Self-adaptive air-fuel ratio control method and system of micro gas turbine

Abstract

The invention provides a self-adaptive air-fuel ratio control method and system for a micro gas turbine, and the method specifically comprises the following steps: S1, collecting the fuel flow, the air flow, the combustion temperature, the oxygen content and the emission concentration in real time; s2, predicting the optimal fuel / air ratio under the current combustion condition by adopting a combustion model or a neural network; s3, calculating an error between the actual combustion result and the combustion result predicted in the step S2; s4, according to the error obtained in the step S3, a self-adaptive control algorithm is adopted to adjust supply of fuel and air; and S5, the combustion chamber conducts combustion according to the adjusted fuel and air supply, the adjusted combustion effect is monitored in real time, and the control strategy is updated according to the combustion effect. The system is high in adaptability, efficient, energy-saving, low in emission and capable of responding in real time.

Description

Technical Field

[0001] The invention belongs to the technical field of micro gas engine control, and relates to an adaptive air-fuel ratio control method and system for a micro gas turbine. Background Art

[0002] A micro gas turbine is a miniaturized gas turbine, usually with a power of no more than 1000KW, and is mainly used in distributed power generation, drones, small power units, and some specific industrial applications. A micro gas turbine control system is a set of electronic components designed specifically to control and manage the operation of a micro gas turbine. The design and function of these control systems are key to ensuring efficient, stable, and safe operation of gas turbines under various operating conditions.

[0003] The combustion control method usually adopts fixed air-fuel ratio parameters for control, which cannot adapt to different load and fuel changes, resulting in energy waste and environmental pollution. In addition, the combustion efficiency is low and the stable operation of the gas turbine under various operating conditions cannot be guaranteed. Summary of the invention

[0004] The present invention provides an adaptive air-fuel ratio control method and system for a micro gas turbine, which has strong adaptability and can automatically adjust combustion parameters according to different fuel types, environmental conditions and load changes; high efficiency and energy saving, optimizes the fuel / air ratio, improves combustion efficiency and reduces fuel consumption; low emissions: accurately controls the combustion process and reduces harmful emissions (such as NOx and CO); real-time response: quickly responds to changes in external conditions to ensure stable operation of the gas turbine under various working conditions.

[0005] The technical solution adopted by the present invention is:

[0006] An adaptive air-fuel ratio control method for a micro gas turbine, the specific steps of which are as follows:

[0007] S1, real-time collection of fuel flow, air flow, combustion temperature, oxygen content, and emission concentration;

[0008] S2, using a combustion model or neural network to predict the optimal fuel / air ratio under current combustion conditions;

[0009] S3, calculating the error between the actual combustion result and the combustion result predicted in step S2;

[0010] S4, adjusting the supply of fuel and air using an adaptive control algorithm according to the error obtained in step S3;

[0011] S5, the combustion chamber performs combustion according to the adjusted fuel and air supply, monitors the adjusted combustion effect in real time, and updates the control strategy according to the combustion effect.

[0012] Further, the adaptive control algorithm in step S4 is an adaptive PID control algorithm or an adaptive neural network control algorithm.

[0013] Furthermore, the adaptive PID control algorithm introduces an adaptive control law to automatically adjust the parameters of the PID controller during operation.

[0014] Furthermore, the neural network of the adaptive neural network control algorithm uses historical data and a combustion model library for initial training to establish the relationship between the fuel / air ratio and the combustion efficiency and emissions.

[0015] Furthermore, the neural network is composed of an input layer, a hidden layer and an output layer. The input layer is based on the actual value of the air-fuel ratio y=λ, the set value of the air-fuel ratio y sp =λ opt , the difference between the actual value of the air-fuel ratio and the set value of the air-fuel ratio e = y sp -y as input; the output layer uses the proportional, integral, and differential control parameters of the PID controller as output.

[0016] Furthermore, the neural network adjusts the weight of the neural network according to the error between the actual combustion result and the predicted result.

[0017] Furthermore, the neural network uses the square of the system output error as an error performance indicator function.

[0018] Furthermore, the neural network uses a gradient descent method to adjust the weights of each layer of the neural network.

[0019] An adaptive air-fuel ratio control system for a micro gas turbine that implements the above-mentioned adaptive air-fuel ratio control method for a micro gas turbine comprises:

[0020] Sensors to monitor key parameters, including fuel flow, air flow, combustion temperature, oxygen content, and emissions concentration;

[0021] A controller for executing an adaptive control algorithm to adjust the supply of fuel and air in real time based on sensor data;

[0022] Model library, which contains combustion models under different operating conditions of gas turbines, used to predict combustion behavior;

[0023] The data acquisition and analysis unit is used to process the sensor data and compare it with the models in the model library to determine the best control strategy.

[0024] The beneficial effects of the present invention are as follows: strong adaptability, capable of automatically adjusting combustion parameters according to different fuel types, environmental conditions and load changes; high efficiency and energy saving, optimizing the fuel / air ratio, improving combustion efficiency and reducing fuel consumption; low emissions: precise control of the combustion process and reduction of harmful emissions (such as NOx and CO); real-time response: rapid response to changes in external conditions to ensure stable operation of the gas turbine under various operating conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a schematic diagram of the principle of the adaptive PID control algorithm of the present invention.

[0026] Figure 2 It is a schematic diagram of the principle of the adaptive neural network of the present invention.

[0027] Figure 3 It is a schematic diagram of the structure of the neural network of the present invention. DETAILED DESCRIPTION

[0028] The present invention is further described below in conjunction with specific embodiments, but the present invention is not limited to these specific embodiments. Those skilled in the art should recognize that the present invention covers all possible alternatives, improvements and equivalents within the scope of the claims.

[0029] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "clockwise", "counterclockwise" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, the meaning of "multiple" is two or more, unless otherwise clearly defined.

[0030] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0031] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may include that the first and second features are in direct contact, or may include that the first and second features are not in direct contact but are in contact through another feature between them. Moreover, a first feature being "above", "above" and "above" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply indicates that the first feature is higher in level than the second feature. A first feature being "below", "below" and "below" a second feature includes that the first feature is directly below and obliquely below the second feature, or simply indicates that the first feature is lower in level than the second feature.

[0032] Technical terms:

[0033] Main components and functions of micro gas turbine:

[0034] 1. Control unit: usually includes one or more microprocessors or digital signal processors (DSPs), responsible for implementing control algorithms, data processing and decision making.

[0035] 2. Sensors: used to monitor various parameters of the gas turbine, such as temperature, pressure, speed and flow, to provide real-time data to the control unit.

[0036] 3. Actuator: According to the instructions of the control unit, the actuator adjusts the fuel supply, adjusts the valve position, etc. to control the operating status of the gas turbine.

[0037] 4. Human-Machine Interface (HMI): Allows the operator to monitor the status of the gas turbine, set parameters, and perform manual intervention when necessary.

[0038] 5. Communication interface: enables the control system to communicate with external systems (such as monitoring systems, other mechanical control systems, etc.) for data exchange and remote control.

[0039] Micro gas turbine control strategies and algorithms:

[0040] PID control: One of the most common control algorithms, used to maintain gas turbine operating parameters (such as speed, temperature, etc.) near preset target values.

[0041] Advanced control strategies: such as improved PID control algorithm, fuzzy logic control, neural network control, adaptive control, etc., used to process nonlinear systems or improve control accuracy and stability in environments with large parameter changes.

[0042] Fault diagnosis and management: Control systems also include fault detection and diagnostic capabilities, as well as the ability to take preventive action when abnormal operation or failure is detected.

[0043] Embodiment 1

[0044] See also Figure 1 The present invention provides an adaptive air-fuel ratio control method for a micro gas turbine, and the specific steps are as follows:

[0045] S1, real-time collection of fuel flow (Ff), air flow (Fa), combustion temperature (Tc), oxygen content (O2), and emission concentration (such as NOx, CO);

[0046] S2, using a combustion model or neural network to predict the optimal fuel / air ratio (λ_opt) under current combustion conditions to achieve the highest combustion efficiency and lowest emissions; by introducing an existing combustion model as a reference model to characterize the expected gas turbine combustion system performance.

[0047] S3, calculating the error e between the actual combustion result and the combustion result predicted in step S2;

[0048] S4, adjusting the supply of fuel and air using an adaptive control algorithm according to the error e obtained in step S3;

[0049] S5, the combustion chamber performs combustion according to the adjusted fuel and air supply, monitors the adjusted combustion effect in real time, and updates the control strategy according to the combustion effect.

[0050] The adaptive control algorithm in step S4 of this embodiment is an adaptive PID control algorithm or an adaptive neural network control algorithm. The core of the controller based on the combination of PID control and model reference adaptive control is to introduce adaptive control law on the basis of traditional PID control method, and use adaptive mechanism to automatically adjust the parameters of PID controller during operation. It can enable the gas turbine system to maintain the expected performance of the closed-loop system in the presence of uncertain dynamics and complex multiple operating conditions, improve the system's robustness and anti-interference ability, and achieve the highest combustion efficiency and lowest emissions of the gas turbine under complex multiple operating conditions.

[0051] The adaptive control law in step S4 of this embodiment establishes an error performance index function between the system output and the reference model output The formula is as follows:

[0052]

[0053] Among them, the adjustable parameters of the PID controller are The collection of ε rm Represents the output y of the system and the output variable y of the reference model rm The error between

[0054] Then, the adaptive law is constructed according to the above error performance index function, and the formula is as follows:

[0055]

[0056] in, Indicates the adaptive value of the parameter of the PID controller The derivative of γ θ represents the adaptive gain coefficient, Represents ε rm about The gradient descent method is used to solve the adaptive law, so that the above error performance index function Get the minimum value, and then solve the adaptive value of the PID controller parameters Right now

[0057] The present invention has strong adaptability and can automatically adjust combustion parameters according to different fuel types, environmental conditions and load changes; it is highly efficient and energy-saving, optimizes the fuel / air ratio, improves combustion efficiency and reduces fuel consumption; low emissions: accurately controls the combustion process and reduces harmful emissions (such as NOx and CO); real-time response: quickly responds to changes in external conditions to ensure stable operation of the gas turbine under various operating conditions.

[0058] Specifically, according to the efficiency of the micro-turbine, the calorific value of the fuel (fuel type, environmental conditions) and the load, the fuel flow rate m f It can be obtained by the following algorithm:

[0059] m f =P*η(temperature, pressure) / H f

[0060] Where P is the load of the micro-turbine; η is the power generation efficiency of the micro-turbine, which is a function of environmental conditions; H f is the calorific value of the fuel.

[0061] Based on the fuel flow and fuel density calculated above, the Wobbe Index for controlling the opening of the fuel flow regulating valve can be calculated to ensure stable combustion of the system.

[0062]

[0063] Where WI is the Wobbe index, H f is the fuel calorific value, ρ f is the fuel density, ρ air is the air density.

[0064] Embodiment 2

[0065] See also Figure 2 , Figure 3 The difference between this embodiment and the first embodiment is that the adaptive control algorithm in step S4 is an adaptive neural network control algorithm; the neural network of the adaptive neural network control algorithm uses historical data and a combustion model library for initial training to establish the relationship between the fuel / air ratio and the combustion efficiency and emissions.

[0066] Specifically, in extremely lean premixed combustion or near flameout, the combustion efficiency η is:

[0067]

[0068] Where λ represents the air / fuel ratio; R co and R co2 Respectively represent the volume concentration of CO and CO2 in the exhaust gas; H f is the calorific value of fuel; H co The calorific value of the fuel is the calorific value of CO.

[0069] Under the condition of stable lean premixed full combustion, the combustion efficiency η is:

[0070]

[0071] Among them, H CO , H UHC , H H2 , H NO is the lower calorific value of the corresponding product, MJ / Nm 3 ; [CO], [UHC], [H2], [NO] are the volume concentrations in the exhaust gas, ppm; V g is the flue gas volume flow rate, m 3 / h; V f is the gas volume flow rate, m 3 / h; H f is the lower calorific value of the gas, MJ / Nm 3 .

[0072] The neural network described in this embodiment is composed of an input layer, a hidden layer and an output layer. The input layer is based on the actual value of the air-fuel ratio y=λ, the set value of the air-fuel ratio y sp =λ opt , the difference between the actual value of the air-fuel ratio and the set value of the air-fuel ratio e = ysp -y as input; the output layer uses the proportional, integral, and differential control parameters of the PID controller as output. Figure 3 This is the structure diagram of the BP neural network when the number of hidden layer neurons is set to 5.

[0073] Real-time input of sensor data to the trained neural network to predict the optimal fuel / air ratio sp =λ opt .

[0074] The neural network described in this embodiment adjusts the weight of the neural network according to the error between the actual combustion result and the predicted result, so that it can continuously learn and adapt to new working conditions.

[0075] Specifically, the neural network uses the square of the system output error as the error performance index function. The form is as follows:

[0076]

[0077] Wherein, the neural network uses the gradient descent method to adjust the weights of each layer of the neural network.

[0078] According to the output of the neural network, the fuel and air supply is adjusted to optimize the combustion process.

[0079] The present invention has strong adaptability and can automatically adjust combustion parameters according to different fuel types, environmental conditions and load changes; it is highly efficient and energy-saving, optimizes the fuel / air ratio, improves combustion efficiency and reduces fuel consumption; low emissions: accurately controls the combustion process and reduces harmful emissions (such as NOx and CO); real-time response: quickly responds to changes in external conditions to ensure stable operation of the gas turbine under various operating conditions.

[0080] Embodiment 3

[0081] This embodiment provides an adaptive air-fuel ratio control system for a micro gas turbine that implements the control method of the first embodiment or the second embodiment, including:

[0082] Sensors to monitor key parameters, including fuel flow, air flow, combustion temperature, oxygen content, and emissions concentration;

[0083] A controller for executing an adaptive control algorithm to adjust the supply of fuel and air in real time based on sensor data;

[0084] Model library, which contains combustion models under different operating conditions of gas turbines, used to predict combustion behavior;

[0085] The data acquisition and analysis unit is used to process the sensor data and compare it with the models in the model library to determine the best control strategy.

[0086] The present invention has strong adaptability and can automatically adjust combustion parameters according to different fuel types, environmental conditions and load changes; it is highly efficient and energy-saving, optimizes the fuel / air ratio, improves combustion efficiency and reduces fuel consumption; low emissions: accurately controls the combustion process and reduces harmful emissions (such as NOx and CO); real-time response: quickly responds to changes in external conditions to ensure stable operation of the gas turbine under various operating conditions.

Claims

1. An adaptive air-fuel ratio control method for a micro gas turbine, the specific steps of which are as follows: S1, real-time collection of fuel flow, air flow, combustion temperature, oxygen content, and emission concentration; S2, using a combustion model or neural network to predict the optimal fuel / air ratio under current combustion conditions; S3, calculating the error between the actual combustion result and the combustion result predicted in step S2; S4, adjusting the supply of fuel and air using an adaptive control algorithm according to the error obtained in step S3; S5, the combustion chamber performs combustion according to the adjusted fuel and air supply, monitors the adjusted combustion effect in real time, and updates the control strategy according to the combustion effect.

2. The adaptive air-fuel ratio control method of a micro gas turbine according to claim 1, characterized in that: The adaptive control algorithm in step S4 is an adaptive PID control algorithm or an adaptive neural network control algorithm.

3. The adaptive air-fuel ratio control method of a micro gas turbine according to claim 2, characterized in that: The adaptive PID control algorithm introduces an adaptive control law to automatically adjust the parameters of the PID controller during operation.

4. The adaptive air-fuel ratio control method of a micro gas turbine according to claim 2, characterized in that: The neural network of the adaptive neural network control algorithm uses historical data and a combustion model library for initial training to establish the relationship between the fuel / air ratio and the combustion efficiency and emissions.

5. The adaptive air-fuel ratio control method of a micro gas turbine according to claim 4, characterized in that: The neural network consists of an input layer, a hidden layer and an output layer. The input layer is based on the actual value of the air-fuel ratio y=λ, the set value of the air-fuel ratio y sp =λ opt , the difference between the actual value of the air-fuel ratio and the set value of the air-fuel ratio e = y sp -y as input; the output layer uses the proportional, integral, and differential control parameters of the PID controller as output.

6. The adaptive air-fuel ratio control method of a micro gas turbine according to claim 5, characterized in that: The neural network adjusts the weight of the neural network according to the error between the actual combustion result and the predicted result.

7. The adaptive air-fuel ratio control method of a micro gas turbine according to claim 6, characterized in that: The neural network uses the square of the system output error as the error performance index function.

8. The adaptive air-fuel ratio control method of a micro gas turbine according to claim 6, characterized in that: The neural network uses a gradient descent method to adjust the weights of each layer of the neural network.

9. An adaptive air-fuel ratio control system for a micro gas turbine, used to implement an adaptive air-fuel ratio control method for a micro gas turbine according to any one of claims 1 to 8, characterized in that: include: Sensors to monitor key parameters, including fuel flow, air flow, combustion temperature, oxygen content, and emissions concentration; A controller for executing an adaptive control algorithm to adjust the supply of fuel and air in real time based on sensor data; Model library, which contains combustion models under different operating conditions of gas turbines, used to predict combustion behavior; The data acquisition and analysis unit is used to process the sensor data and compare it with the models in the model library to determine the best control strategy.

Images