Cooperative control system and method for primary frequency modulation of thermal power generating unit

Through the coordinated control of high-frequency data acquisition and multi-modal compensation decision modules, the problems of primary frequency regulation response delay and safety risks of thermal power units are solved, rapid response and reduction of equipment losses are achieved, and the stability and safety of frequency regulation are improved.

CN120613753APending Publication Date: 2025-09-09内蒙古电力(集团)有限责任公司电力调度控制分公司
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202510782051.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-12
Publication Date
2025-09-09

AI Technical Summary

Technical Problem

The existing thermal power units have problems such as delayed primary frequency regulation response and frequent operation, which leads to increased equipment losses and high safety risks.

Method used

A high-frequency data acquisition module, a multimodal compensation decision module, a parameter optimization module, and a safety constraint execution module are used. Data is collected synchronously through the FPGA chip, and the multimodal dynamic compensation model is called to perform intelligent parameter optimization and reinforcement learning. The decoupling matrix is ​​combined to eliminate multivariable coupling and achieve collaborative control.

Benefits of technology

It improves the response speed of primary frequency regulation of thermal power units, reduces equipment loss, reduces safety risks, and improves the stability of frequency regulation and equipment life.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120613753A_ABST
    Figure CN120613753A_ABST
Patent Text Reader

Abstract

The invention discloses a primary frequency modulation cooperative control system for a thermal power generating unit, and the system comprises a high-frequency data collection module which synchronously collects the frequency of a power grid, the valve position of a steam turbine and the main steam pressure through an FPGA chip, calculates the frequency change gradient, and activates a rapid frequency modulation mode when the frequency change gradient exceeds a preset range or not; the multi-modal compensation decision module is used for calling a multi-modal dynamic compensation model to predict a power gap in a future time period and distributing a compensation amount; the safety constraint execution module is used for monitoring the main steam pressure deviation and triggering the reinforcement learning agent to update the parameter library when the main steam pressure deviation exceeds the preset load change rate; and the parameter optimization module is used for carrying out reinforcement learning dynamic adjustment on state space and action space parameters, and integrating security constraint indexes in a reward function. Through collaborative design of multi-mode dynamic compensation, intelligent parameter optimization and security constraint protection, the problems of response delay, parameter mismatch and security risk of a traditional frequency modulation technology are solved, and the method has remarkable technical innovation and engineering application value.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of frequency regulation of thermal power units, and in particular relates to a primary frequency regulation coordinated control system and method for thermal power units. Background Art

[0002] With the large-scale integration of renewable energy, grid frequency fluctuations have intensified, and primary frequency regulation (PFR) of thermal power units has become a critical link in maintaining grid stability. However, existing technologies suffer from response delays and frequent operation: traditional PID control relies on fixed parameters, resulting in delayed response to rapid load changes (the initial power contribution of frequency regulation is only 40%-60% of the theoretical value), and frequent operation leads to equipment loss (verification of rotor low-cycle fatigue life loss increases by 2.3 times during frequency regulation). There are also high safety risks: rapid frequency regulation can cause main steam pressure fluctuations (±1.2MPa) and excessive metal wall temperature differences (with a probability of >50°C, 45%). Summary of the Invention

[0003] In response to the problems of delayed response and frequent actions of the existing primary frequency regulation coordinated control system of thermal power units, which lead to equipment loss and high safety risks, the present invention provides a primary frequency regulation coordinated control system and method for thermal power units.

[0004] In order to achieve the above technical objectives, the technical solutions adopted by the present invention are as follows:

[0005] A primary frequency regulation coordinated control system for a thermal power unit, comprising a high-frequency data acquisition module, a multi-modal compensation decision module, a parameter optimization module, and a safety constraint execution module;

[0006] The high-frequency data acquisition module uses an FPGA chip to synchronously collect grid frequency, turbine valve position, and main steam pressure, calculate the frequency change gradient, and activate the rapid frequency regulation mode when the frequency change gradient exceeds the preset range;

[0007] The multimodal compensation decision module uses the multimodal dynamic compensation model to predict the power gap in the future period and allocate the compensation amount;

[0008] The safety constraint execution module monitors the main steam pressure deviation and triggers the reinforcement learning agent to update the parameter library when it exceeds the preset load change rate;

[0009] The parameter optimization module dynamically adjusts the state space and action space parameters through reinforcement learning, and integrates safety constraint indicators into the reward function.

[0010] Furthermore, the calculation formula for calculating the frequency change gradient in the high-frequency data acquisition module is:

[0011]

[0012] When |Δf|>0.05Hz, the fast frequency modulation mode is activated.

[0013] Furthermore, the multimodal compensation decision module allocates the compensation amount in the following manner:

[0014] Dynamically allocate the feedforward amount to 60% on the steam side and 40% on the flue gas side;

[0015] When the load change rate is greater than 3% / min, the condensate throttling auxiliary frequency regulation is activated.

[0016] The specific calculation formula is:

[0017] Δu value =0.7ΔQ+0.2Q inst ;

[0018] Δu fuel =0.3ΔQ+0.5Q mid .

[0019] Furthermore, the main steam pressure deviation monitored by the safety constraint execution module is set to ΔP. When ΔP>0.6MPa, the load change rate is limited to ≤0.6P_n / min, triggering the reinforcement learning agent to update the parameter library.

[0020] Furthermore, the parameter optimization module calculates performance indicators every 10 seconds:

[0021] J=0.6∫|Δf|dt+0.2∫|ΔP|dt+0.2·Life loss

[0022] Among them, Δf is the frequency deviation, ΔP is the main steam pressure deviation, Life loss Damage to equipment life;

[0023] If J exceeds the threshold for three consecutive cycles, the DDPG algorithm is started to update the control parameters (taking < 3 seconds).

[0024] Furthermore, it also includes a collaborative control execution module, which is connected to the multimodal compensation decision module in communication and eliminates multivariable coupling through a decoupling matrix:

[0025]

[0026] Δu valve is the valve opening adjustment amount, Δu fuel is the fuel adjustment amount;

[0027] When the load change rate is >5% / min, the condensate throttling system is linked to release the stored energy.

[0028] A method for coordinated control of primary frequency regulation of a thermal power unit, comprising the steps of:

[0029] S1, synchronously collect the grid frequency through the FPGA chip and calculate the frequency change gradient;

[0030] S2. When the frequency change gradient exceeds the preset range, activate the fast frequency modulation mode;

[0031] S3. Call the multimodal dynamic compensation model to predict the power gap in the future period and allocate the compensation amount;

[0032] S4. Monitor the main steam pressure deviation. When it exceeds the preset load change rate, trigger the reinforcement learning agent to update the parameter library, synchronously perform reinforcement learning dynamic adjustment on the state space and action space parameters, and integrate safety constraint indicators into the reward function.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] Through the collaborative design of multi-modal dynamic compensation, intelligent parameter optimization and safety constraint protection, the response delay, parameter mismatch and safety risk problems of traditional frequency modulation technology have been overcome, and it has significant technological innovation and engineering application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is an overall structural block diagram of a primary frequency regulation coordinated control system for a thermal power unit according to an embodiment of the present invention;

[0036] Figure 2 This is an overall flow chart of a method for coordinated control of primary frequency regulation of a thermal power unit in an embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to facilitate understanding by those skilled in the art, the present invention will be further described below with reference to embodiments and drawings. The contents mentioned in the embodiments are not intended to limit the present invention.

[0038] like Figure 1 As shown, this embodiment provides a primary frequency regulation coordinated control system for thermal power units, including a high-frequency data acquisition module, a multi-modal compensation decision module, a parameter optimization module, and a safety constraint execution module;

[0039] The high-frequency data acquisition module uses an FPGA chip to synchronously collect grid frequency, turbine valve position, and main steam pressure, calculate the frequency change gradient, and activate the rapid frequency regulation mode when the frequency change gradient exceeds the preset range;

[0040] The multimodal compensation decision module uses the multimodal dynamic compensation model to predict the power gap in the future period and allocate the compensation amount;

[0041] The safety constraint execution module monitors the main steam pressure deviation and triggers the reinforcement learning agent to update the parameter library when it exceeds the preset load change rate;

[0042] The parameter optimization module dynamically adjusts the state space and action space parameters through reinforcement learning, and integrates safety constraint indicators into the reward function.

[0043] The calculation formula for calculating the frequency change gradient in the high-frequency data acquisition module is:

[0044]

[0045] When |Δf|>0.05Hz, the fast frequency modulation mode is activated.

[0046] The multimodal compensation decision module allocates compensation in the following way:

[0047] Dynamically allocate the feedforward amount to 60% on the steam side and 40% on the flue gas side;

[0048] When the load change rate is greater than 3% / min, the condensate throttling auxiliary frequency regulation is activated.

[0049] The specific calculation formula is:

[0050] Δu value =0.7ΔQ+0.2Q inst ;

[0051] Δu fuel =0.3ΔQ+0.5Q mid .

[0052] The main steam pressure deviation monitored by the safety constraint execution module is set to ΔP. When ΔP>0.6MPa, the load change rate is limited to ≤0.6P_n / min, triggering the reinforcement learning agent to update the parameter library.

[0053] The parameter optimization module calculates performance indicators every 10 seconds:

[0054] J=0.6∫|Δf|dt+0.2∫|ΔP|dt+0.2·Life loss

[0055] Among them, Δf is the frequency deviation, ΔP is the main steam pressure deviation, Life loss Damage to equipment life;

[0056] If J exceeds the threshold for three consecutive cycles, the DDPG algorithm is started to update the control parameters (taking < 3 seconds).

[0057] It also includes a collaborative control execution module, which is connected to the multi-modal compensation decision module and eliminates multi-variable coupling through a decoupling matrix:

[0058]

[0059] Δu valve is the valve opening adjustment amount, Δu fuel is the fuel adjustment amount;

[0060] When the load change rate is >5% / min, the condensate throttling system is linked to release the stored energy.

[0061] like Figure 2 As shown, a method for coordinated control of primary frequency regulation of a thermal power unit includes the following steps:

[0062] S1, synchronously collect the grid frequency through the FPGA chip and calculate the frequency change gradient;

[0063] S2. When the frequency change gradient exceeds the preset range, activate the fast frequency modulation mode;

[0064] S3. Call the multimodal dynamic compensation model to predict the power gap in the future period and allocate the compensation amount;

[0065] S4. Monitor the main steam pressure deviation. When it exceeds the preset load change rate, trigger the reinforcement learning agent to update the parameter library, synchronously perform reinforcement learning dynamic adjustment on the state space and action space parameters, and integrate safety constraint indicators into the reward function.

[0066] Compared with the prior art, the present invention has the following beneficial effects:

[0067] Through the collaborative design of multi-modal dynamic compensation, intelligent parameter optimization and safety constraint protection, the response delay, parameter mismatch and safety risk problems of traditional frequency modulation technology have been overcome, and it has significant technological innovation and engineering application value.

[0068] The above describes in detail a coordinated control system and method for primary frequency regulation of a thermal power unit provided by this application. The description of the specific embodiments is intended only to facilitate understanding of the method and core concept of this application. It should be noted that, without departing from the principles of this application, a person skilled in the art may make several improvements and modifications to this application, and such improvements and modifications also fall within the scope of protection of the claims of this application.

Claims

1. A primary frequency regulation coordinated control system for thermal power units, characterized in that: It includes high-frequency data acquisition module, multi-modal compensation decision module, parameter optimization module and safety constraint execution module; The high-frequency data acquisition module uses an FPGA chip to synchronously collect grid frequency, turbine valve position, and main steam pressure, calculate the frequency change gradient, and activate the rapid frequency regulation mode when the frequency change gradient exceeds the preset range; The multimodal compensation decision module uses the multimodal dynamic compensation model to predict the power gap in the future period and allocate the compensation amount; The safety constraint execution module monitors the main steam pressure deviation and triggers the reinforcement learning agent to update the parameter library when it exceeds the preset load change rate; The parameter optimization module dynamically adjusts the state space and action space parameters through reinforcement learning, and integrates safety constraint indicators into the reward function.

2. A thermal power unit primary frequency regulation coordinated control system according to claim 1, characterized in that: The calculation formula for calculating the frequency change gradient in the high-frequency data acquisition module is: When |Δf|>0.05Hz, the fast frequency modulation mode is activated.

3. A thermal power unit primary frequency regulation coordinated control system according to claim 2, characterized in that: The multimodal compensation decision module allocates compensation in the following way: Dynamically allocate the feedforward amount to 60% on the steam side and 40% on the flue gas side; When the load change rate is greater than 3% / min, the condensate throttling auxiliary frequency regulation is activated.

4. A thermal power unit primary frequency regulation coordinated control system according to claim 3, characterized in that: The main steam pressure deviation monitored by the safety constraint execution module is set to ΔP. When ΔP>0.6MPa, the load change rate is limited to ≤0.6P_n / min, triggering the reinforcement learning agent to update the parameter library.

5. A thermal power unit primary frequency regulation coordinated control system according to claim 4, characterized in that: The parameter optimization module calculates performance indicators every 10 seconds: J=0.6∫|Δf|dt+0.2∫|ΔP|dt+0.2·Life loss Among them, Δf is the frequency deviation, ΔP is the main steam pressure deviation, Life loss Damage to equipment life; If J exceeds the threshold for three consecutive cycles, the DDPG algorithm is started to update the control parameters.

6. A thermal power unit primary frequency regulation coordinated control system according to claim 5, characterized in that: It also includes a collaborative control execution module, which is connected to the multi-modal compensation decision module and eliminates multi-variable coupling through a decoupling matrix: Δu valve is the valve opening adjustment amount, Δu fuel is the fuel adjustment amount; When the load change rate is >5% / min, the condensate throttling system is linked to release the stored energy.

7. A method for coordinated control of primary frequency regulation of thermal power units, characterized in that: Including steps: S1, synchronously collect the grid frequency through the FPGA chip and calculate the frequency change gradient; S2. When the frequency change gradient exceeds the preset range, activate the fast frequency modulation mode; S3. Call the multimodal dynamic compensation model to predict the power gap in the future period and allocate the compensation amount; S4. Monitor the main steam pressure deviation. When it exceeds the preset load change rate, trigger the reinforcement learning agent to update the parameter library, synchronously perform reinforcement learning dynamic adjustment on the state space and action space parameters, and integrate safety constraint indicators into the reward function.

Citation Information

Cited By

  • Frequency modulation control method and system for thermal power generating unit

    CN120999681A