Gas turbine regulation and control method and system based on distributed control system

Abstract

The invention discloses a gas turbine regulation and control method and system based on a distributed control system, and particularly relates to the field of gas turbine regulation and control. S2, performing feature engineering processing on local sensing data through the edge computing node; s3, the main controller adopts an improved model predictive control algorithm to realize controlled quantity decoupling based on a distributed control system architecture; s4, after each control period is completed, the control effect is evaluated; s5, establishing a regulation and control threshold value, judging the evaluation according to the regulation and control threshold value, and sending out a corresponding signal according to the judgment; the distributed sensor array is used for synchronously collecting multi-field coupling parameters, local data real-time processing is achieved through the edge computing nodes, the dynamic response capacity of the gas turbine under the multi-dimensional working condition is improved, and the occurrence rate of combustion instability events is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of gas engine control, and more particularly to a gas engine control method and system based on a distributed control system. Background Art

[0002] In the field of energy and power, gas turbines are core power equipment, and their operating stability and control accuracy directly affect energy conversion efficiency and system safety.

[0003] Traditional gas turbine control systems rely on a centralized control architecture, and suffer from problems such as data processing lag and difficulty in multi-variable coupling control. Especially under complex operating conditions (such as sudden load changes and fuel composition fluctuations), it is difficult to achieve coordinated optimization of gas turbine combustion efficiency, emission indicators and equipment life, resulting in energy waste and increased environmental pollution risks.

[0004] Therefore, there is an urgent need for a gas turbine control method and system based on a distributed control system, which can improve the dynamic response capability of the gas turbine under multi-dimensional working conditions through multi-node collaborative perception and distributed computing. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a gas turbine control method and system based on a distributed control system, which solves the problems raised in the above-mentioned background technology through the following scheme.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for controlling a gas turbine based on a distributed control system, comprising:

[0007] S1. synchronously collecting gas turbine operating parameters using the distributed sensor array;

[0008] S2. Performing feature engineering processing on the local perception data through the edge computing node;

[0009] S3, the main controller is based on a distributed control system architecture and adopts an improved model predictive control algorithm to achieve control variable decoupling;

[0010] S4. After each control cycle is completed, evaluate the control effect;

[0011] S5. Establish a control threshold, judge the evaluation according to the control threshold, and send a corresponding signal according to the judgment.

[0012] Preferably, the engine operating parameters include: collecting the pressure fluctuation signal p(t) through a high-frequency dynamic pressure sensor, with a sampling frequency of f = 10kHz, and calculating the root mean square value of the dynamic pressure of the combustion chamber according to the time window Δt = 1s Among them, N = f × s × Δt represents the number of sampling points in a single window, p iIndicates the pressure value of the i-th sampling point; the temperature field matrix is ​​collected using an infrared thermal imaging array with a pixel resolution of 256×256 to obtain T j The j-th pixel temperature value T j and the total energy of the temperature field T t ; Online measurement of O2 volume fraction by laser gas analyzer Calculation of excess air coefficient based on the ideal gas state equation The fuel mass flow signal f is output through the mass flow meter mass (t), the fuel flow fluctuation rate is obtained by first-order differentiation and normalization Among them, f nom represents the nominal value of fuel flow, Δt=1s represents the differential time interval; the pulse signal is collected by the magnetoelectric speed sensor, the number of pulses C per unit time Δt=1s is calculated, and converted into speed through the transmission ratio i=1 Where k represents the number of pulses per sensor revolution.

[0013] Preferably, the feature engineering process includes pressure fluctuation characteristics, temperature field uniformity index and combustion risk warning function; the pressure fluctuation characteristics: used to calculate the root mean square pressure stability index Where P represents the root mean square value of the dynamic pressure in the combustion chamber; P avg Indicates the average pressure under the current working condition, taking the average of the last 10 time windows P; f dom Indicates the main frequency of the pressure signal, obtained through FFT analysis; f ref Indicates the pressure fluctuation reference frequency under the design working condition; the temperature field uniformity index: used to calculate the temperature field entropy value Among them, T j represents the temperature value of the jth pixel of the infrared thermal imaging array; T t Represents the total energy of the temperature field; and normalizes it: define the uniformity index The combustion risk warning function is used to calculate the comprehensive risk index R=S P +(1-U T ).

[0014] Preferably, the method includes dynamic regulation of fuel flow, optimization of air guide vane angle and adaptive adjustment of ignition energy; the dynamic regulation of fuel flow: according to the load instruction L set Calculate the target fuel flow rate using the excess air coefficient φ And enforce the constraint: |f set -f c |≤v f ×Δt, where φ opt represents the optimal excess air coefficient, HV represents the fuel calorific value, η represents the combustion efficiency, fc Indicates the actual fuel flow value at the current moment, v f Indicates the response speed of the actuator, Δt indicates the control period; the air guide blade angle optimization is used to establish the blade angle θ and the uniformity index U T The mapping relationship Where θ0 represents the design operating angle, k H It represents the temperature uniformity sensitivity coefficient, which is determined by orthogonal test. represents the uniformity critical threshold, and when When increasing the blade angle to enhance turbulence; the ignition energy is adaptively adjusted: the ignition energy compensation function is designed according to the fuel flow fluctuation rate F Among them, E0 represents the reference ignition energy, F def It represents the fuel flow fluctuation threshold, and when the flow fluctuation rate exceeds the threshold by 1%, the ignition energy increases by 2%.

[0015] Preferably, the specific method of evaluation is: calculating the control amount deviation Among them, f set represents the target fuel flow rate, f a Indicates the actual measured value of fuel flow, f max Indicates the upper limit of fuel flow control, θ set Indicates the angle setting value of the air guide blade, θ a Indicates the actual measured value of the air guide blade angle, θ max Indicates the mechanical upper limit of the air guide blade angle, E set Indicates the ignition energy setting value, E a Indicates the actual output value of ignition energy, E max Indicates the upper limit of ignition energy output.

[0016] Preferably, the control threshold is marked as ∈. When Δu≤∈, a normal signal is issued, which indicates that the control quantity deviation is less than or equal to the control threshold, indicating that the engine is in good control condition; when Δu>∈, an early warning signal is issued, which indicates that the control quantity deviation is greater than the control threshold, indicating that the engine is in poor control condition.

[0017] Preferably, a gas turbine control system based on a distributed control system includes: a distributed sensor array, an edge computing node, and a main controller, specifically including:

[0018] Multi-field coupling parameter real-time perception module: using the distributed sensor array to synchronously collect gas turbine operating parameters;

[0019] Distributed working condition feature extraction module: performs feature engineering processing on local perception data through the edge computing node;

[0020] Multivariable decoupling control strategy module: The main controller is based on a distributed control system architecture and uses an improved model predictive control algorithm to achieve control variable decoupling;

[0021] Real-time evaluation module: After each control cycle is completed, the control effect is evaluated;

[0022] Human-computer interaction module: establishes a control threshold, judges the evaluation according to the control threshold, and sends a corresponding signal according to the judgment.

[0023] The technical effects and advantages of the present invention are as follows:

[0024] 1. The present invention builds a distributed perception-computation-execution network, utilizes a distributed sensor array to synchronously collect multi-field coupling parameters, and implements real-time local data processing through edge computing nodes, achieving microsecond-level synchronous acquisition and millisecond-level local computing capabilities. This solves the problems of data processing lag and multivariable coupling control difficulties in traditional gas turbine control systems in the background art, improves the dynamic response capability of gas turbines under multi-dimensional operating conditions, and reduces the incidence of combustion instability events.

[0025] 2. This invention uses an improved model predictive control algorithm to achieve multivariable decoupling control of fuel flow, air guide vane angle, and ignition energy. Combined with specific calculation formulas and control strategies, it solves the problem in prior art of achieving coordinated optimization of combustion efficiency, emission indicators, and equipment life under complex operating conditions, thereby improving combustion efficiency and reducing environmental pollution risks.

[0026] 3. The present invention completes control effect evaluation, model parameter update and actuator characteristic correction in each control cycle by setting up a closed-loop feedback and parameter self-learning mechanism, thereby solving the problems of response lag and insufficient robustness of traditional systems under complex working conditions in the background technology, and achieving the beneficial effect of improving the operating stability and adaptability of the gas turbine under complex working conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 Schematic diagram of the method structure of the present invention;

[0028] Figure 2 Schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0029] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0030] As attached Figure 1 A combustion engine control method based on a distributed control system is shown, comprising:

[0031] S1. synchronously collecting gas turbine operating parameters using the distributed sensor array;

[0032] In this embodiment, it should be specifically explained that the engine operating parameters include: collecting the pressure fluctuation signal p(t) through a high-frequency dynamic pressure sensor, the sampling frequency f = 10kHz, and calculating the root mean square value of the dynamic pressure of the combustion chamber according to the time window Δt = 1s. Among them, N = f × s × Δt represents the number of sampling points in a single window, p i Indicates the pressure value of the i-th sampling point; the temperature field matrix is ​​collected using an infrared thermal imaging array with a pixel resolution of 256×256 to obtain T j The j-th pixel temperature value T j and the total energy of the temperature field T t ; Online measurement of O2 volume fraction by laser gas analyzer Calculation of excess air coefficient based on the ideal gas state equation The fuel mass flow signal f is output through the mass flow meter mass (t), the fuel flow fluctuation rate is obtained by first-order differentiation and normalization Among them, f nom represents the nominal value of fuel flow, Δt=1s represents the differential time interval; the pulse signal is collected by the magnetoelectric speed sensor, the number of pulses C per unit time Δt=1s is calculated, and converted into speed through the transmission ratio i=1 Where k represents the number of pulses per revolution of the sensor.

[0033] S2. Performing feature engineering processing on the local perception data through the edge computing node;

[0034] In this embodiment, it should be specifically explained that: the feature engineering process includes pressure fluctuation characteristics, temperature field uniformity index and combustion risk warning function; the pressure fluctuation characteristics: used to calculate the root mean square pressure stability index Where P represents the root mean square value of the dynamic pressure in the combustion chamber; P avg Indicates the average pressure under the current working condition, taking the average of the last 10 time windows P; f dom Indicates the main frequency of the pressure signal, obtained through FFT analysis; f ref Indicates the pressure fluctuation reference frequency under the design working condition; the temperature field uniformity index: used to calculate the temperature field entropy value Among them, T j represents the temperature value of the jth pixel of the infrared thermal imaging array; Tt Represents the total energy of the temperature field; and normalizes it: define the uniformity index The combustion risk warning function is used to calculate the comprehensive risk index R=S P +(1-U T ).

[0035] S3, the main controller is based on a distributed control system architecture and adopts an improved model predictive control algorithm to achieve control variable decoupling;

[0036] In this embodiment, it should be specifically explained that: the fuel flow rate is dynamically adjusted, the air guide blade angle is optimized, and the ignition energy is adaptively adjusted; the fuel flow rate is dynamically adjusted: according to the load instruction L set Calculate the target fuel flow rate using the excess air coefficient φ And enforce the constraint: |f set -f c |≤v f ×Δt, where φ opt represents the optimal excess air coefficient, HV represents the fuel calorific value, η represents the combustion efficiency, f c Indicates the actual fuel flow value at the current moment, v f Indicates the response speed of the actuator, Δt indicates the control period; the air guide blade angle optimization is used to establish the blade angle θ and the uniformity index U T The mapping relationship θ=θ0+k H ×ln(1+U T )×sign(U T -U T0 ), where θ0 represents the design operating angle, k H It represents the temperature uniformity sensitivity coefficient, which is determined by orthogonal test. represents the uniformity critical threshold, and when When increasing the blade angle to enhance turbulence; the ignition energy is adaptively adjusted: the ignition energy compensation function is designed according to the fuel flow fluctuation rate F Among them, E0 represents the reference ignition energy, F def It represents the fuel flow fluctuation threshold, and when the flow fluctuation rate exceeds the threshold by 1%, the ignition energy increases by 2%.

[0037] S4. After each control cycle is completed, evaluate the control effect;

[0038] In this embodiment, it should be specifically explained that: the specific evaluation method is: calculating the control amount deviation Among them, f set represents the target fuel flow rate, f a Indicates the actual measured value of fuel flow, fmax Indicates the upper limit of fuel flow control, θ set Indicates the air guide blade angle setting value, θ a Indicates the actual measured value of the air guide blade angle, θ max Indicates the mechanical upper limit of the air guide blade angle, E set Indicates the ignition energy setting value, E a Indicates the actual output value of ignition energy, E max Indicates the upper limit of ignition energy output.

[0039] S5. Establish a control threshold, judge the evaluation according to the control threshold, and send a corresponding signal according to the judgment.

[0040] In this embodiment, it is specifically necessary to explain that: the control threshold is marked as ∈, and when Δu≤∈, a normal signal is issued, which indicates that the control amount deviation is less than or equal to the control threshold, indicating that the engine is in good condition; when Δu>∈, an early warning signal is issued, which indicates that the control amount deviation is greater than the control threshold, indicating that the engine is in poor condition.

[0041] Based on the above scheme and Figure 2 The present invention also provides a gas turbine control system based on a distributed control system, comprising:

[0042] Multi-field coupling parameter real-time perception module: using the distributed sensor array to synchronously collect gas turbine operating parameters;

[0043] Distributed working condition feature extraction module: performs feature engineering processing on local perception data through the edge computing node;

[0044] Multivariable decoupling control strategy module: The main controller is based on a distributed control system architecture and uses an improved model predictive control algorithm to achieve control variable decoupling;

[0045] Real-time evaluation module: After each control cycle is completed, the control effect is evaluated;

[0046] Human-computer interaction module: establishes a control threshold, judges the evaluation according to the control threshold, and sends a corresponding signal according to the judgment.

[0047] Secondly: The drawings of the embodiments disclosed in the present invention only involve structures related to the embodiments disclosed in the present invention. Other structures may refer to conventional designs. The same embodiment and different embodiments of the present invention may be combined with each other without conflict.

[0048] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for controlling a gas turbine based on a distributed control system, characterized in that: It includes a distributed sensor array, edge computing nodes, and a main controller, and specifically includes the following steps: S1. synchronously collecting gas turbine operating parameters using the distributed sensor array; S2. Performing feature engineering processing on the local perception data through the edge computing node; S3, the main controller is based on a distributed control system architecture and adopts an improved model predictive control algorithm to achieve control variable decoupling; S4. After each control cycle is completed, evaluate the control effect; S5. Establish a control threshold, judge the evaluation according to the control threshold, and send a corresponding signal according to the judgment.

2. The method for controlling a gas turbine based on a distributed control system according to claim 1, characterized in that: The engine operating parameters include: collecting the pressure fluctuation signal p(t) through a high-frequency dynamic pressure sensor, with a sampling frequency of f = 10kHz, and calculating the root mean square value of the dynamic pressure of the combustion chamber according to the time window Δt = 1s Among them, N = f × s × Δt represents the number of sampling points in a single window, p i Indicates the pressure value of the i-th sampling point; the temperature field matrix is ​​collected using an infrared thermal imaging array with a pixel resolution of 256×256 to obtain T j The j-th pixel temperature value T j and the total energy of the temperature field T t ; Online measurement of O2 volume fraction by laser gas analyzer Calculation of excess air coefficient based on the ideal gas state equation The fuel mass flow signal f is output through the mass flow meter mass (t), the fuel flow fluctuation rate is obtained by first-order differentiation and normalization Among them, f nom represents the nominal value of fuel flow, Δt=1s represents the differential time interval; the pulse signal is collected by the magnetoelectric speed sensor, the number of pulses C per unit time Δt=1s is calculated, and converted into speed through the transmission ratio i=1 Where k represents the number of pulses per revolution of the sensor.

3. The method for controlling a gas turbine based on a distributed control system according to claim 1, characterized in that: The feature engineering process includes pressure fluctuation characteristics, temperature field uniformity index and combustion risk warning function; the pressure fluctuation characteristics: used to calculate the root mean square pressure stability index Where P represents the root mean square value of the dynamic pressure in the combustion chamber; P avg Indicates the average pressure under the current working condition, taking the average of the last 10 time windows P; f dom Indicates the main frequency of the pressure signal, obtained through FFT analysis; f ref Indicates the pressure fluctuation reference frequency under the design working condition; the temperature field uniformity index: used to calculate the temperature field entropy value Among them, T j Represents the temperature value of the jth pixel of the infrared thermal imaging array; Tt represents the total energy of the temperature field; and normalized processing is performed: the uniformity index is defined The combustion risk warning function is used to calculate the comprehensive risk index R=S P +(1-U T ).

4. The method for controlling a gas turbine based on a distributed control system according to claim 1, characterized in that: The method includes dynamic regulation of fuel flow, optimization of air guide vane angle and adaptive adjustment of ignition energy; the dynamic regulation of fuel flow: according to the load instruction L set Calculate the target fuel flow rate using the excess air coefficient φ And enforce the constraint: |f set -f c |≤v f ×Δt, where φ opt represents the optimal excess air coefficient, HV represents the fuel calorific value, η represents the combustion efficiency, f c Indicates the actual fuel flow value at the current moment, v f Indicates the response speed of the actuator, Δt indicates the control period; the air guide blade angle optimization is used to establish the blade angle θ and the uniformity index U T The mapping relationship Where θ0 represents the design operating angle, k H It represents the temperature uniformity sensitivity coefficient, which is determined by orthogonal test. represents the uniformity critical threshold, and when When increasing the blade angle to enhance turbulence; the ignition energy is adaptively adjusted: the ignition energy compensation function is designed according to the fuel flow fluctuation rate F Among them, E0 represents the reference ignition energy, F def It represents the fuel flow fluctuation threshold, and when the flow fluctuation rate exceeds the threshold by 1%, the ignition energy increases by 2%.

5. The method for controlling a gas turbine based on a distributed control system according to claim 1, characterized in that: The specific evaluation method is: calculating the control amount deviation Among them, f set represents the target fuel flow rate, f a Indicates the actual measured value of fuel flow, f max Indicates the upper limit of fuel flow control, θ set Indicates the angle setting value of the air guide blade, θ a Indicates the actual measured value of the air guide blade angle, θ max Indicates the mechanical upper limit of the air guide blade angle, E set Indicates the ignition energy setting value, E a Indicates the actual output value of ignition energy, E max Indicates the upper limit of ignition energy output.

6. The method for controlling a gas turbine based on a distributed control system according to claim 1, characterized in that: The control threshold is marked as ∈. When Δu≤∈, a normal signal is issued, which indicates that the control amount deviation is less than or equal to the control threshold, indicating that the engine is in good condition. When Δu>∈, a warning signal is issued, which indicates that the control amount deviation is greater than the control threshold, indicating that the engine is in poor condition.

7. A gas turbine control system based on a distributed control system, used to implement the gas turbine control method based on a distributed control system as described in any one of claims 1 to 6, characterized in that: It includes a distributed sensor array, edge computing nodes, and a main controller, specifically including: Multi-field coupling parameter real-time perception module: using the distributed sensor array to synchronously collect gas turbine operating parameters; Distributed working condition feature extraction module: performs feature engineering processing on local perception data through the edge computing node; Multivariable decoupling control strategy module: The main controller is based on a distributed control system architecture and uses an improved model predictive control algorithm to achieve control variable decoupling; Real-time evaluation module: After each control cycle is completed, the control effect is evaluated; Human-computer interaction module: establishes a control threshold, judges the evaluation according to the control threshold, and sends a corresponding signal according to the judgment.

Images