period by timestamps, a set of characteristic parameters reflecting the system's dynamic characteristics is constructed. .

[0037] Next, using the change in the control valve opening as input and the change in the steam drum pressure as output, a first-order inertial plus pure time-delay model is used to fit the steam drum pressure object. The transfer function form of the first-order inertial plus pure time-delay model is as follows: .in, K The model gain represents the ratio of the steady-state change in output to the change in input. T This is the time constant, reflecting the magnitude of the system's inertia, and its unit is seconds; The lag time reflects the pure delay between a change in input and the start of an output response, measured in seconds. The first-order inertia plus pure lag model accurately describes the pressure object of the steam drum because, as a large-capacity thermal container, the steam drum, after receiving changes in the opening of the regulating valve, exhibits both a gradual accumulation process (inertia) and a response delay caused by fluid transport and heat transfer (pure lag). This closely matches the mathematical structure of the first-order inertia plus pure lag model.

[0038] Model parameters adopted The parameter vector is obtained by solving the least squares identification algorithm. Specifically, a data matrix A and an output vector b are constructed. Here, A consists of the input and output data at the sampling time, and b is the pressure response sequence. The parameter vector to be solved The numerical solutions for model gain, time constant, and lag time obtained from the identification together constitute the controlled object model.

[0039] Finally, using the proportional coefficient P and integral time I as decision variables, minimizing the integral deviation value as the objective function, and employing the controlled object model as the performance evaluation model in the optimization process, the objective parameter combination is obtained through particle swarm optimization. The integral deviation value is obtained by calculating the integral absolute error (IAE) from the steam drum liquid level response curve recorded in the step disturbance test. The optimization objective function with the proportional coefficient and integral time as decision variables is defined as follows: . P This is the proportionality coefficient. I The integral time is the time of integration, and the two together constitute the decision variable; IAE is the integral value of the deviation, which is obtained by calculating the integral absolute error of the steam drum liquid level response curve recorded from the step disturbance test.

[0040] In particle swarm optimization, the proportionality coefficient of each candidate group and the integration time are used. As input, the identified controlled object model is used to simulate the set of control parameters, and the integral deviation (IAE) of the corresponding drum liquid level response curve is calculated. This IAE value is used as the control performance evaluation value of the set of control parameters. The smaller the IAE value, the closer the drum liquid level response is to the ideal step response, and the better the control quality. Therefore, the particle swarm optimization algorithm takes minimizing this objective function as its search direction, and finally searches for the optimal control parameter. A set that obtains the minimum value This refers to the combination of target parameters.

[0041] The above technical solution, by applying a step disturbance signal and collecting dynamic response data, extracts features such as pressure overshoot and oscillation period through signal filtering and time series analysis, constructing a set of characteristic parameters reflecting the dynamic characteristics of the system. Then, a controlled object model is obtained through a first-order inertial plus pure time delay model and a least squares identification algorithm, providing a calculable performance evaluation model for parameter optimization. Using this model to replace the real system in particle swarm optimization simulation search, the control performance of each set of proportional coefficients and integral times can be quickly evaluated without repeatedly applying step disturbances. This avoids frequent interference with production operations and ensures the accuracy of target parameter combination optimization and the safety of online deployment.

[0042] In an optional embodiment, the method further includes: using the controlled object model and the current control parameters to determine the dynamic response characteristics of the steam drum pressure object to a step disturbance signal, and calculating the theoretical overshoot based on the dynamic response characteristics; applying a step disturbance signal to the steam drum pressure setpoint, and extracting the measured overshoot from the steam drum pressure response curve; if the residual between the theoretical overshoot and the measured overshoot exceeds a preset threshold for a set number of times, then based on the change in the opening of the steam drum pressure regulating valve and the change in the steam drum pressure during the online operation of the controlled object model, resolving the model gain, time constant, and lag time using the least squares identification algorithm to update the controlled object model.

[0043] During the online operation of the target parameter combination, the accuracy of the controlled object model is a prerequisite for ensuring the quality of control parameter search. However, the dynamic characteristics of the steam drum pressure object will slowly change due to factors such as heat exchanger fouling and production load fluctuations, causing the originally identified controlled object model to gradually deviate from the actual object. If this is not detected and updated, the control performance indicators calculated based on the inaccurate model will lose their reference value, thereby affecting the reliability of the target parameter combination searched by the subsequent particle swarm optimization algorithm. Therefore, by continuously verifying the consistency between the model output and the actual system response, the model is automatically re-identified when a significant deviation is detected.

[0044] First, using the controlled object model and current control parameters, the dynamic response characteristics of the steam drum pressure system to a step disturbance signal are determined, and the theoretical overshoot is calculated based on these dynamic response characteristics. The dynamic response characteristics refer to the damping degree and oscillation tendency of the output response curve of the closed-loop system under the action of a step disturbance signal; these characteristics are jointly determined by the controlled object model and the current control parameters. The identified model gain K, time constant T, and lag time are then used as parameters. τ Substituting the current proportional gain P and integral time I into the closed-loop transfer function, the damping ratio is obtained. And according to the overshoot formula of a standard second-order system Calculate theoretical overshoot Among them, the damping ratio It is obtained by solving the closed-loop characteristic equation, involving The relationship between the damping ratio and the controllable object model parameters is that the damping ratio is determined by the proportional gain, integral time, and controllable object model parameters. The theoretical overshoot reflects the theoretical percentage by which the peak response exceeds the steady-state final value after being subjected to a step disturbance signal, under the current model and control parameters.

[0045] Meanwhile, after the system reaches steady state, a step disturbance signal is applied to the steam drum pressure setpoint, and the measured overshoot is extracted from the steam drum pressure response curve. Measured overshoot Defined as the peak value of the response curve With steady-state final value The difference The measured overshoot directly comes from the step response of the real system and is actual operating data that does not depend on the model.

[0046] Then, based on Residual analysis is performed on the theoretical and measured overshoot to calculate the residuals. A preset residual threshold is set. For example, taking 5% of the steady-state final value, i.e. A counter is set up. After each step disturbance test, the residual is compared with a threshold: if the residual exceeds the preset threshold, the counter is incremented by 1; otherwise, the counter is reset to zero. When the residual exceeds the preset threshold for a set number of times, that is, when the counter accumulates to the set value, if three consecutive tests meet the threshold... When the controlled object model is determined to be unable to accurately describe the actual dynamic characteristics of the steam drum pressure object, the model has become invalid and needs to be updated.

[0047] Once the model is determined to be faulty, the model parameter re-identification process is immediately triggered. This is based on the changes in the opening degree of the steam drum pressure regulating valve recorded during the online operation of the controlled object model. Pressure change of steam drum The model parameters are then re-solved using the least squares identification algorithm. Specifically, the input and output data during the online operation of the controlled object model—that is, the period from the last model update to the failure determination—are extracted to construct a data matrix A and an output vector b. The parameter vector is then re-solved using the least squares formula. The updated model gain is obtained. Time constant and lag time The original model parameters are replaced with the updated model to complete the update of the controlled object model. The updated model is then reused for subsequent calculations of theoretical overshoot and settling time, ensuring that the control performance indicators are always based on an accurate object model.

[0048] The above technical solution establishes a continuous verification mechanism for model effectiveness by calculating the theoretical overshoot using the controlled object model and current control parameters, and comparing the residual with the measured overshoot extracted from the steam drum pressure response curve. When the residual exceeds a preset threshold for a set number of times, it indicates that the controlled object model can no longer accurately reflect the actual dynamic characteristics of the steam drum pressure object. At this time, based on the changes in the opening of the steam drum pressure regulating valve and the changes in steam drum pressure accumulated during the online operation of the controlled object model, the model gain, time constant, and lag time are re-solved using the least squares identification algorithm to update the model. This allows the controlled object model to adaptively correct itself according to changes in operating conditions, avoiding subsequent control parameter optimization operations based on an incorrect performance evaluation model due to model inaccuracy. This ensures the accuracy and continuous effectiveness of the target parameter combination optimization under time-varying operating conditions.

[0049] In an optional embodiment, the method further includes: obtaining the operating characteristics of the steam drum when the step disturbance test is triggered, the operating characteristics including average load and / or steam drum pressure range; associating the parameter combination obtained by re-executing the control parameter optimization operation with the operating characteristics when the step disturbance test is triggered, and storing it as a parameter optimization record in the optimization knowledge base.

[0050] After completing a full control parameter optimization operation and deploying the new target parameter combination online, this solution also includes a knowledge accumulation step to save the optimization experience and provide a basis for parameter initialization under similar working conditions in the future, thereby gradually establishing the system's adaptive learning capability.

[0051] First, the operating characteristics of the steam drum at the time the step disturbance test is triggered are obtained. Operating characteristics refer to a set of characteristic parameters reflecting the current operating environment and load state of the steam drum, including average load and / or steam drum pressure range. Average load reflects the overall level of steam consumption during production, and the steam drum pressure range reflects the operating range of the steam drum pressure. These operating characteristics are obtained at the moment this step disturbance test is triggered, and are consistent with the background operating conditions of this optimization operation in the time dimension.

[0052] After re-executing the control parameter optimization operation to obtain the parameter combination, this parameter combination is associated with the operating condition characteristics at the time the step disturbance test was triggered, and stored as a parameter optimization record in the optimization knowledge base. The optimization knowledge base is a storage unit used to store the experience data accumulated from previous control parameter optimization operations. Each parameter optimization record includes the target parameter combination consisting of a proportional coefficient and integral time, the corresponding operating condition characteristics, the optimization date, the increase in the average gas production, and the change in the average daily operating frequency of the control valve before and after optimization. The life loss data of the control valve can be calculated through the operating frequency, with each operation converted into a certain equivalent wear.

[0053] The above technical solution acquires the operating characteristics of the steam drum when a step disturbance test is triggered, and stores the parameter combination obtained by re-executing the control parameter optimization operation with the operating characteristics at the time of triggering the step disturbance test in the optimization knowledge base, thus forming a continuous accumulation of parameter optimization experience. As the records in the optimization knowledge base become richer, when the control parameter optimization operation needs to be re-executed under different operating conditions, the historical parameter optimization record that matches the current operating condition characteristics can be directly retrieved as the initial tuning benchmark for particle swarm optimization, avoiding starting the search from the general starting point determined by the constant amplitude oscillation test each time. This accelerates the convergence process of the particle swarm optimization algorithm, reduces the disturbance to production caused by the excessively long optimization process, and realizes adaptive learning capability based on historical experience.

[0054] Example 2 Figure 2 This is a flowchart of the waste heat recovery steam generation method provided in Example 2. This example is a further optimization based on the above examples.

[0055] like Figure 2 As shown, the method includes: S210. Update the current control parameters of the steam drum pressure control module based on the target parameter combination, and during the online operation of the target parameter combination, use a preset sliding window to statistically analyze the steam generation of the steam drum to obtain the variance and mean of the gas production; wherein, the target parameter combination consists of the optimization result value of the proportional coefficient and the integral time.

[0056] S220. If the variance of gas production exceeds a preset variance threshold within the preset sliding window, or if the average increase in gas production for a consecutive preset number of windows is lower than a preset increase threshold, then a step disturbance test is triggered.

[0057] S230. In response to the step disturbance test, using the proportional coefficient and the integral time as decision variables and minimizing the deviation integral value as the objective function, initialize the position of each particle in the particle swarm near the initial tuning reference; wherein, the deviation integral value is obtained by calculating the integral absolute error of the steam drum liquid level response curve recorded by the step disturbance test.

[0058] The decision variables are the variables that the particle swarm optimization algorithm needs to determine in the search space; in this case, they are the proportional coefficient P and the integration time I. The deviation integral value is obtained by calculating the integral absolute error (IAE) from the steam drum liquid level response curve recorded in the step disturbance test. The search space is a two-dimensional parameter plane composed of the proportional coefficient P and the integration time I. The objective function is defined as follows: .

[0059] The initial tuning datum is the starting position center for all particles in the particle swarm to begin their search. It plays the role of the search starting point in the particle swarm optimization algorithm. All particles are distributed around this datum in the parameter space, forming the initial search population. Let the particle swarm size be m, such as m=30, and the th... j The initial positions of the particles are ;in, , ; and The proportional gain and integral time are used in the initial tuning reference. exist Uniformly randomized values ​​are selected from the inside. exist The values ​​are uniformly and randomly selected within the range. The purpose of initializing the positions of each particle near the initial tuning benchmark is that the initial tuning benchmark is already a set of feasible parameters that have been verified in engineering. Searching in its vicinity ensures that the search starting point is located in a region with good control performance, avoiding the algorithm wasting computational resources in regions with invalid parameters.

[0060] S240. The position of each particle is iteratively updated through the particle swarm optimization algorithm, so that each particle converges to its individual optimal position and the global optimal position of the swarm.

[0061] After the particle swarm initialization is complete, the position of each particle is iteratively updated using the particle swarm optimization algorithm, causing each particle to converge towards its individual optimal position and the global optimal position of the swarm. In each iteration, for each particle... j Using the controlled object model through simulation Calculate the objective function value corresponding to its current position. Indicates the first j The position vector of each particle in the parameter space This is the proportionality coefficient corresponding to that particle. This is the integration time corresponding to the particle; IAE This is the integral value of the deviation.

[0062] Individual optimal position It is a particle j The position that minimizes the IAE value found in each iteration is the global optimal position for the population. It is the position found among all particles that minimizes the IAE value.

[0063] The formula for iteratively updating particle positions is: ; Among them, For particles j Movement speed, superscript k Indicates the first k iteration w The inertial weight, ranging from 0.7 to 0.9, is used to balance global and local searches; and The learning factor, ranging from 1.5 to 2.0, controls the acceleration of particles toward their individual optimal position and the global optimal position, respectively. and is a random number that is uniformly distributed in [0,1].

[0064] S250. When the preset convergence condition is met, output the proportional coefficient and integration time corresponding to the global optimal position of the group as the new parameter combination.

[0065] Preset convergence criteria are the rules for determining when the particle swarm optimization algorithm stops iterating, including reaching a preset maximum number of iterations, such as... Or, the absolute value of the change in the global optimal position of the population in multiple consecutive iterations is less than a preset threshold. ,Right now . The global optimal position for the population, i.e., the position found by all particles in each iteration that satisfies the objective function. The location where the minimum value is found. When one of the above conditions is met, it indicates that the particle swarm has converged sufficiently, and further iterations will not significantly improve the objective function value, so there is no need to continue the search.

[0066] At this time, based on The global optimal position of the group The corresponding proportionality coefficient and points time The extracted parameters are used as the output of this control parameter optimization operation, i.e., the new parameter combination. This parameter combination is the proportional coefficient and integration time that minimize the integral value of the deviation, obtained after a thorough search of the parameter space by the particle swarm optimization algorithm under the current operating conditions.

[0067] S260. Update the current control parameters based on the new parameter combination.

[0068] The technical solution of this application uses the proportional coefficient and integral time as decision variables and the minimization of the deviation integral value as the objective function, transforming the optimization of control parameters into a clear optimization problem. By initializing the particle swarm position near the initial tuning reference, the search starting point is placed within a verified safe and feasible region, accelerating convergence. The particle swarm optimization algorithm rapidly approaches the global optimum while maintaining search diversity through coordinated convergence towards individual optimal positions and the global optimum position of the swarm. Using simulation calculations of the deviation integral value from actual step disturbance experiments to evaluate each set of parameters avoids frequent interference with the production process, ensuring both optimization accuracy and online operational safety.

[0069] In an optional embodiment, the initial tuning benchmark is determined as follows: The operating characteristics of the steam drum are obtained when the positions of each particle in the particle swarm are initialized; a parameter optimization record matching the operating characteristics is retrieved from the optimization knowledge base; the optimization knowledge base stores parameter combinations obtained from previous parameter optimization operations and their associated operating characteristics; if a matching parameter optimization record is found, the parameter combination in that record is used as the initial tuning benchmark; if no matching parameter optimization record is found, the initial tuning benchmark is determined through a constant amplitude oscillation test.

[0070] The selection of the initial tuning benchmark directly affects the convergence speed and quality finding of the particle swarm optimization algorithm: if the starting position is too far from the true optimal parameters, the algorithm needs more iterations to converge, and may even get stuck in a local optimum.

[0071] First, the operating characteristics of the steam drum are obtained when initializing the positions of each particle in the particle swarm. These operating characteristics are acquired during particle swarm initialization and serve as query conditions for retrieving the optimization knowledge base. Then, parameter optimization records matching the current operating characteristics are retrieved from the optimization knowledge base. The optimization knowledge base can be stored in a relational database, with indexes created for the operating characteristic fields to support fast matching retrieval. The matching criterion is the degree of similarity between operating characteristics; for example, when both the average load and the steam drum pressure range are within a preset similarity interval, a matching parameter optimization record is considered to have been retrieved.

[0072] If a matching parameter optimization record is found, the parameter combination in that record is used as the initial tuning benchmark for this particle swarm optimization. This is because the dynamic characteristics of the steam drum pressure object are closely related to its operating conditions, and the optimal proportional coefficient and integral time under the same or similar operating conditions often have similarities. Using parameter combinations that have been verified to be effective under matching operating conditions as the search starting point allows the initial position of the particle swarm to be closer to the true optimal solution under the current operating conditions, thereby shortening the convergence time of the particle swarm optimization algorithm, improving the efficiency of parameter optimization, and reducing the disturbance to the production process caused by an excessively long optimization process.

[0073] If no matching parameter optimization record is found, the initial tuning reference is determined through a constant-amplitude oscillation test. The constant-amplitude oscillation test is a classic PID parameter engineering tuning method in process control. Specifically, the integral action is temporarily disabled, leaving only the proportional control. Starting with a small proportional coefficient, it is gradually increased while applying a step disturbance signal to the steam drum pressure setpoint and observing the steam drum pressure response curve. When the response curve exhibits sustained constant-amplitude oscillations, the proportional coefficient at this point is recorded as the critical gain. The period of the constant-amplitude oscillation is read from the curve as the critical oscillation period. The unit is seconds. Then, the initial tuning value is calculated according to the Ziegler-Nichols empirical formula: , Substitute the calculated initial setpoint into the system for a step disturbance test. If the steam drum liquid level response curve still shows significant overshoot, decrease the proportional coefficient by a fixed step size, such as 5% to 10% of the current P value, until the response curve converges and stabilizes. The proportional coefficient and integral time obtained at this time are the initial setpoint reference.

[0074] The above technical solution acquires the boiler drum operating condition characteristics during particle swarm optimization (PSO) initialization and prioritizes retrieving matching historical parameter optimization records from the optimization knowledge base as initial tuning benchmarks. This allows the PSO search starting point to utilize empirical data accumulated from previous parameter optimization operations, directly reusing verified parameter combinations under similar operating conditions. This accelerates the convergence process of the PSO algorithm and reduces invalid iterations caused by the search starting point deviating from the optimal solution. When matching records are lacking, the algorithm reverts to determining the initial tuning benchmark through constant-amplitude oscillation experiments, ensuring a safe and reliable search starting point even under operating conditions without available historical experience, thus balancing the efficiency and versatility of parameter optimization.

[0075] Example 3 Figure 3 This is a schematic diagram of the structure of the waste heat recovery steam generation enhancement device provided in Embodiment 3 of this application. This embodiment is applicable to the business scenario of increasing steam generation through adaptive control of steam drum pressure in the process of industrial waste heat recovery. The device can be implemented by software and / or hardware and can be configured in electronic equipment.

[0076] like Figure 3 As shown, the device may include: The data statistics module 310 is used to update the current control parameters of the steam drum pressure control module based on the target parameter combination, and to statistically analyze the steam generation of the steam drum using a preset sliding window during the online operation of the target parameter combination to obtain the variance and mean of the gas production; wherein, the target parameter combination is composed of the optimization result value of the proportional coefficient and the integral time. The disturbance triggering module 320 is used to trigger a step disturbance test if the variance of gas production exceeds a preset variance threshold or the average increase of gas production in a consecutive preset number of windows is lower than a preset increase threshold. The optimization execution module 330 is used to respond to the step disturbance test by re-executing the control parameter optimization operation to obtain a new parameter combination, and to update the current control parameters based on the new parameter combination.

[0077] The technical solution of this application continuously statistically analyzes the steam generation during the online operation of the target parameter combination using a preset sliding window, obtaining the variance and mean of the steam generation, thus achieving data-driven monitoring of the actual performance of the control parameters. When the variance of the steam generation exceeds the threshold or the increase in the mean of the steam generation is consistently insufficient, a step disturbance test is automatically triggered and the control parameter optimization operation is re-executed to obtain a new parameter combination. This ensures that the proportional coefficient and integral time can be matched with the current operating conditions in real time, effectively suppressing steam drum pressure fluctuations caused by parameter mismatch and improving the steam generation and its stability.

[0078] Optionally, the device further includes: a signal monitoring module, used to monitor the opening signal of the steam drum pressure regulating valve during the online operation of the target parameter combination; an oscillation identification module, used to determine that the steam drum pressure regulating valve is oscillating if the opening signal has two consecutive extreme points in opposite directions and the amplitude difference between the two extreme points exceeds a preset amplitude; and a parameter rollback module, used to roll back the current control parameters to effective control parameters if the steam drum pressure regulating valve is oscillating or if the average gas production rate, which represents a decrease in steam generation, is low.

[0079] Optionally, the optimization execution module 330 includes: a position initialization submodule, used to initialize the position of each particle in the particle swarm near the initial tuning reference, using the proportional coefficient and the integration time as decision variables and minimizing the deviation integral value as the objective function; wherein the deviation integral value is obtained by calculating the integral absolute error of the steam drum liquid level response curve recorded by the step disturbance test; a position adjustment submodule, used to iteratively update the position of each particle through the particle swarm optimization algorithm, so that each particle converges to its individual optimal position and the global optimal position of the swarm; and a new combination determination submodule, used to output the proportional coefficient and integration time corresponding to the global optimal position of the swarm as the new parameter combination when the preset convergence condition is met.

[0080] Optionally, the initial tuning benchmark is determined as follows: The operating characteristics of the steam drum are obtained when the positions of each particle in the particle swarm are initialized; a parameter optimization record matching the operating characteristics is retrieved from the optimization knowledge base; the optimization knowledge base stores parameter combinations obtained from previous parameter optimization operations and their associated operating characteristics; if a matching parameter optimization record is found, the parameter combination in that record is used as the initial tuning benchmark; if no matching parameter optimization record is found, the initial tuning benchmark is determined through a constant amplitude oscillation test.

[0081] Optionally, the target parameter combination is determined as follows: a step disturbance signal is applied to the steam drum pressure setpoint, and dynamic response data of the steam drum pressure value changing with the step disturbance signal is collected; the dynamic response data is subjected to signal filtering and time series analysis to extract pressure overshoot, oscillation period, and steady-state error characteristics, and a set of characteristic parameters reflecting the dynamic characteristics of the system is constructed; the change in the opening of the regulating valve is used as input and the change in the steam drum pressure is used as output, and a first-order inertial plus pure lag model is used to fit the steam drum pressure object, and the model gain, time constant, and lag time are calculated by the least squares identification algorithm to obtain the controlled object model; the proportional coefficient and integral time are used as decision variables, the minimization of the integral value of the deviation is used as the objective function, and the controlled object model is used as the performance evaluation model in the optimization process, and the target parameter combination is obtained by searching through the particle swarm optimization algorithm.

[0082] Optionally, the device further includes: a theoretical overshoot determination module, used to determine the dynamic response characteristics of the steam drum pressure object to a step disturbance signal using the controlled object model and the current control parameters, and to calculate the theoretical overshoot based on the dynamic response characteristics; a measured overshoot determination module, used to apply a step disturbance signal to the steam drum pressure setpoint and extract the measured overshoot from the steam drum pressure response curve; and a model update module, used to update the controlled object model by resolving the model gain, time constant, and lag time using the least squares identification algorithm based on the opening change of the steam drum pressure regulating valve and the pressure change of the steam drum during the online operation of the controlled object model.

[0083] Optionally, the device further includes: a condition determination module, used to acquire the condition characteristics of the steam drum when the step disturbance test is triggered, the condition characteristics including average load and / or steam drum pressure range; and a record storage module, used to associate the parameter combination obtained by re-executing the control parameter optimization operation with the condition characteristics when the step disturbance test is triggered, and store it as a parameter optimization record in the optimization knowledge base.

[0084] The waste heat recovery steam generation boosting device provided in this application embodiment can execute the waste heat recovery steam generation boosting method provided in any embodiment of this application, and has the corresponding performance modules and beneficial effects for executing the waste heat recovery steam generation boosting method.

[0085] Example 4 According to embodiments of this application, this application also provides an electronic device, a readable storage medium, and a computer program product.

[0086] Figure 4 A schematic diagram of an electronic device 410, which can be implemented using an embodiment, is shown. The electronic device 410 includes at least one processor 411 and a memory, such as a read-only memory (ROM) 412, a random access memory (RAM) 413, etc., communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 418 into the RAM 413. The RAM 413 may also store various programs and data required for the operation of the electronic device 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0087] Multiple components in electronic device 410 are connected to I / O interface 415, including: input unit 416, such as keyboard, mouse, etc.; output unit 417, such as various types of displays, speakers, etc.; storage unit 418, such as disk, optical disk, etc.; and communication unit 419, such as network card, modem, wireless transceiver, etc. Communication unit 419 allows electronic device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0088] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 411 performs the various methods and processes described above, such as the waste heat recovery steam generation enhancement method.

[0089] In some embodiments, the waste heat recovery steam generation enhancement method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 410 via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the waste heat recovery steam generation enhancement method described above may be performed. Alternatively, in other embodiments, processor 411 may be configured to perform the waste heat recovery steam generation enhancement method by any other suitable means (e.g., by means of firmware).

[0090] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0091] Computer programs used to implement the methods of this application may be written in any combination of one or more programming languages. These computer programs may be provided to the processor of a general-purpose computer, a special-purpose computer, or other programmable waste heat recovery steam generation booster, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0092] In the context of this application, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0093] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0094] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., a waste heat recovery steam generation booster server), or middleware components (e.g., an application server), or frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0095] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0096] This application also discloses a computer program product, which includes a computer program that, when executed by a processor, implements the waste heat recovery steam generation increase method provided in any embodiment of this application. This program product and the waste heat recovery steam generation increase method disclosed in the embodiments of this application belong to the same inventive concept, and therefore will not be described in detail here.

[0097] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this application can be achieved, and this is not limited herein.

[0098] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for increasing the amount of waste heat recovery steam generated, characterized in that, The method includes: The current control parameters of the steam drum pressure control module are updated based on the target parameter combination. During the online operation of the target parameter combination, the steam generation of the steam drum is statistically analyzed using a preset sliding window to obtain the variance and mean of the gas production. The target parameter combination consists of the optimization result value of the proportional coefficient and the integral time. If the variance of gas production exceeds a preset variance threshold within the preset sliding window, or if the average increase in gas production for a consecutive preset number of windows is lower than a preset increase threshold, a step disturbance test is triggered. In response to the step disturbance test, the control parameter optimization operation is re-executed to obtain a new parameter combination, and the current control parameters are updated based on the new parameter combination.

2. The method of claim 1, wherein, The method further includes: During the online operation of the target parameter combination, the opening signal of the steam drum pressure regulating valve is monitored; If the opening signal has two consecutive extreme points in opposite directions, and the amplitude difference between the two extreme points exceeds the preset amplitude, then it is determined that the steam drum pressure regulating valve is oscillating back and forth. If the steam drum pressure regulating valve oscillates back and forth or the average steam production value indicates a decrease in steam generation, the current control parameters will be rolled back to the effective control parameters.

3. The method of claim 1, wherein, The re-execution of the control parameter optimization operation to obtain a new parameter combination includes: Using the proportional coefficient and the integration time as decision variables, and minimizing the integral value of the deviation as the objective function, the positions of each particle in the particle swarm are initialized near the initial tuning reference; wherein, the integral value of the deviation is obtained by calculating the integral absolute error of the steam drum liquid level response curve recorded by the step disturbance test. The position of each particle is iteratively updated by the particle swarm optimization algorithm, so that each particle converges to its individual optimal position and the global optimal position of the swarm. When the preset convergence condition is met, the proportional coefficient and integration time corresponding to the global optimal position of the population are output as the new parameter combination.

4. The method of claim 3, wherein, The initial tuning benchmark is determined in the following manner: The operating characteristics of the steam drum are obtained when the positions of each particle in the particle swarm are initialized; Retrieve parameter optimization records that match the operating condition characteristics from the optimization knowledge base; the optimization knowledge base stores parameter combinations obtained from previous parameter optimization operations and their associated operating condition characteristics. If a matching parameter optimization record is found, the parameter combination in the parameter optimization record is used as the initial tuning benchmark. If no matching parameter optimization record is found, the initial tuning benchmark is determined through constant amplitude oscillation test.

5. The method of claim 1, wherein, The target parameter combination is determined in the following manner: A step disturbance signal is applied to the steam drum pressure setpoint, and dynamic response data of the steam drum pressure value as a function of the step disturbance signal is collected. The dynamic response data is subjected to signal filtering and time series analysis to extract pressure overshoot, oscillation period and steady-state error characteristics, and to construct a set of characteristic parameters reflecting the dynamic characteristics of the system. The control object model is obtained by taking the change in the opening of the regulating valve as the input and the change in the pressure of the steam drum as the output, and using a first-order inertial plus pure time delay model to fit the steam drum pressure object. The model gain, time constant and time delay time are calculated by the least squares identification algorithm. Using the proportional coefficient and integral time as decision variables, minimizing the integral value of the deviation as the objective function, and using the controlled object model as the performance evaluation model in the optimization process, the combination of objective parameters is obtained by searching through the particle swarm optimization algorithm.

6. The method of claim 5, wherein, The method further includes: Using the controlled object model and the current control parameters, the dynamic response characteristics of the steam drum pressure object to a step disturbance signal are determined, and the theoretical overshoot is calculated based on the dynamic response characteristics. A step disturbance signal is applied to the steam drum pressure setpoint, and the measured overshoot is extracted from the steam drum pressure response curve. If the residual between the theoretical overshoot and the measured overshoot exceeds a preset threshold for a set number of times, then based on the change in the opening of the steam drum pressure regulating valve and the change in the pressure of the steam drum during the online operation of the controlled object model, the model gain, time constant, and lag time are re-solved using the least squares identification algorithm to update the controlled object model.

7. The method of claim 1, wherein, The method further includes: The operating characteristics of the steam drum at the time of the step disturbance test are obtained, including the average load and / or the steam drum pressure range; The parameter combination obtained by re-executing the control parameter optimization operation is associated with the operating condition characteristics when the step disturbance test is triggered, and stored as a parameter optimization record in the optimization knowledge base.

8. A waste heat recovery steam generation boosting device, characterized in that, The device includes: The data statistics module is used to update the current control parameters of the steam drum pressure control module based on the target parameter combination, and to statistically analyze the steam generation of the steam drum using a preset sliding window during the online operation of the target parameter combination to obtain the variance and mean of the gas production; wherein, the target parameter combination is composed of the optimization result value of the proportional coefficient and the integral time. The disturbance triggering module is used to trigger a step disturbance test if the variance of gas production exceeds a preset variance threshold within the preset sliding window or if the average increase in gas production for a consecutive preset number of windows is lower than a preset increase threshold. The optimization execution module is used to respond to the step disturbance test by re-executing the control parameter optimization operation to obtain a new parameter combination, and updating the current control parameters based on the new parameter combination.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the waste heat recovery steam generation method as described in any one of claims 1-7.

10. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the waste heat recovery steam generation method as described in any one of claims 1-7.

Images