Coordinated optimization control method and device, electronic equipment and storage medium

Abstract

This disclosure presents a coordinated optimization control method and apparatus, electronic equipment, and storage medium. Through this application, by obtaining the predicted information of the unit's future load and main steam pressure in advance, feedforward regulation is performed on the turbine side and boiler side respectively, and control parameters are adaptively adjusted in combination with the real-time load deviation of the unit. This allows for the early matching of the response characteristics of both the turbine and boiler sides and the compensation for the response lag of combustion and heat exchange on the boiler side. Therefore, it can solve the technical problems of the traditional turbine-boiler coordinated control under deep peak shaving conditions, such as the mismatch of turbine and boiler response speeds, energy supply and demand imbalance, large fluctuations in main steam pressure, and threats to the safe operation of the unit caused by frequent and large-amplitude changes in unit load. It achieves the technical effects of improving the accuracy of turbine-boiler coordinated control, stabilizing main steam pressure, ensuring the safe and stable operation of the unit under deep peak shaving, and rapidly responding to load commands.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to a coordinated optimization control method and apparatus, electronic device and storage medium. Background Technology

[0002] Currently, large thermal power units generally employ a coordinated control system for the turbine and boiler. By adjusting the turbine control valve opening and boiler fuel supply, the unit can quickly respond to automatic power generation control commands while maintaining stable main steam pressure. Traditional coordinated control strategies are based on PID control theory, adjusting the outputs of the turbine main control and boiler main control respectively according to load and pressure deviations to ensure energy balance between the turbine and boiler.

[0003] Under deep peak shaving operation, the unit load changes frequently, with large amplitude and fast rate, resulting in a mismatch between the turbine and boiler response speeds: the turbine side adjusts and responds quickly, while the boiler side responds slowly due to the large inertia of the combustion and heat exchange processes. This leads to an imbalance between turbine and boiler energy supply and demand during rapid load changes, causing large fluctuations in main steam pressure. In severe cases, it can even cause unit overpressure and threaten operational safety. Summary of the Invention

[0004] This disclosure provides a coordinated optimization control method, apparatus, electronic device, and storage medium.

[0005] According to a first aspect of this disclosure, a coordinated optimization control method is provided, comprising:

[0006] Obtain future load forecast information and future main steam pressure forecast information for the generating unit; Based on the future load forecast information, the control commands on the turbine side are adjusted in a feedforward manner. Based on the predicted future main steam pressure, the control commands on the boiler side are adjusted in a feedforward manner. Based on the real-time deviation of the unit load, the control parameters on the turbine side and / or boiler side are adaptively adjusted. Generate and output coordinated control commands for the boiler and turbine units to control the units to complete deep peak shaving.

[0007] Optionally, obtaining the unit's future load forecast information and future main steam pressure forecast information includes: Based on historical load data, dynamic regression prediction technology is used to determine the load forecast for future times.

[0008] Optionally, the adaptive adjustment of control parameters on the turbine side and / or boiler side based on the real-time deviation of the unit load includes: When the real-time deviation is greater than or equal to a preset threshold, the turbine valve opening is accelerated through the first adjustment mode. When the real-time deviation is less than the preset threshold, the turbine valve opening is adjusted by deceleration through the second adjustment mode.

[0009] Optionally, the method further includes: Based on the real-time deviation of the unit load, a compensation amount for the main steam pressure setpoint is generated through fuzzy adjustment calculation, and the energy balance between the turbine side and the boiler side is coordinated based on the compensation amount.

[0010] Optionally, the feedforward adjustment of the control commands on the boiler side based on the future main steam pressure prediction information includes: Based on the setpoint and predicted value of the main steam pressure, the fuel supply to the boiler is adjusted in advance; wherein, the main steam pressure is determined according to the sliding pressure operation curve and its compensation amount.

[0011] Optionally, the feedforward adjustment of the control commands on the boiler side based on the predicted future main steam pressure information further includes: The parameters of the PID controller in the main control loop of the boiler are self-tuned online using a dynamic particle swarm optimization algorithm to adapt to changes in the boiler's thermal characteristics.

[0012] According to a second aspect of this disclosure, a coordinated optimization control device is provided, comprising: The acquisition unit is used to acquire future load forecast information and future main steam pressure forecast information of the unit. The first adjustment unit is used to perform feedforward adjustment of the control commands on the turbine side based on the future load forecast information; The second regulating unit is used to feedforward regulate the control commands on the boiler side based on the predicted future main steam pressure information. The third regulating unit is used to adaptively adjust the control parameters on the turbine side and / or boiler side according to the real-time deviation of the unit load. The control unit is used to generate and output coordinated control commands for the boiler and turbine to control the unit to complete deep peak shaving.

[0013] Optionally, the acquisition unit is further configured to: Based on historical load data, dynamic regression prediction technology is used to determine the load forecast for future times.

[0014] Optionally, the third adjustment unit is further configured to: When the real-time deviation is greater than or equal to a preset threshold, the turbine valve opening is accelerated through the first adjustment mode. When the real-time deviation is less than the preset threshold, the turbine valve opening is adjusted by deceleration through the second adjustment mode.

[0015] Optionally, the device further includes: The generation unit is used to generate a compensation amount for the main steam pressure setpoint based on the real-time deviation of the unit load through fuzzy adjustment calculation, and coordinate the energy balance between the turbine side and the boiler side based on the compensation amount.

[0016] Optionally, the second adjustment unit is further configured to: Based on the setpoint and predicted value of the main steam pressure, the fuel supply to the boiler is adjusted in advance; wherein, the main steam pressure is determined according to the sliding pressure operation curve and its compensation amount.

[0017] Optionally, the second adjustment unit is further configured to: The parameters of the PID controller in the main control loop of the boiler are self-tuned online using a dynamic particle swarm optimization algorithm to adapt to changes in the boiler's thermal characteristics.

[0018] According to a third aspect of this disclosure, an electronic device is provided, comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect above.

[0019] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect above.

[0020] According to a fifth aspect of this disclosure, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in the first aspect above.

[0021] The coordinated optimization control method, device, electronic equipment, and storage medium provided in this disclosure can obtain the predicted information of future unit load and main steam pressure in advance, perform feedforward regulation on the turbine side and boiler side respectively, and adaptively adjust control parameters in combination with the real-time load deviation of the unit. It can match the response characteristics of the turbine and boiler sides in advance and make up for the response lag of combustion and heat exchange on the boiler side. Therefore, it can solve the technical problems of the traditional turbine-boiler coordinated control under deep peak shaving conditions, such as the mismatch of turbine and boiler response speed, energy supply and demand imbalance, large fluctuation of main steam pressure, and threats to the safe operation of the unit caused by frequent and large amplitude and rate changes in unit load. It achieves the technical effects of improving the accuracy of turbine-boiler coordinated control, stabilizing main steam pressure, ensuring the safe and stable operation of the unit under deep peak shaving, and responding quickly to load commands.

[0022] 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

[0023] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 A flowchart illustrating a coordinated optimization control method provided in an embodiment of this disclosure; Figure 2 This is a schematic diagram of the structure of a coordination and optimization control device provided in an embodiment of the present disclosure; Figure 3 This is a schematic diagram of the structure of a coordination and optimization control device provided in an embodiment of the present disclosure; Figure 4 A schematic block diagram of an example electronic device 600 provided for embodiments of this disclosure. Detailed Implementation

[0024] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0025] The following description, with reference to the accompanying drawings, outlines a coordinated optimization control method, apparatus, electronic device, and storage medium according to embodiments of the present disclosure.

[0026] Figure 1 This is a flowchart illustrating a coordinated optimization control method provided in an embodiment of the present disclosure.

[0027] like Figure 1 As shown, the method includes the following steps: Step 101: Obtain the future load forecast information and future main steam pressure forecast information of the unit; The acquisition of future load forecast information relies on the historical operating data of the unit's current load. Through dynamic autoregressive forecasting technology, trend analysis and change extrapolation are performed on continuous historical load data to ultimately form forecast information that reflects the trend of unit load changes in subsequent periods. This information can intuitively reflect the future change pattern of unit load and provide a predictive basis for load adjustment actions on the turbine side.

[0028] Future main steam pressure forecasting information is based on historical operating data of the unit's current main steam pressure. Dynamic regression prediction technology is used to deeply mine and analyze the historical data of main steam pressure fluctuation trends, thereby obtaining forecasting information that shows the changes in main steam pressure in subsequent periods. This information clearly reflects the future fluctuation characteristics of the main steam pressure, providing a predictive reference for boiler-side main steam pressure regulation and coal feed demand output. The accurate acquisition of these two types of forecasting information allows the regulation and control on both the boiler and turbine sides to no longer rely solely on real-time operating parameters, but can instead be proactively adjusted based on future parameter change trends. This significantly improves the foresight and targeting of boiler and turbine regulation, laying a solid data foundation for the precise implementation of subsequent coordinated boiler and turbine control.

[0029] Step 102: Based on the future load forecast information, perform feedforward adjustment of the control commands on the turbine side; Feedforward regulation directly integrates future load forecast information into the current turbine-side load regulation and control system. It uses future load trends as a crucial basis for adjusting turbine-side control commands, proactively adapting various turbine-side control commands based on predicted load changes. This ensures that turbine-side regulation actions anticipate future load changes. When the unit load enters a rising or falling phase, feedforward regulation can drive turbine-side control commands to respond in advance, ensuring good speed and responsiveness of the unit load during these fluctuations, and guaranteeing that turbine-side regulation actions always match the changing rhythm of the unit's given load.

[0030] Meanwhile, relying on this feedforward regulation, the final state of load change can be predicted in advance before the unit load rises or falls, avoiding overshoot problems that occur after the load rises or falls from the regulation command level. It also allows the energy output of the turbine side to be adjusted in advance, initially achieving rhythm matching with the energy supply of the boiler side, alleviating the imbalance of turbine and boiler energy matching in traditional control, improving the overall rationality of turbine main control loop regulation, and laying a solid foundation for turbine-side regulation for overall coordinated and optimized control of the turbine and boiler.

[0031] Step 103: Based on the predicted future main steam pressure information, feedforward adjustment is performed on the control commands on the boiler side; Feedforward regulation deeply integrates future main steam pressure prediction information into the current main steam pressure regulation system on the boiler side. It uses the future fluctuation trend of main steam pressure as the key basis for adjusting various control commands on the boiler side. Based on the predicted main steam pressure change trend, it makes targeted adjustments to the control commands on the boiler side in advance, so that the regulation actions on the boiler side can meet the future changes in main steam pressure in advance.

[0032] When the unit enters a load transition period, this feedforward regulation can prompt the boiler-side control commands to respond in advance, accurately controlling the output rhythm of the coal feed demand value. This ensures that the coal feed adjustment always matches the expected changes in main steam pressure, directly guaranteeing the stability of main steam pressure during load transitions and preventing main steam pressure overshoot from the source. Simultaneously, this feedforward regulation allows the boiler-side regulation to proactively adjust based on predicted trends, rather than passively following real-time parameter changes. This significantly improves the accuracy and speed of the boiler main control loop adjustment, enabling the boiler-side energy supply rhythm to better match the turbine-side energy output changes. This further alleviates the imbalance between boiler and turbine energy matching, laying a solid foundation for the coordinated and optimized control of the entire unit on the boiler side.

[0033] Step 104: Adaptively adjust the control parameters on the turbine side and / or boiler side according to the real-time deviation of the unit load; After completing the feedforward adjustment of control commands on the turbine and boiler sides, adaptive adjustment of control parameters on the turbine and / or boiler sides is performed based on the real-time load deviation. This effectively solves the problem of fixed control parameters in traditional control modes, which cannot match the complex and variable operating conditions of the unit and are prone to causing energy mismatch between the turbine and boiler. It ensures that the control parameters on both sides are dynamically adjusted according to the real-time load deviation, improving the adaptability of control parameters to the actual operating conditions of the unit. For the adjustment of control parameters on the turbine side, fuzzy adjustment calculations are performed based on the real-time load deviation. The compensation amount of the main steam pressure setpoint is accurately obtained through calculation and integrated into the original control parameter system on the turbine side. This completes the dynamic adaptation adjustment of the turbine side control parameters, allowing the turbine side adjustment parameters to conform to the changing characteristics of the real-time load deviation, further strengthening the coordinated control relationship between the turbine and boiler, and making the turbine side adjustment actions more closely aligned with the actual load requirements of the unit.

[0034] For boiler-side control parameter adjustment, the real-time deviation of the unit load is introduced into the integral variable input of the boiler-side PID controller. This allows for targeted correction of the integral variable input, avoiding oscillations in the PID proportional and derivative controls caused by load deviation correction. Simultaneously, the boiler-side PID controller parameters can be adaptively adjusted using dynamic particle swarm optimization, taking into account the real-time load deviation. This enables timely optimization of boiler-side control parameters based on changes in load deviation and boiler thermodynamic characteristics. This type of adaptive adjustment based on real-time load deviation frees the turbine-side and boiler-side control parameters from fixed settings, achieving dynamic optimization with load changes. This significantly improves the flexibility and accuracy of overall unit control, further alleviating the imbalance in turbine-boiler energy matching and ensuring stable unit operation under various load conditions.

[0035] Step 105: Generate and output the boiler-turbine coordination control command to control the unit to complete deep peak shaving.

[0036] After completing the acquisition of future unit parameters, feedforward adjustment of control commands on the turbine and boiler sides, and adaptive adjustment of control parameters on both sides, generating and outputting coordinated control commands is the final execution step for achieving deep peak shaving of the unit. It is also the core step for integrating and implementing the results of previous adjustment operations. This step directly connects the control strategy with the actual operating actuators of the unit. The generation of coordinated control commands is not a simple superposition of single adjustment commands on the turbine and boiler sides, but a comprehensive integration of the feedforward adjusted turbine-side control commands, the adaptively adjusted and optimized turbine-side control parameters, the feedforward adjusted boiler-side control commands, and the adaptively adjusted boiler-side control parameters. It combines the dynamic load change requirements and main steam pressure stability control requirements during the deep peak shaving process of the unit to perform full-dimensional collaborative integration and optimization calculations. This ensures that the generated commands are both precisely aligned with the load adjustment rhythm on the turbine side and highly matched with the energy supply rhythm on the boiler side, achieving deep coordination of control commands on both sides and completely solving the problem of energy mismatch between the turbine and boiler in the traditional control mode from the command level.

[0037] After the optimized generation of instructions is completed, the coordinated control instructions for the turbine and boiler are directly output to the core actuators of the turbine and boiler. This directly guides key operations such as adjusting the opening of the turbine regulating valves and outputting the boiler coal feed demand value. This ensures that the adjustment actions on both sides of the turbine and boiler are precisely linked, ensuring that the unit can quickly follow the unit's AGC instructions to complete the load adjustment during the load rise and fall process of deep peak shaving. It can also effectively avoid problems such as load overshoot and main steam pressure overshoot, keeping the unit's various operating parameters within a stable range. This adapts to the complex and ever-changing operating conditions under deep peak shaving, improves the control accuracy and operating economy of the unit during the deep peak shaving process, and ultimately ensures that the unit can complete the deep peak shaving operation efficiently and smoothly.

[0038] In some embodiments, obtaining the unit's future load forecast information and future main steam pressure forecast information includes: Based on historical load data, dynamic regression prediction technology is used to determine the load forecast for future times.

[0039] When obtaining future load forecast information for the generating unit, determining the load forecast value for future moments based on historical load data using dynamic regression forecasting technology is the core method to ensure the accuracy of future load forecast information. This can effectively avoid the problem of turbine-side regulation inaccuracy caused by forecast data deviation, and make the regulation actions based on forecast information more in line with the actual load change needs of the generating unit.

[0040] Historical load data is a continuous and complete collection of load-related operating data of the unit under various past operating conditions. It covers multiple dimensions such as real-time values ​​of different load ranges of the unit, the rate of change of load rise and fall, and the numerical fluctuations during the stable operation phase of the load. This data truly and comprehensively reflects the operating rules and dynamic change characteristics of the unit load and is the basis for carrying out load forecasting. Before forecasting, it is necessary to ensure the continuity and accuracy of this type of data to lay a solid data foundation for subsequent forecasting calculations.

[0041] Dynamic regression prediction technology is a professional forecasting method that relies on data statistical analysis and trend extrapolation. It can perform in-depth pattern mining and feature analysis on the collected historical load data. By constructing a dynamic regression prediction model that fits the characteristics of unit load changes, continuous historical load data is substituted into the model for systematic calculation and trend extrapolation. This accurately fits the trend of unit load changes in future periods, thereby determining the load forecast values ​​corresponding to different future times. This forms complete and accurate future load forecast information, which can truly reflect the future change pattern of unit load and provide accurate predictive basis for feedforward regulation on the turbine side.

[0042] In some embodiments, the adaptive adjustment of control parameters on the turbine side and / or boiler side based on the real-time deviation of the unit load includes: When the real-time deviation is greater than or equal to a preset threshold, the turbine valve opening is accelerated through the first adjustment mode. When the real-time deviation is less than the preset threshold, the turbine valve opening is adjusted by deceleration through the second adjustment mode.

[0043] In the process of adaptively adjusting the turbine-side control parameters based on the real-time deviation of the unit load, the core implementation method of turbine-side adaptive adjustment is to adjust the turbine valve opening in different modes according to the comparison results of the real-time deviation and the preset threshold. This allows the adjustment rhythm of the turbine valve opening to accurately match the degree of load deviation change, solving the problem of poor load following caused by the fixed valve opening adjustment rhythm in traditional regulation, and greatly improving the accuracy of turbine-side load regulation.

[0044] The preset threshold is a pre-set quantitative judgment standard for load deviation, based on the unit's own operating characteristics and the actual operating conditions required for deep peak shaving. It serves as an important basis for classifying different regulation modes, ensuring the rationality and timeliness of regulation mode switching. When the real-time deviation of the unit load is greater than or equal to the preset threshold, the first regulation mode is immediately activated. This mode directly accelerates the adjustment of the turbine valve opening through the adapted regulation logic, rapidly changing the energy output rhythm on the turbine side. This achieves a rapid response to load deviation, effectively reducing the real-time deviation of the unit load in a short period of time, and ensuring that the unit load can quickly approach the given load even when the deviation is large.

[0045] When the real-time deviation of the unit load is less than a preset threshold, the system automatically switches to the second regulation mode. This mode uses optimized regulation logic to slow down the adjustment of the turbine valve opening, reducing the adjustment pace of the turbine valves and avoiding unit load overshoot caused by large and rapid adjustments in valve opening. This allows for fine-tuning of the turbine valve opening during periods of small deviation, achieving precise alignment with the unit's given load. The two regulation modes dynamically switch according to changes in the real-time deviation of the unit load, ensuring that the adjustment of the turbine valve opening always matches the degree of load deviation. This truly achieves dynamic adaptive adjustment of turbine-side control parameters, allowing the unit load to better follow the given load and further enhancing the coordinated control effect between the turbine and the boiler.

[0046] In some embodiments, the method further includes: Based on the real-time deviation of the unit load, a compensation amount for the main steam pressure setpoint is generated through fuzzy adjustment calculation, and the energy balance between the turbine side and the boiler side is coordinated based on the compensation amount.

[0047] The compensation amount for the main steam pressure setpoint is generated by fuzzy adjustment calculation based on the real-time deviation of the unit load. Then, the energy balance between the turbine side and the boiler side is coordinated based on the compensation amount. This is a key operation to enhance the effect of turbine-boiler coordinated control. It can make the main steam pressure setpoint fit the real-time change of the unit load. It solves the problem of turbine-boiler energy matching imbalance in traditional control from the core steam and water parameter level, and makes the energy output of the turbine side and the energy supply of the boiler side form a precise dynamic fit.

[0048] Fuzzy regulation calculation is a professional calculation method adapted to the complex and ever-changing operating conditions of the unit. This calculation fully combines the multi-dimensional characteristics of the real-time load deviation of the unit, such as the magnitude of the deviation, the rate of change of the deviation, and the development trend of the deviation. It performs fuzzy processing and systematic logical calculation on various deviation information, abandoning the limitations of the traditional fixed calculation mode. It can accurately generate the main steam pressure setpoint compensation amount that meets the adjustment requirements according to the actual operating conditions of the unit, so that the magnitude of the compensation amount and the adjustment direction can accurately match the current load deviation status.

[0049] By integrating this compensation amount into the original main steam pressure setting system, dynamic correction of the main steam pressure setting can be achieved. This allows the corrected main steam pressure setting to become a common reference for regulation on both the turbine and boiler sides. The turbine side adjusts its energy output rhythm based on the corrected setting, while the boiler side uses this as a standard to regulate steam and water parameters and coal feed. This achieves linkage between the regulation actions on both sides of the turbine and boiler from the core steam and water parameter level of main steam pressure, accurately coordinating the energy balance between the turbine and boiler sides. This ensures that the energy matching on both sides of the turbine and boiler always meets the real-time load change requirements of the unit, further improving the accuracy and stability of turbine-boiler coordinated control under deep peak shaving conditions, and effectively avoiding the problem of inaccurate regulation caused by a fixed main steam pressure setting.

[0050] In some embodiments, the feedforward adjustment of the control commands on the boiler side based on the future main steam pressure prediction information includes: Based on the setpoint and predicted value of the main steam pressure, the fuel supply to the boiler is adjusted in advance; wherein, the main steam pressure is determined according to the sliding pressure operation curve and its compensation amount.

[0051] When adjusting the control commands on the boiler side based on the predicted main steam pressure, the boiler-side feedforward adjustment is carried out with the setpoint and predicted main steam pressure as the core basis. This is a specific implementation method of boiler-side feedforward adjustment. This method enables the adjustment of boiler fuel supply to have clear foresight and can accurately meet the changing needs of main steam pressure. It effectively solves the problem that traditional fuel supply adjustment lags behind changes in main steam pressure and is prone to causing main steam pressure fluctuations, allowing the boiler's energy supply rhythm to better match the control requirements of main steam pressure.

[0052] The determination of the main steam pressure is based on the sliding pressure operating curve. Under the condition that the unit adopts the sliding pressure regulation mode, the original sliding pressure operating curve is optimized and corrected according to the real-time changes of the pressure setpoint, relying on predictive technology to form a corresponding sliding pressure curve compensation amount. After the sliding pressure operating curve and this compensation amount are fused and calculated, the main steam pressure suitable for the current unit operating condition can be determined. After obtaining the accurate main steam pressure setpoint and the future main steam pressure prediction value, the two are compared and analyzed. The deviation value and the trend of deviation change are used as key references for boiler fuel supply regulation. The control command for boiler fuel supply is adjusted in advance to achieve adaptive regulation of boiler fuel supply.

[0053] This proactive adjustment allows changes in boiler fuel supply to anticipate future fluctuations in main steam pressure, precisely controlling the output rhythm of fuel supply, such as coal feed, ensuring that fuel supply adjustments always align with the control requirements of main steam pressure. From the fuel supply perspective, this guarantees that main steam pressure remains stable during unit load increases and decreases. Simultaneously, it allows the boiler's energy supply to adapt to changes in turbine energy output in advance, further enhancing the energy matching effect between the boiler and turbine sides and improving the accuracy and speed of boiler-side control command adjustments.

[0054] In some embodiments, the feedforward adjustment of the control commands on the boiler side based on the future main steam pressure prediction information further includes: The parameters of the PID controller in the main control loop of the boiler are self-tuned online using a dynamic particle swarm optimization algorithm to adapt to changes in the boiler's thermal characteristics.

[0055] In the process of feedforward adjustment of boiler-side control commands based on future main steam pressure prediction information, the online self-tuning of PID controller parameters in the boiler main control loop using dynamic particle swarm optimization algorithm is a key operation for optimizing boiler-side regulation and control performance and adapting to dynamic changes in boiler thermodynamic characteristics. As an important supplement to boiler-side feedforward adjustment, this operation can effectively solve the problem that traditional PID controller parameters are fixed and cannot be adjusted in a timely manner to keep up with changes in boiler thermodynamic characteristics, which can easily lead to a decrease in boiler regulation accuracy and oscillations in regulation actions. It provides a stable and accurate control basis for the advanced adjustment of boiler fuel supply, making the boiler-side feedforward adjustment more in line with the actual operating state of the boiler.

[0056] The dynamic particle swarm optimization algorithm is a professional optimization algorithm that relies on swarm intelligence to achieve iterative optimization of parameters. It can capture the changes in the thermodynamic characteristics of the boiler under deep peak shaving conditions in real time. Based on the real-time status of boiler steam-water exchange and heat transfer, the algorithm performs online self-tuning of various parameters of the PID controller through dynamic iterative calculations. It abandons the traditional manual tuning and fixed parameter mode and realizes real-time optimization and adjustment of controller parameters.

[0057] The boiler's thermodynamic characteristics change dynamically with fluctuations in load and operating conditions, directly affecting the response of main steam pressure regulation and fuel supply on the boiler side. The PID controller parameters, after online self-tuning via dynamic particle swarm optimization algorithm, can accurately match the boiler's real-time thermodynamic characteristics, achieving optimal control. This allows the boiler's main control loop to respond more accurately and regulate more efficiently to future main steam pressure predictions, ensuring that the advance regulation of fuel supply always matches the boiler's own operating characteristics. This not only guarantees the stability of main steam pressure during load changes but also enhances the adaptive capability and intelligence level of the boiler's main control loop. Furthermore, it strengthens the feedforward regulation effect of boiler-side control commands, better matches the energy output changes on the turbine side, and promotes energy balance between the boiler and turbine sides.

[0058] Corresponding to the above-described coordinated optimization control method, this invention also proposes a coordinated optimization control device. Since the device embodiments of this invention correspond to the above-described method embodiments, details not disclosed in the device embodiments can be referred to the above-described method embodiments, and will not be repeated here.

[0059] Figure 2 This is a schematic diagram of the structure of a coordination and optimization control device provided in an embodiment of this disclosure, as shown below. Figure 2 As shown, it includes: Acquisition unit 21 is used to acquire future load forecast information and future main steam pressure forecast information of the unit; The first adjustment unit 22 is used to perform feedforward adjustment of the control commands on the turbine side based on the future load forecast information; The second adjustment unit 23 is used to perform feedforward adjustment of the control commands on the boiler side based on the future main steam pressure prediction information. The third regulating unit 24 is used to adaptively adjust the control parameters on the turbine side and / or boiler side according to the real-time deviation of the unit load. Control unit 25 is used to generate and output coordinated control commands for the boiler and turbine to control the unit to complete deep peak shaving.

[0060] Furthermore, in one possible implementation of this disclosure, the acquisition unit 21 is further configured to: Based on historical load data, dynamic regression prediction technology is used to determine the load forecast for future times.

[0061] Furthermore, in one possible implementation of this disclosure, the third adjustment unit 24 is further configured to: When the real-time deviation is greater than or equal to a preset threshold, the turbine valve opening is accelerated through the first adjustment mode. When the real-time deviation is less than the preset threshold, the turbine valve opening is adjusted by deceleration through the second adjustment mode.

[0062] Furthermore, in one possible implementation of the embodiments of this disclosure, such as Figure 3 As shown, the device further includes: The generation unit 26 is used to generate a compensation amount for the main steam pressure setpoint based on the real-time deviation of the unit load through fuzzy adjustment calculation, and coordinate the energy balance between the turbine side and the boiler side based on the compensation amount.

[0063] Furthermore, in one possible implementation of this disclosure, the second adjustment unit 23 is further configured to: Based on the setpoint and predicted value of the main steam pressure, the fuel supply to the boiler is adjusted in advance; wherein, the main steam pressure is determined according to the sliding pressure operation curve and its compensation amount.

[0064] Furthermore, in one possible implementation of this disclosure, the second adjustment unit 23 is further configured to: The parameters of the PID controller in the main control loop of the boiler are self-tuned online using a dynamic particle swarm optimization algorithm to adapt to changes in the boiler's thermal characteristics.

[0065] It should be noted that the foregoing explanation of the method embodiments also applies to the apparatus of the embodiments of this disclosure, and the principle is the same. Therefore, the embodiments of this disclosure are not limited thereto.

[0066] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0067] Figure 4 A schematic block diagram of an example electronic device 400 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0068] like Figure 4 As shown, device 400 includes a computing unit 401, which can perform various appropriate actions and processes based on a computer program stored in ROM (Read-Only Memory) 402 or a computer program loaded from storage unit 408 into RAM (Random Access Memory) 403. RAM 403 may also store various programs and data required for the operation of device 400. The computing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. I / O (Input / Output) interface 405 is also connected to bus 404.

[0069] Multiple components in device 400 are connected to I / O interface 405, including: input unit 406, such as keyboard, mouse, etc.; output unit 407, such as various types of monitors, speakers, etc.; storage unit 408, such as disk, optical disk, etc.; and communication unit 409, such as network card, modem, wireless transceiver, etc. Communication unit 409 allows device 400 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0070] The computing unit 401 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, CPUs (Central Processing Units), GPUs (Graphics Processing Units), various special-purpose AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, DSPs (Digital Signal Processors), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as coordinated optimization control methods. For example, in some embodiments, the coordinated optimization control method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on device 400 via ROM 402 and / or communication unit 409. When the computer program is loaded into RAM 403 and executed by the computing unit 401, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the aforementioned coordinated optimization control method by any other suitable means (e.g., by means of firmware).

[0071] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application-Specific Standard Products), SOCs (System-on-Chips), CPLDs (Complex Programmable Logic Devices), 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.

[0072] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0073] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable 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. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0074] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. 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).

[0075] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users 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., communication networks). Examples of communication networks include LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, and blockchain networks.

[0076] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via 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. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0077] It's important to note that artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies primarily include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0078] 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 disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0079] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. 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 disclosure should be included within the scope of protection of this disclosure.

Claims

1. A coordinated optimization control method characterized by, include: Obtain future load forecast information and future main steam pressure forecast information for the generating unit; Based on the future load forecast information, the control commands on the turbine side are adjusted in a feedforward manner. Based on the predicted future main steam pressure, the control commands on the boiler side are adjusted in a feedforward manner. Based on the real-time deviation of the unit load, the control parameters on the turbine side and / or boiler side are adaptively adjusted. Generate and output coordinated control commands for the boiler and turbine units to control the units to complete deep peak shaving.

2. The method according to claim 1, characterized in that, The acquisition of future load forecast information and future main steam pressure forecast information of the generating unit includes: Based on historical load data, dynamic regression prediction technology is used to determine the load forecast for future times.

3. The method according to claim 1, characterized in that, The adaptive adjustment of control parameters on the turbine side and / or boiler side based on the real-time deviation of the unit load includes: When the real-time deviation is greater than or equal to a preset threshold, the turbine valve opening is accelerated through the first adjustment mode. When the real-time deviation is less than the preset threshold, the turbine valve opening is adjusted by deceleration through the second adjustment mode.

4. The method according to claim 1, characterized in that, The method further includes: Based on the real-time deviation of the unit load, a compensation amount for the main steam pressure setpoint is generated through fuzzy adjustment calculation, and the energy balance between the turbine side and the boiler side is coordinated based on the compensation amount.

5. The method according to claim 1, characterized in that, The feedforward adjustment of the control commands on the boiler side based on the predicted future main steam pressure information includes: Based on the setpoint and predicted value of the main steam pressure, the fuel supply to the boiler is adjusted in advance; wherein, the main steam pressure is determined according to the sliding pressure operation curve and its compensation amount.

6. The method according to claim 5, characterized in that, The feedforward adjustment of the control commands on the boiler side based on the predicted future main steam pressure information also includes: The parameters of the PID controller in the main control loop of the boiler are self-tuned online using a dynamic particle swarm optimization algorithm to adapt to changes in the boiler's thermal characteristics.

7. A coordinated optimization control device, characterized in that, include: The acquisition unit is used to acquire future load forecast information and future main steam pressure forecast information of the unit. The first adjustment unit is used to perform feedforward adjustment of the control commands on the turbine side based on the future load forecast information; The second regulating unit is used to feedforward regulate the control commands on the boiler side based on the predicted future main steam pressure information. The third regulating unit is used to adaptively adjust the control parameters on the turbine side and / or boiler side according to the real-time deviation of the unit load. The control unit is used to generate and output coordinated control commands for the boiler and turbine to control the unit to complete deep peak shaving.

8. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images