Gas turbine control method and system based on distributed control system

Abstract

The application discloses a gas turbine regulation and control method and system based on a decentralized control system, and particularly relates to the field of gas turbine regulation and control, and comprises the following steps: S1, synchronously collecting gas turbine operation parameters by using a distributed sensor array; S2, performing feature engineering processing on local perception data by an edge computing node; S3, based on a decentralized control system architecture, adopting an improved model predictive control algorithm to realize control quantity decoupling; S4, after completing each control cycle, evaluating the control effect; S5, establishing a regulation and control threshold, judging the evaluation according to the regulation and control threshold, and issuing a corresponding signal according to the judgment; the application synchronously collects multi-field coupling parameters by using a distributed sensor array and realizes real-time processing of local data through an edge computing node, thereby improving the dynamic response capability of the gas turbine under multi-dimensional working conditions and reducing the occurrence rate of combustion instability events.

Description

Technical Field

[0001] This invention relates to the field of gas turbine control technology, and more specifically, to a gas turbine control method and system based on a distributed control system. Background Technology

[0002] In the field of energy and power, gas turbines, as core power equipment, directly affect energy conversion efficiency and system safety through their operational stability and control precision.

[0003] Traditional gas turbine control systems rely on a centralized control architecture, which suffers from problems such as data processing lag and difficulty in controlling multiple variables. 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 lifespan, leading to increased energy waste and 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 operating conditions through multi-node collaborative sensing 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 mentioned in the background art through the following solutions.

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

[0007] S1. Synchronously collect gas turbine operating parameters using the distributed sensor array;

[0008] S2. Perform 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 uses an improved model predictive control algorithm to achieve decoupling of control quantities;

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

[0011] S5. Establish a control threshold, judge the evaluation based on the control threshold, and issue a corresponding signal based on the judgment.

[0012] Preferably, the gas turbine operating parameters include: acquiring pressure fluctuation signals p(t) via a high-frequency dynamic pressure sensor, with a sampling frequency f = 10 kHz, and sampling within a time window. Calculate the root mean square value of dynamic pressure in the combustion chamber. Where N=f Indicates the number of sampling points in a single window. This represents the pressure value at the i-th sampling point; the temperature field matrix is ​​acquired using an infrared thermal imaging array with a pixel resolution of 256. Obtain the temperature value of the j-th pixel in the infrared thermal imaging array. And the total energy of the temperature field obtained by summing the temperature values ​​of all pixels. Online measurement using a laser gas analyzer Volume fraction The excess air coefficient is calculated based on the derivation of the ideal gas law. The fuel mass flow rate signal is output through the mass flow meter. Where t represents the current sampling time, the fuel flow fluctuation rate is obtained after first-order differentiation and normalization. in, Indicates the nominal value of fuel flow rate. =1s represents the differential time interval; pulse signals are acquired by a magnetoelectric speed sensor to calculate the unit time. The number of internal pulses C is converted into rotational speed via a transmission ratio i=1. , where k represents the number of pulses per revolution of the sensor.

[0013] Preferably, the feature engineering processing includes pressure fluctuation characteristics, temperature field uniformity index, and combustion risk warning function; the pressure fluctuation characteristics are 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; This represents the average pressure under the current operating conditions, calculated as the average of the most recent 10 time windows P. The dominant frequency of the pressure signal is obtained through FFT analysis. The reference frequency for pressure fluctuation under design conditions; the temperature field uniformity index: used to calculate the temperature field entropy value. Where M represents the number of pixels in the temperature field. Let be the temperature value of the j-th pixel in the infrared thermal imaging array; Represents the total energy of the temperature field; and performs normalization: defines the temperature field homogeneity index. The combustion risk early warning function is used to calculate the comprehensive risk index. .

[0014] Preferably, the decoupling of control quantities using the improved model predictive control algorithm includes dynamic adjustment of fuel flow, optimization of air guide vane angle, and adaptive adjustment of ignition energy; the dynamic adjustment of fuel flow is based on load commands. With excess air coefficient Calculate the target fuel flow rate and enforce constraints: ,in, HV represents the optimal excess air coefficient and the fuel calorific value. Indicates combustion efficiency. This represents the actual fuel flow rate at the current moment. Indicates the response speed of the executing agency. Indicates the control cycle; the air guide vane angle optimization: used to establish the vane angle. With temperature field uniformity index mapping relationship ,in, Indicates the design working condition angle. The sensitivity coefficient for temperature uniformity is determined through orthogonal experiments. This represents the critical threshold for homogeneity, and when... > Increasing the blade angle enhances turbulence; the ignition energy is adaptively adjusted by designing an ignition energy compensation function for the fuel flow rate fluctuation rate F. ,in, Indicates the baseline ignition energy. This represents the fuel flow fluctuation threshold, and for every 1% increase in flow fluctuation rate beyond the threshold, the ignition energy increases by 2%.

[0015] Preferably, the evaluation method is as follows: calculating the control quantity deviation. ,in, Indicates the target fuel flow rate. This represents the actual measured value of fuel flow. This indicates the upper limit of fuel flow control. This indicates the air guide vane angle setting value. This indicates the actual measured value of the air guide vane angle. This indicates the upper mechanical limit of the air guide vane angle. This indicates the ignition energy setpoint. This represents the actual output value of ignition energy. This indicates the upper limit of ignition energy output.

[0016] Preferably, the control threshold is marked as ,when When the control deviation is less than or equal to the control threshold, a normal signal is issued, indicating that the gas turbine is in good condition; when When the control deviation exceeds the control threshold, a warning signal is issued, indicating that the gas turbine is in poor condition.

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

[0018] Real-time sensing module for multi-field coupling parameters: synchronously collects gas turbine operating parameters using the distributed sensor array;

[0019] Distributed operating condition feature extraction module: performs feature engineering processing on local sensing data through the edge computing nodes;

[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 decoupling of control quantities;

[0021] Real-time evaluation module: Evaluates the control effect after each control cycle is completed;

[0022] Human-computer interaction module: Establishes a control threshold, judges the evaluation based on the control threshold, and issues a corresponding signal based on the judgment.

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

[0024] 1. This invention constructs a distributed sensing-computing-execution network, utilizes a distributed sensor array to synchronously collect multi-field coupling parameters, and achieves real-time local data processing through edge computing nodes, thereby obtaining microsecond-level synchronous acquisition and millisecond-level local computing capabilities. This solves the problems of data processing lag and difficulty in multi-variable coupling control in traditional gas turbine control systems in the background technology, 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 achieves multivariate decoupled control of fuel flow rate, air guide vane angle, and ignition energy by employing an improved model predictive control algorithm. Combined with specific calculation formulas and control strategies, it solves the problem in the background technology of the difficulty in achieving coordinated optimization of gas turbine combustion efficiency, emission indicators, and equipment life under complex operating conditions, thereby improving combustion efficiency and reducing environmental pollution risks.

[0026] 3. By setting up a closed-loop feedback and parameter self-learning mechanism, this invention completes the evaluation of control effect, updating of model parameters and correction of actuator characteristics in each control cycle, which solves the problems of response lag and insufficient robustness of traditional systems under complex operating conditions in the background technology, and achieves the beneficial effect of improving the stability and adaptability of gas turbines under complex operating conditions. Attached Figure Description

[0027] Figure 1 This is a schematic diagram of the method structure of the present invention;

[0028] Figure 2 This is a schematic diagram of the system structure of the present invention. Detailed Implementation

[0029] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0030] As attached Figure 1 The gas turbine control method based on a distributed control system, as shown, includes:

[0031] S1. Synchronously collect gas turbine operating parameters using the distributed sensor array;

[0032] In this embodiment, it should be specifically noted that the gas turbine operating parameters include: acquiring pressure fluctuation signals p(t) via a high-frequency dynamic pressure sensor, with a sampling frequency f=10kHz, and according to a time window. Calculate the root mean square value of dynamic pressure in the combustion chamber. Where N=f Indicates the number of sampling points in a single window. This represents the pressure value at the i-th sampling point; the temperature field matrix is ​​acquired using an infrared thermal imaging array with a pixel resolution of 256. Obtain the temperature value of the j-th pixel in the infrared thermal imaging array. And the total energy of the temperature field obtained by summing the temperature values ​​of all pixels. Online measurement using a laser gas analyzer Volume fraction The excess air coefficient is calculated based on the derivation of the ideal gas law. The fuel mass flow rate signal is output through the mass flow meter. Where t represents the current sampling time, the fuel flow fluctuation rate is obtained after first-order differentiation and normalization. in, Indicates the nominal value of fuel flow rate. =1s represents the differential time interval; pulse signals are acquired by a magnetoelectric speed sensor to calculate the unit time. The number of internal pulses C is converted into rotational speed via a transmission ratio i=1. , where k represents the number of pulses per revolution of the sensor.

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

[0034] In this embodiment, it should be specifically noted that: the feature engineering processing includes pressure fluctuation characteristics, temperature field uniformity index, and combustion risk warning function; the pressure fluctuation characteristics are 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; This represents the average pressure under the current operating conditions, calculated as the average of the most recent 10 time windows P. The dominant frequency of the pressure signal is obtained through FFT analysis. The reference frequency for pressure fluctuation under design conditions; the temperature field uniformity index: used to calculate the temperature field entropy value. Where M represents the number of pixels in the temperature field. Let be the temperature value of the j-th pixel in the infrared thermal imaging array; Represents the total energy of the temperature field; and performs normalization: defines the temperature field homogeneity index. The combustion risk early warning function is used to calculate the comprehensive risk index. .

[0035] S3. The main controller is based on a distributed control system architecture and uses an improved model predictive control algorithm to achieve decoupling of control quantities;

[0036] In this embodiment, it should be specifically noted that: the decoupling of control quantities using the improved model predictive control algorithm includes dynamic adjustment of fuel flow, optimization of air guide vane angle, and adaptive adjustment of ignition energy; the dynamic adjustment of fuel flow is based on load commands. With excess air coefficient Calculate the target fuel flow rate and enforce constraints: ,in, HV represents the optimal excess air coefficient and the fuel calorific value. Indicates combustion efficiency. This represents the actual fuel flow rate at the current moment. Indicates the response speed of the executing agency. Indicates the control cycle; the air guide vane angle optimization: used to establish the vane angle. With temperature field uniformity index mapping relationship ,in, Indicates the design working condition angle. The sensitivity coefficient for temperature uniformity is determined through orthogonal experiments. This represents the critical threshold for homogeneity, and when... > Increasing the blade angle enhances turbulence; the ignition energy is adaptively adjusted by designing an ignition energy compensation function for the fuel flow rate fluctuation rate F. ,in, Indicates the baseline ignition energy. This represents the fuel flow fluctuation threshold, and for every 1% increase in flow fluctuation rate beyond the threshold, 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 noted that the evaluation method is as follows: calculating the control quantity deviation. ,in, Indicates the target fuel flow rate. This represents the actual measured value of fuel flow. This indicates the upper limit of fuel flow control. This indicates the air guide vane angle setting value. This indicates the actual measured value of the air guide vane angle. This indicates the upper mechanical limit of the air guide vane angle. This indicates the ignition energy setpoint. This represents the actual output value of ignition energy. This indicates the upper limit of ignition energy output.

[0039] S5. Establish a control threshold, judge the evaluation based on the control threshold, and issue a corresponding signal based on the judgment.

[0040] In this embodiment, it should be specifically noted that: the control threshold is marked as ,when When the control deviation is less than or equal to the control threshold, a normal signal is issued, indicating that the gas turbine is in good condition; when When the control deviation exceeds the control threshold, a warning signal is issued, indicating that the gas turbine is in poor condition.

[0041] Based on the above scheme and appendix 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 sensing module: synchronously collects gas turbine operating parameters using the distributed sensor array;

[0043] Distributed operating condition feature extraction module: performs feature engineering processing on local sensing data through the edge computing nodes;

[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 decoupling of control quantities;

[0045] Real-time evaluation module: Evaluates the control effect after each control cycle is completed;

[0046] Human-computer interaction module: Establishes a control threshold, judges the evaluation based on the control threshold, and issues a corresponding signal based on the judgment.

[0047] Secondly: The accompanying drawings of the embodiments disclosed in this invention only involve the structures involved in the embodiments disclosed in this invention. Other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of this invention can be combined with each other.

[0048] In conclusion, 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 within the protection scope of the present invention.

Claims

1. A method for regulating a combustion engine based on a decentralized control system, characterized in that, The method comprises a distributed sensor array, an edge computing node and a main controller, and specifically comprises the following steps: S1, synchronously collecting gas turbine operation parameters by using the distributed sensor array; S2, performing feature engineering processing on local perception data by using the edge computing node; The feature engineering process includes a pressure fluctuation feature, a temperature field uniformity index, and a combustion risk early warning function; the pressure fluctuation feature is used for calculating a root mean square pressure stability index , wherein P represents a root mean square value of a combustion chamber dynamic pressure; , wherein P represents a root mean square value of a combustion chamber dynamic pressure; , wherein P represents a root mean square value of a combustion chamber dynamic pressure; , wherein P represents a root mean square value of a combustion chamber dynamic pressure; The temperature field uniformity index is used for calculating a temperature field entropy value , wherein M represents a temperature field pixel point number, , wherein M represents a temperature field pixel point number, , wherein M represents a temperature field pixel point number, , wherein M represents a temperature field pixel point number, The combustion risk early warning function is used for calculating a comprehensive risk index , wherein M represents a temperature field pixel point number, S3, decoupling control variables by using the main controller based on a decentralized control system architecture and an improved model predictive control algorithm; The improved model predictive control algorithm for decoupling control variables includes dynamic fuel flow regulation, air guide vane angle optimization, and adaptive ignition energy adjustment. The dynamic fuel flow regulation is based on load commands. With excess air coefficient Calculate the target fuel flow rate and enforce constraints: ,in, HV represents the optimal excess air coefficient and the fuel calorific value. Indicates combustion efficiency. This represents the actual fuel flow rate at the current moment. Indicates the response speed of the executing agency. Indicates the control cycle; the air guide vane angle optimization: used to establish the vane angle. With temperature field uniformity index mapping relationship ,in Indicates the design working condition angle. The sensitivity coefficient for temperature uniformity is determined through orthogonal experiments. This represents the critical threshold for homogeneity, and when... > Increasing the blade angle enhances turbulence; the ignition energy is adaptively adjusted by designing an ignition energy compensation function for the fuel flow rate fluctuation rate F. ,in, Indicates the baseline ignition energy. This represents the fuel flow fluctuation threshold, and for every 1% increase in flow fluctuation rate beyond the threshold, the ignition energy increases by 2%. S4, evaluating control effects after each control cycle is completed; S5, establishing a control threshold, judging the evaluation according to the control threshold, and issuing a corresponding signal according to the judgment.

2. The method according to claim 1, wherein the method is characterized by: The engine operating parameters include: through the high frequency dynamic pressure sensor, collecting pressure fluctuation signal p(t), sampling frequency f=10 kHz, according to time window , calculating the dynamic pressure root mean square value of the combustion chamber , wherein N=f represents the number of single window sampling points, represents the pressure value of the i-th sampling point; using an infrared thermal imaging array to collect a temperature field matrix, with a pixel resolution of 256 , obtaining the temperature value of the j-th pixel of the infrared thermal imaging array , and the total energy of the temperature field obtained by accumulating all pixel temperature values ; through the laser gas analyzer, the volume fraction , the excess air coefficient is calculated based on the ideal gas state equation ; through the mass flow meter, the fuel mass flow signal , wherein t represents the current sampling time, and the fuel flow fluctuation rate is obtained by first-order differentiation and normalization , wherein represents the nominal value of the fuel flow, =1s represents the differential time interval; through the magneto-electric speed sensor, collecting the pulse signal, calculating the number of pulses C in a unit time , and converting it into the speed through the transmission ratio i=1 , wherein k represents the number of pulses per revolution of the sensor.​ 3. The method of claim 1, wherein the method further comprises: determining a plurality of control parameters of the gas turbine engine based on the plurality of operating parameters; and adjusting the plurality of control parameters of the gas turbine engine based on the plurality of operating parameters. The evaluation is specifically a calculation of a control quantity deviation wherein denotes a target fuel flow rate, denotes an actual measured value of the fuel flow rate, denotes an upper limit value of the fuel flow rate control, denotes an air guide vane angle set value, denotes an actual measured value of the air guide vane angle, denotes an upper limit value of the air guide vane angle mechanically, denotes an ignition energy set value, denotes an actual output value of the ignition energy, denotes an upper limit value of the ignition energy output.

4. The method according to claim 3, wherein the method further comprises: determining a target value of the parameter based on the parameter value and the parameter limit value; and adjusting the parameter of the gas turbine based on the target value. The control threshold is marked as When , a normal signal is sent, which indicates that the control quantity deviation is less than or equal to the control threshold, and the combustion engine is in good condition; when , a warning signal is sent, which indicates that the control quantity deviation is greater than the control threshold, and the combustion engine is in poor condition.

5. A distributed control system based gas turbine control system for implementing the distributed control system based gas turbine control method of any one of claims 1 to 4, characterized in that: The method comprises a distributed sensor array, an edge computing node and a main controller, and specifically comprises the following steps: A multi-field coupling parameter real-time perception module: synchronously collecting gas turbine operation parameters by using the distributed sensor array; A distributed working condition feature extraction module: performing feature engineering processing on local perception data by using the edge computing node; A multivariable decoupling control strategy module: decoupling control variables by using the main controller based on a decentralized control system architecture and an improved model predictive control algorithm; A real-time evaluation module: evaluating control effects after each control cycle is completed; A human-computer interaction module: establishing a control threshold, judging the evaluation according to the control threshold, and issuing a corresponding signal according to the judgment.

Images