Gas turbine control method, device and system

Abstract

The present invention provides a gas turbine control method, device, and system. The method includes receiving measured and predicted values ​​of measured data transmitted by a control platform, inputting the measured and predicted values ​​of the measured data into a Kalman filter for optimal estimation to obtain a deviation of the measured data. Based on the deviation of the measured data, a machine learning algorithm is then used to determine a deviation of the unmeasured data. The deviation of the measured and unmeasured data is then transmitted to an online model of the gas turbine to correct the predicted values ​​of the measured and unmeasured data output by the online model. This allows Kalman filtering to be performed outside the control platform, resolving the technical difficulties associated with implementing Kalman filtering on control platforms in related technologies. Furthermore, by correcting the output of the online model based on the data deviation, the accuracy of the online model can be effectively improved, optimizing control performance.

Description

Technical Field

[0001] The present invention relates to the technical field of gas turbines, and in particular to a gas turbine control method, device and system. Background Art

[0002] In model-based control of gas turbines, Kalman filtering is often used to combine measured values ​​with the model's calculated values ​​to optimally estimate them. However, both Kalman filtering and extended Kalman filtering are designed for linear models, or they expand the nonlinear system into a Taylor series and omit second-order and higher terms to obtain an approximate linearized model. However, due to the multivariable and strongly nonlinear characteristics of gas turbines, linearization within the gas turbine inevitably introduces errors. Furthermore, due to the limitations of the control platform's configuration environment, the implementation of Kalman filtering within the control platform presents certain difficulties. Summary of the Invention

[0003] The present invention aims to solve one of the technical problems in the related art at least to a certain extent.

[0004] To this end, the first purpose of the present invention is to propose a gas turbine control method, which is applied to a computing platform to realize Kalman filtering outside the control platform, effectively avoiding the errors caused by linearization processing in the gas turbine, and at the same time solving the technical problems in related technologies that Kalman filtering is difficult to implement on the control platform.

[0005] A second object of the present invention is to provide a gas turbine control method for use in a control platform.

[0006] A third object of the present invention is to provide a gas turbine control system.

[0007] A fourth object of the present invention is to provide a gas turbine control device.

[0008] A fifth object of the present invention is to provide another gas turbine control device.

[0009] A sixth object of the present invention is to provide a non-transitory computer-readable storage medium.

[0010] A seventh object of the present invention is to provide a computer program product.

[0011] To achieve the above objectives, a first embodiment of the present invention provides a gas turbine control method, which is applied to a computing platform. The method includes:

[0012] Receive the measured values ​​and predicted values ​​of the measured data sent by the control platform;

[0013] Inputting the measured value and the predicted value of the measured data into a Kalman filter for optimal estimation to obtain a deviation of the measured data;

[0014] Determining the deviation of unmeasured data using a machine learning algorithm based on the deviation of the measured data;

[0015] The deviation of the measured data and the deviation of the unmeasured data are sent to an online model of the gas turbine to correct the predicted values ​​of the measured data and the predicted values ​​of the unmeasured data output by the online model.

[0016] Optionally, as a first possible implementation manner of the first aspect, determining the deviation of the unmeasured data by using a machine learning algorithm based on the deviation of the measured data includes:

[0017] The deviation of the measured data is used as an input of the machine learning algorithm, and the deviation of the unmeasured data is output according to a mapping relationship between the deviation of the measured data and the deviation of the unmeasured data.

[0018] Optionally, as a second possible implementation manner of the first aspect, the method further includes:

[0019] Obtaining the training deviation of measured data and the training deviation of unmeasured data;

[0020] The machine learning algorithm is trained with the training deviation of the measured data as input and the training deviation of the unmeasured data as output, so that the machine learning algorithm learns the mapping relationship between the deviation of the measured data and the deviation of the unmeasured data.

[0021] Optionally, as a third possible implementation of the first aspect, the measured data includes at least: compressor outlet pressure, compressor outlet temperature, turbine outlet temperature; the unmeasured data includes at least: compressor efficiency, turbine efficiency, combustion chamber efficiency, air flow, surge margin, and flame temperature.

[0022] The gas turbine control method according to an embodiment of the present invention receives measured and predicted values ​​of measured data from a control platform, then inputs these values ​​into a Kalman filter for optimal estimation to obtain a deviation of the measured data. Based on the deviation of the measured data, a machine learning algorithm is then used to determine the deviation of the unmeasured data. The deviation of the measured and unmeasured data is then sent to the gas turbine's online model to correct the predicted values ​​of the measured and unmeasured data output by the online model. This allows Kalman filtering to be performed outside the control platform, resolving the technical issue of difficulty in implementing Kalman filtering on control platforms in related technologies. Furthermore, by correcting the output of the online model based on the data deviation, the accuracy of the online model can be effectively improved, optimizing control performance.

[0023] To achieve the above-mentioned object, a second embodiment of the present invention provides a gas turbine control method applied to a control platform, the method comprising:

[0024] Acquiring environmental data, and inputting the environmental data into an online model to predict measured data and unmeasured data, so as to obtain predicted values ​​of the measured data and the unmeasured data;

[0025] Measuring the measured data using a measuring device to obtain a measurement value of the measured data;

[0026] sending the measured values ​​and predicted values ​​of the measured data to a computing platform;

[0027] receiving the deviation of the measured data and the deviation of the unmeasured data sent by the computing platform;

[0028] The predicted values ​​of the measured data and the predicted values ​​of the unmeasured data output by the online model are corrected according to the deviation of the measured data and the deviation of the unmeasured data.

[0029] Optionally, as a first possible implementation manner of the second aspect, inputting the environmental data into an online model to predict measured data and unmeasured data to obtain predicted values ​​of the measured data and the unmeasured data includes:

[0030] The environmental data is input into an online model so that the online model predicts the measured data and the unmeasured data based on a target formula; wherein the target formula includes an energy conservation formula and a set thermodynamic formula.

[0031] Optionally, as a second possible implementation manner of the second aspect, the method includes:

[0032] The corrected predicted values ​​of the measured data and the predicted values ​​of the unmeasured data are used as control boundaries of a control algorithm.

[0033] Optionally, as a third possible implementation of the second aspect, the environmental data includes at least: ambient temperature, ambient pressure, inlet guide vane IGV angle, fuel quantity, and rotational speed; the measured data includes at least: compressor outlet pressure, compressor outlet temperature, and turbine outlet temperature; the unmeasured data includes at least: compressor efficiency, turbine efficiency, combustion chamber efficiency, air flow, surge margin, and flame temperature.

[0034] A gas turbine control method according to an embodiment of the present invention acquires environmental data, inputs the environmental data into an online model to predict measured data and unmeasured data to obtain predicted values ​​of the measured data and unmeasured data, and uses a measuring device to measure the measured data to obtain measured values ​​of the measured data. The measured values ​​and predicted values ​​of the measured data are then sent to a computing platform. After receiving the measured data deviation and the unmeasured data deviation sent by the computing platform, the predicted values ​​of the measured data and the unmeasured data output by the online model are corrected based on the measured data deviation and the unmeasured data deviation. Thus, by receiving the measured data deviation and the unmeasured data deviation sent by the computing platform and correcting the measured data prediction and the unmeasured data prediction output by the online model based on the measured data deviation and the unmeasured data deviation, the accuracy of the online model can be effectively improved, thereby optimizing control performance.

[0035] To achieve the above-mentioned objectives, a third embodiment of the present invention provides a gas turbine control system, which includes: a control platform and a computing platform.

[0036] Wherein, the control platform includes a gas turbine, an online model and a control algorithm module, for executing the method described in the second aspect;

[0037] The computing platform includes a Kalman filter and a machine learning algorithm module, which is used to execute the method described in the first aspect.

[0038] To achieve the above-mentioned object, a fourth embodiment of the present invention provides a gas turbine control system, the device comprising:

[0039] A first receiving module is used to receive the measured values ​​and predicted values ​​of the measured data sent by the control platform;

[0040] an optimal estimation module, configured to input the measured value and the predicted value of the measured data into a Kalman filter for optimal estimation to obtain a deviation of the measured data;

[0041] a determination module, configured to determine a deviation amount of unmeasured data using a machine learning algorithm based on the deviation amount of the measured data;

[0042] The first sending module is used to send the deviation of the measured data and the deviation of the unmeasured data to the online model of the gas turbine to correct the predicted values ​​of the measured data and the predicted values ​​of the unmeasured data output by the online model.

[0043] Optionally, as a first possible implementation manner of the fourth aspect, the determining module is specifically configured to:

[0044] The deviation of the measured data is used as an input of the machine learning algorithm, and the deviation of the unmeasured data is output according to a mapping relationship between the deviation of the measured data and the deviation of the unmeasured data.

[0045] Optionally, as a second possible implementation manner of the fourth aspect, the apparatus further includes:

[0046] An acquisition module, used to acquire a training deviation of measured data and a training deviation of unmeasured data;

[0047] A training module is used to train the machine learning algorithm with the training deviation of the measured data as input and the training deviation of the unmeasured data as output, so that the machine learning algorithm learns the mapping relationship between the deviation of the measured data and the deviation of the unmeasured data.

[0048] Optionally, as a third possible implementation of the fourth aspect, the measured data includes at least: compressor outlet pressure, compressor outlet temperature, turbine outlet temperature; the unmeasured data includes at least: compressor efficiency, turbine efficiency, combustion chamber efficiency, air flow, surge margin, and flame temperature.

[0049] The gas turbine control device of an embodiment of the present invention receives measured and predicted values ​​of measured data from a control platform and then inputs these values ​​into a Kalman filter for optimal estimation to obtain a deviation of the measured data. Based on the deviation of the measured data, a machine learning algorithm is then used to determine the deviation of the unmeasured data. These deviations are then sent to the gas turbine's online model to correct the predicted values ​​of the measured and unmeasured data output by the online model. This allows Kalman filtering to be performed outside the control platform, resolving the technical issue of difficulty in implementing Kalman filtering on control platforms in related technologies. Furthermore, by correcting the output of the online model based on the data deviation, the accuracy of the online model can be effectively improved, optimizing control performance.

[0050] To achieve the above-mentioned object, a fifth embodiment of the present invention provides a gas turbine control device, the device comprising:

[0051] A first processing module is configured to obtain environmental data and input the environmental data into an online model to predict measured data and unmeasured data, so as to obtain predicted values ​​of the measured data and the unmeasured data;

[0052] a measuring module, configured to measure the measured data using a measuring device to obtain a measurement value of the measured data;

[0053] A second sending module, configured to send the measured values ​​and predicted values ​​of the measured data to a computing platform;

[0054] a second receiving module, configured to receive the deviation of the measured data and the deviation of the unmeasured data sent by the computing platform;

[0055] The correction module is used to correct the predicted value of the measured data and the predicted value of the unmeasured data output by the online model according to the deviation of the measured data and the deviation of the unmeasured data.

[0056] Optionally, as a first possible implementation manner of the fifth aspect, the first processing module is further configured to:

[0057] The environmental data is input into an online model so that the online model predicts the measured data and the unmeasured data based on a target formula; wherein the target formula includes an energy conservation formula and a set thermodynamic formula.

[0058] Optionally, as a second possible implementation manner of the fifth aspect, the apparatus includes:

[0059] The second processing module is configured to use the corrected predicted value of the measured data and the predicted value of the unmeasured data as control boundaries of a control algorithm.

[0060] Optionally, as a third possible implementation of the fifth aspect, the environmental data includes at least: ambient temperature, ambient pressure, inlet guide vane IGV angle, fuel quantity, and rotation speed; the measured data includes at least: compressor outlet pressure, compressor outlet temperature, and turbine outlet temperature; the unmeasured data includes at least: compressor efficiency, turbine efficiency, combustion chamber efficiency, air flow, surge margin, and flame temperature.

[0061] A gas turbine control device according to an embodiment of the present invention acquires environmental data, inputs the environmental data into an online model to predict measured data and unmeasured data to obtain predicted values ​​of the measured data and unmeasured data, and measures the measured data using a measuring device to obtain measured values ​​of the measured data. The device then transmits the measured and predicted values ​​of the measured data to a computing platform. After receiving the measured and unmeasured data deviations from the computing platform, the device corrects the predicted values ​​of the measured and unmeasured data output by the online model based on the measured and unmeasured data deviations. Thus, by receiving the measured and unmeasured data deviations from the computing platform and correcting the predicted values ​​of the measured and unmeasured data output by the online model based on the measured and unmeasured data deviations, the accuracy of the online model can be effectively improved, thereby optimizing control performance.

[0062] To achieve the above-mentioned object, a sixth embodiment of the present invention provides an electronic device, comprising:

[0063] at least one processor; and

[0064] a memory communicatively connected to the at least one processor; wherein,

[0065] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the gas turbine control method described in the first aspect, or execute the gas turbine control method described in the second aspect.

[0066] To achieve the above-mentioned purpose, the seventh aspect embodiment of the present invention proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the gas turbine control method described in the first aspect, or to execute the gas turbine control method described in the second aspect.

[0067] To achieve the above-mentioned purpose, an eighth embodiment of the present invention proposes a computer program product, including a computer program, which, when executed by a processor, implements the gas turbine control method described in the first aspect, or implements the gas turbine control method described in the second aspect.

[0068] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0070] Figure 1 A flow chart of a gas turbine control method provided by an embodiment of the present invention;

[0071] Figure 2 A schematic diagram of a gas turbine operating in a scenario provided by an embodiment of the present invention;

[0072] Figure 3 A schematic flow chart of another gas turbine control method provided by an embodiment of the present invention;

[0073] Figure 4 A schematic flow chart of another gas turbine control method provided by an embodiment of the present invention;

[0074] Figure 5 A schematic flow chart of another gas turbine control method provided by an embodiment of the present invention;

[0075] Figure 6 A schematic structural diagram of a gas turbine control system provided by an embodiment of the present invention;

[0076] Figure 7 A schematic structural diagram of a gas turbine control device provided by an embodiment of the present invention;

[0077] Figure 8 A schematic structural diagram of another gas turbine control method provided by an embodiment of the present invention;

[0078] Figure 9 A schematic structural diagram of another gas turbine control method provided by an embodiment of the present invention;

[0079] Figure 10 A schematic structural diagram of another gas turbine control method provided by an embodiment of the present invention; and

[0080] Figure 11 A schematic structural diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0081] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0082] In related technologies, Kalman filtering, or linearization, is inherently error-prone due to the multivariable and strongly nonlinear nature of gas turbines. Furthermore, implementation of Kalman filtering within control platforms presents challenges due to the limitations of the control platform's configuration environment.

[0083] In response to the above problems, an embodiment of the present invention provides a gas turbine control method to implement Kalman filtering outside the control platform, effectively avoiding the errors caused by linearization processing within the gas turbine, and at the same time solving the technical problem of difficulty in implementing Kalman filtering on the control platform in related technologies.

[0084] A gas turbine control method and apparatus according to embodiments of the present invention will be described below with reference to the accompanying drawings.

[0085] Figure 1 A flow chart of a gas turbine control method provided by an embodiment of the present invention.

[0086] The gas turbine control method provided in an embodiment of the present invention can be executed by a gas turbine control device. The gas turbine control device can be an electronic device or can be configured in an electronic device. The electronic device can be any stationary or mobile computing device capable of data processing, such as a mobile computing device such as a laptop computer, smartphone, or wearable device, or a stationary computing device such as a desktop computer, or a server, or other type of computing device, and the embodiments of the present invention are not limited thereto.

[0087] like Figure 1 As shown, the gas turbine control method includes the following steps:

[0088] Step 101: Receive measured values ​​and predicted values ​​of measured data sent by a control platform.

[0089] It should be noted that the gas turbine control method according to the embodiment of the present invention can be applied to a computing platform, and the computing platform is located outside the gas turbine to implement Kalman filtering outside the gas turbine.

[0090] In this embodiment, the computing platform can receive measured values ​​and predicted values ​​of measured data sent by the control platform. Measured data can be understood as data that can be measured and has been measured in the gas turbine, including but not limited to compressor outlet pressure, compressor outlet temperature, and turbine outlet temperature. Optionally, the computing platform can receive the measured values ​​and predicted values ​​of the measured data sent by the control platform via network transmission.

[0091] It is understood that the measured value and predicted value of measured data are two different values ​​obtained for the same type of data, namely, the measured data. The measured value of the measured data can be understood as the value obtained by the control platform using a measuring device to measure the measured data, and the predicted value of the measured data can be understood as the value obtained by the control platform predicting the measured data.

[0092] Step 102: Input the measured value and the predicted value of the measured data into a Kalman filter for optimal estimation to obtain the deviation of the measured data.

[0093] In this embodiment, the computing platform can input the measured values ​​and predicted values ​​of the measured data into a Kalman filter for optimal estimation, thereby obtaining the deviation of the measured data. Kalman filtering is an algorithm that uses a linear system state equation to optimally estimate the system state by inputting and outputting observation data. Because the observation data includes the effects of noise and interference in the system, optimal estimation can also be considered a filtering process.

[0094] In this embodiment, the calculation process of using Kalman filtering to perform optimal estimation on the measured value and predicted value of the measured data can be as follows:

[0095] For a gas turbine, its state equation can be Δx = A·Δx + B·Δu, and its output equation can be Δy = C·Δy + D·Δu. Where, the state variable x = [n p2 U] T , n is the speed, p2 is the compressor outlet pressure, U is the combustion chamber gas specific internal energy; input variable u=[IGV W f ] T , IGV is the IGV (inlet guide vanes) angle, W f is the gas flow rate; output variable y=[n p2 T4] T , T4 is the turbine outlet temperature.

[0096] In order to more clearly illustrate the relationship between the above variables, this embodiment provides Figure 2 A schematic diagram of the gas turbine operation under a scenario shown in FIG. Figure 2 As shown, the inlet conditions, i.e., the IGV angle and the gas flow rate, are input into the compressor to obtain the compressor outlet pressure, which is input into the combustion chamber, so that the turbine outlet temperature can be output through the turbine.

[0097] However, due to the existence of systematic errors, the above equation can be written as:

[0098] State equation: Δx = A·Δx + B·Δu + G·W, output equation: Δy = C·Δy + D·Δu + V.

[0099] Where W is the system noise and V is the measurement noise.

[0100] Assume x k is the true value of the system state at time k, is the predicted value of the system state at time k, also known as a prior state estimate. is the optimal estimate of the system state at time k, i.e., the deviation, also known as a posteriori state estimate, K is the Kalman filter system, so and It can be expressed as the following formula:

[0101]

[0102]

[0103] Assumptions is the prior state error of the system state at time k, e k is the posterior state error of the system state at time k, is the covariance between the true value and the predicted value of the system state at time k, P k is the covariance between the true value and the optimal estimate of the system state at time k, so e k 、 and P k It can be expressed as the following formula:

[0104]

[0105]

[0106]

[0107]

[0108] Therefore, update We can get:

[0109]

[0110]

[0111] Update P k We can get:

[0112]

[0113]

[0114]

[0115] Step 103: Determine the deviation of the unmeasured data using a machine learning algorithm based on the deviation of the measured data.

[0116] In this embodiment, after obtaining the deviation of the measured data, the computing platform can employ a machine learning algorithm to determine the deviation of the unmeasured data based on the deviation of the measured data. Unmeasured data can be understood as data that cannot be measured in a gas turbine, including but not limited to compressor efficiency, turbine efficiency, combustor efficiency, air flow, surge margin, and flame temperature. It is understood that unmeasured data can be used to characterize gas turbine performance. For example, surge margin is a primary indicator for measuring engine surge performance and is directly related to engine stability.

[0117] It should be noted that the machine learning algorithm used in this step is a machine learning algorithm that has been trained with a large amount of data and has learned the mapping relationship between the deviation of measured data and the deviation of unmeasured data, so that the deviation of unmeasured data can be determined based on the deviation of measured data.

[0118] Step 104 : Send the deviation of the measured data and the deviation of the unmeasured data to the online model of the gas turbine to correct the predicted values ​​of the measured data and the predicted values ​​of the unmeasured data output by the online model.

[0119] In this embodiment, after obtaining the measured and unmeasured data deviations, the computing platform can transmit these deviations to the gas turbine's online model via a network to correct the predicted values ​​of the measured and unmeasured data output by the online model. This effectively improves the accuracy of the online model and optimizes control performance.

[0120] A gas turbine control method provided in an embodiment of the present invention obtains environmental data, inputs the environmental data into an online model to predict measured data and unmeasured data to obtain predicted values ​​of the measured data and the unmeasured data, and uses a measuring device to measure the measured data to obtain measured values ​​of the measured data. The measured values ​​and predicted values ​​of the measured data are then sent to a computing platform. After receiving the measured data deviation and the unmeasured data deviation sent by the computing platform, the predicted values ​​of the measured data and the unmeasured data output by the online model are corrected based on the measured data deviation and the unmeasured data deviation. Thus, by receiving the measured data deviation and the unmeasured data deviation sent by the computing platform and correcting the measured data prediction and the unmeasured data prediction output by the online model based on the measured data deviation and the unmeasured data deviation, the accuracy of the online model can be effectively improved, thereby optimizing control performance.

[0121] From the above analysis, it can be seen that the machine learning algorithm used in the present invention is a machine learning algorithm that has been trained with a large amount of data and has learned the mapping relationship between the deviation of measured data and the deviation of unmeasured data. In order to clearly illustrate how the machine learning algorithm is trained in the present invention, this embodiment provides another gas turbine control method. Figure 3 A schematic flow chart of another gas turbine control method provided by an embodiment of the present invention.

[0122] like Figure 3 As shown, the gas turbine control method may include the following steps:

[0123] Step 301: Obtain a training deviation of measured data and a training deviation of unmeasured data.

[0124] In this embodiment, the computing platform can obtain a large amount of training deviations of measured data and training deviations of unmeasured data based on a nonlinear degradation model or experimental data to train a machine learning algorithm.

[0125] Step 302 : Using the training deviation of the measured data as input and the training deviation of the unmeasured data as output, the machine learning algorithm is trained so that the machine learning algorithm learns the mapping relationship between the deviation of the measured data and the deviation of the unmeasured data.

[0126] In this embodiment, after obtaining the training deviation of the measured data and the training deviation of the unmeasured data, the training deviation of the measured data can be used as the input of the machine learning algorithm, and the training deviation of the unmeasured data can be used as the output of the machine learning algorithm to train the machine learning algorithm so that the machine learning algorithm learns the mapping relationship between the deviation of the measured data and the deviation of the unmeasured data.

[0127] Step 303: Receive the measured values ​​and predicted values ​​of the measured data sent by the control platform.

[0128] In step 304 , the measured value and the predicted value of the measured data are input into a Kalman filter for optimal estimation to obtain the deviation of the measured data.

[0129] It should be noted that the specific implementation process of steps 303-304 can be found in the description of the previous embodiment 101-102. The principles are the same and will not be repeated here.

[0130] Step 305 : Using the deviation of the measured data as input to a machine learning algorithm, and outputting the deviation of the unmeasured data based on a mapping relationship between the deviation of the measured data and the deviation of the unmeasured data.

[0131] In this embodiment, because the machine learning algorithm has learned the mapping relationship between the deviation of the measured data and the deviation of the unmeasured data, the deviation of the unmeasured data can be determined based on the deviation of the measured data and the mapping relationship between the deviation of the measured data and the deviation of the unmeasured data. Specifically, the deviation of the measured data can be used as input to the machine learning algorithm, so that the machine learning algorithm outputs the deviation of the unmeasured data based on the learned mapping relationship between the deviation of the measured data and the deviation of the unmeasured data.

[0132] Step 306 : Send the deviation of the measured data and the deviation of the unmeasured data to the online model of the gas turbine to correct the predicted values ​​of the measured data and the predicted values ​​of the unmeasured data output by the online model.

[0133] It should be noted that the specific implementation process of this step can be found in the description of the previous embodiment 104. The principle is the same and will not be repeated here.

[0134] The gas turbine control method provided in an embodiment of the present invention obtains a training deviation of measured data and a training deviation of unmeasured data, thereby training a machine learning algorithm using the training deviation of the measured data as input and the training deviation of the unmeasured data as output, so that the machine learning algorithm learns the mapping relationship between the deviation of the measured data and the deviation of the unmeasured data. Thus, the deviation of the measured data can be used as input to the machine learning algorithm, and the deviation of the unmeasured data can be output based on the mapping relationship between the deviation of the measured data and the deviation of the unmeasured data. Thus, the machine learning algorithm can be trained so that the algorithm learns the mapping relationship between the deviation of the measured data and the deviation of the unmeasured data.

[0135] It should be noted that the above embodiment is described from the perspective of a computing platform. In order to more clearly illustrate the gas turbine control process, the embodiment of the present invention provides a possible implementation of a gas turbine control method described from the perspective of a control platform. Figure 4 It is a flow chart of another gas turbine control method provided by an embodiment of the present invention.

[0136] like Figure 4 As shown, the gas turbine control method may include the following steps:

[0137] Step 401 : Acquire environmental data, and input the environmental data into an online model to predict measured data and unmeasured data, so as to obtain predicted values ​​of the measured data and the unmeasured data.

[0138] It should be noted that the gas turbine control method according to the embodiment of the present invention can be applied to a control platform, and the control platform can control the gas turbine and the online model operation of the gas turbine based on a control algorithm.

[0139] In this embodiment, the control platform can acquire environmental data and input it into an online model to predict measured and unmeasured data, thereby obtaining predicted values ​​for the measured and unmeasured data. Environmental data can be understood as measurable data about the gas turbine's environment, including but not limited to ambient temperature, ambient pressure, IGV angle, fuel flow, and rotational speed. Ambient temperatures can include compressor outlet temperature and turbine outlet temperature, while ambient pressures can include compressor outlet pressure.

[0140] In this embodiment, measured data can be understood as data that can be measured and has been measured in a gas turbine, including but not limited to compressor outlet pressure, compressor outlet temperature, and turbine outlet temperature. Unmeasured data can be understood as data that cannot be measured in a gas turbine, including but not limited to compressor efficiency, turbine efficiency, combustor efficiency, air flow, surge margin, and flame temperature. It is understood that unmeasured data can be used to characterize gas turbine performance. For example, surge margin is a primary indicator for measuring engine surge performance and is directly related to engine stability.

[0141] It should be noted that the control platform in the embodiment of the present invention can obtain environmental data through various open, legal and compliant methods. For example, the control platform can collect environmental data in real time through measuring equipment, or it can also obtain environmental data from other devices, or it can also obtain environmental data through other open, legal and compliant methods. This is not limited in this embodiment.

[0142] In this embodiment, after obtaining environmental data, the environmental data can be input into the online model for calculation to obtain predicted values ​​for measured data and unmeasured data. It should be noted that the predicted values ​​for measured data and unmeasured data are not true values; they are merely predicted values ​​calculated by the online model based on the environmental data.

[0143] Step 402: Use a measuring device to measure the measured data to obtain a measurement value of the measured data.

[0144] In this embodiment, the control platform may use a measuring device to measure the measured data, thereby obtaining a measured value of the measured data. Alternatively, the measuring device may be a sensor configured on the gas turbine, so that the control platform can measure the measured data in real time using the measuring device configured on the gas turbine to obtain the measured value of the measured data.

[0145] Step 403: Send the measured values ​​and predicted values ​​of the measured data to the computing platform.

[0146] In this embodiment, the control platform can send the predicted values ​​of the measured data predicted by the online model and the measured values ​​of the measured data measured by the measuring device to the computing platform, so that the computing platform performs Kalman filtering on the measured values ​​and the predicted values ​​of the measured data using a Kalman filter. Optionally, the control platform can send the measured values ​​and the predicted values ​​of the measured data to the computing platform via network transmission.

[0147] Step 404: Receive the deviation of the measured data and the deviation of the unmeasured data sent by the computing platform.

[0148] In this embodiment, the control platform can receive the deviation of the measured data and the deviation of the unmeasured data sent by the computing platform, and calibrate the online model based on the deviation of the measured data and the deviation of the unmeasured data. Alternatively, the control platform can receive the deviation of the measured data and the deviation of the unmeasured data sent by the computing platform via network transmission.

[0149] Step 405 : Correcting the predicted values ​​of the measured data and the predicted values ​​of the unmeasured data output by the online model according to the deviation of the measured data and the deviation of the unmeasured data.

[0150] In this embodiment, after receiving the deviation of the measured data and the deviation of the unmeasured data sent by the computing platform, the control platform can correct the predicted value of the measured data and the predicted value of the unmeasured data output by the online model based on the deviation of the measured data and the deviation of the unmeasured data, so that the predicted value of the measured data output by the online model is consistent with the measured value of the measured data, thereby ensuring that the predicted value of the unmeasured data output by the online model has high accuracy and is consistent with the unmeasured data of the actual gas turbine.

[0151] A gas turbine control method provided in an embodiment of the present invention obtains environmental data, inputs the environmental data into an online model to predict measured data and unmeasured data to obtain predicted values ​​of the measured data and the unmeasured data, and uses a measuring device to measure the measured data to obtain measured values ​​of the measured data. The measured values ​​and predicted values ​​of the measured data are then sent to a computing platform. After receiving the measured data deviation and the unmeasured data deviation sent by the computing platform, the predicted values ​​of the measured data and the unmeasured data output by the online model are corrected based on the measured data deviation and the unmeasured data deviation. Thus, by receiving the measured data deviation and the unmeasured data deviation sent by the computing platform and correcting the measured data prediction and the unmeasured data prediction output by the online model based on the measured data deviation and the unmeasured data deviation, the accuracy of the online model can be effectively improved, thereby optimizing control performance.

[0152] In order to clearly illustrate the above embodiment, this embodiment provides another gas turbine control method. Figure 5 A schematic flow chart of another gas turbine control method provided by an embodiment of the present invention.

[0153] like Figure 5 As shown, the gas turbine control method may include the following steps:

[0154] Step 501 , obtaining environmental data, and inputting the environmental data into an online model, so that the online model predicts measured data and unmeasured data based on a target formula, to obtain predicted values ​​of the measured data and the unmeasured data.

[0155] In this embodiment, after inputting environmental data into the online model, the online model can predict the measured data and the unmeasured data based on a target formula, thereby obtaining predicted values ​​for the measured data and the unmeasured data. The target formula may include an energy conservation formula and a predetermined thermodynamic formula.

[0156] It should be noted that for other specific implementation processes of this step, please refer to the description of the previous embodiment 401. The principles are the same and will not be repeated here.

[0157] Step 502: Use a measuring device to measure the measured data to obtain a measurement value of the measured data.

[0158] Step 503: Send the measured values ​​and predicted values ​​of the measured data to the computing platform.

[0159] Step 504: Receive the deviation of the measured data and the deviation of the unmeasured data sent by the computing platform.

[0160] Step 505 : Correcting the predicted values ​​of the measured data and the predicted values ​​of the unmeasured data output by the online model according to the deviation of the measured data and the deviation of the unmeasured data.

[0161] It should be noted that the specific implementation process of steps 502-505 can refer to the description of the previous embodiment 402-405. The principles are the same and will not be repeated here.

[0162] Step 506 : Using the corrected predicted values ​​of the measured data and the predicted values ​​of the unmeasured data as control boundaries of the control algorithm.

[0163] In this embodiment, the corrected predicted values ​​of the measured data and the predicted values ​​of the unmeasured data can be used as control boundaries of a control algorithm. The control algorithm is used to issue control instructions to the gas turbine and the online model of the gas turbine to control the operation of the gas turbine and the online model of the gas turbine.

[0164] The gas turbine control method provided by an embodiment of the present invention can realize inputting environmental data into an online model so that the online model predicts measured data and unmeasured data based on a target formula, obtains predicted values ​​of the measured data and predicted values ​​of the unmeasured data, and optimizes control performance by using the corrected predicted values ​​of the measured data and the predicted values ​​of the unmeasured data as control boundaries of the control algorithm.

[0165] In order to more clearly illustrate the above embodiment, the present invention further provides a gas turbine control system.

[0166] Figure 6 A schematic structural diagram of a gas turbine control system provided by an embodiment of the present invention.

[0167] It should be noted that Figure 6 The gas turbine control system shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0168] like Figure 6 As shown, the gas turbine control system includes: a control platform and a computing platform.

[0169] The control platform includes a gas turbine 61, an online model 62 and a control algorithm module 63 for executing Figure 4 or Figure 5 The gas turbine control method;

[0170] The computing platform includes a Kalman filter 64 and a machine learning algorithm module 65 for executing Figures 1 to 3 The gas turbine control method.

[0171] Specifically, the control algorithm module 63 of the control platform can send a first control instruction to the gas turbine 61 to control the gas turbine 61 to measure measured data via sensors, thereby obtaining a measured value for the measured data. Simultaneously, the control algorithm module 63 can also send a second control instruction and environmental data to the online model 62 to control the online model to predict measured data and unmeasured data based on the environmental data, thereby obtaining a predicted value for the measured data and a predicted value for the unmeasured data. The environmental data can be obtained by the control platform through various public, legal, and compliant means. The gas turbine 61 can then send the obtained measured value for the measured data to the Kalman filter 64 of the computing platform, and the online model 62 can also send the obtained predicted value for the measured data to the Kalman filter 64 of the computing platform. The Kalman filter 64 then performs a Kalman filter based on the measured and predicted values ​​of the measured data to obtain a deviation value for the measured data. The deviation value for the measured data is then sent to the machine learning algorithm module 65, which then determines a deviation value for the unmeasured data based on the deviation value for the measured data. Furthermore, the machine learning algorithm module 65 can send the deviation values ​​of the measured data and the deviation values ​​of the unmeasured data to the online model 62 of the control platform to correct the predicted values ​​of the measured data and the predicted values ​​of the unmeasured data output by the online model 62, thereby improving the accuracy of the online model and optimizing the control performance.

[0172] It should be noted that if Figure 6As shown, the control platform can implement a closed-loop control mode, and the gas turbine 61 can also send gas turbine related data to the control algorithm module 63 so that the control algorithm module 63 can better control the gas turbine 61, and the online model can also send the corrected predicted values ​​of the measured data and the predicted values ​​of the unmeasured data to the control algorithm module 63 as the control boundaries of the control algorithm to optimize the control performance.

[0173] With the above Figures 1 to 3 Corresponding to the gas turbine control method provided in the embodiment, the present invention also provides a gas turbine control device. Figures 1 to 3 The gas turbine control method provided in the embodiment corresponds to the embodiment, so the implementation of the gas turbine control method is also applicable to the gas turbine control device provided in the embodiment of the present invention, and will not be described in detail in the embodiment of the present invention.

[0174] Figure 7 A schematic structural diagram of a gas turbine control device provided in an embodiment of the present invention.

[0175] like Figure 7 As shown, the gas turbine control device includes: a first receiving module 71 , an optimal estimation module 72 , a determination module 73 and a first sending module 74 .

[0176] A first receiving module 71 is configured to receive measured values ​​and predicted values ​​of measured data sent by the control platform;

[0177] An optimal estimation module 72 is used to input the measured value and the predicted value of the measured data into the Kalman filter for optimal estimation to obtain the deviation of the measured data;

[0178] A determination module 73 is configured to determine the deviation of the unmeasured data using a machine learning algorithm based on the deviation of the measured data;

[0179] The first sending module 74 is configured to send the deviation of the measured data and the deviation of the unmeasured data to the online model of the gas turbine to correct the predicted values ​​of the measured data and the predicted values ​​of the unmeasured data output by the online model.

[0180] Furthermore, in a possible implementation of the embodiment of the present invention, the determination module 73 is specifically configured to:

[0181] The deviation of the measured data is used as the input of the machine learning algorithm, and the deviation of the unmeasured data is output according to the mapping relationship between the deviation of the measured data and the deviation of the unmeasured data.

[0182] Furthermore, in a possible implementation of an embodiment of the present invention, the measured data includes at least: compressor outlet pressure, compressor outlet temperature, turbine outlet temperature; the unmeasured data includes at least: compressor efficiency, turbine efficiency, combustion chamber efficiency, air flow, surge margin, and flame temperature.

[0183] Based on the above embodiments, the present invention further provides a possible implementation of a gas turbine control device. Figure 8 This is a schematic structural diagram of another gas turbine control device provided by an embodiment of the present invention. Based on the previous embodiment, the gas turbine control device further includes: an acquisition module 75 and a training module 76.

[0184] An acquisition module 75 is used to acquire a training deviation of measured data and a training deviation of unmeasured data;

[0185] The training module 76 is used to train the machine learning algorithm with the training deviation of the measured data as input and the training deviation of the unmeasured data as output, so that the machine learning algorithm learns the mapping relationship between the deviation of the measured data and the deviation of the unmeasured data.

[0186] The gas turbine control device provided in an embodiment of the present invention receives measured and predicted values ​​of measured data transmitted by a control platform, and then inputs these values ​​into a Kalman filter for optimal estimation to obtain a deviation of the measured data. Based on the deviation of the measured data, a machine learning algorithm is then used to determine the deviation of the unmeasured data. The deviation of the measured and unmeasured data is then transmitted to the gas turbine's online model to correct the predicted values ​​of the measured and unmeasured data output by the online model. This allows Kalman filtering to be performed outside the control platform, resolving the technical issue of difficulty in implementing Kalman filtering on control platforms in related technologies. Furthermore, by correcting the output of the online model based on the data deviation, the accuracy of the online model can be effectively improved, optimizing control performance.

[0187] With the above Figure 3 、 Figure 4 Corresponding to the gas turbine control method provided in the embodiment, the present invention also provides a gas turbine control device. Figure 3 、 Figure 4 The gas turbine control method provided in the embodiment corresponds to the embodiment, so the implementation of the gas turbine control method is also applicable to the gas turbine control device provided in the embodiment of the present invention, and will not be described in detail in the embodiment of the present invention.

[0188] Figure 9A schematic structural diagram of another gas turbine control device provided in an embodiment of the present invention.

[0189] like Figure 9 As shown, the gas turbine control device includes: a first processing module 91 , a measuring module 92 , a second sending module 93 , a second receiving module 94 and a correction module 95 .

[0190] The first processing module 91 is used to obtain environmental data and input the environmental data into the online model to predict the measured data and the unmeasured data to obtain the predicted value of the measured data and the predicted value of the unmeasured data;

[0191] The measuring module 92 is configured to measure the measured data using a measuring device to obtain a measurement value of the measured data;

[0192] A second sending module 93 is used to send the measured values ​​and predicted values ​​of the measured data to the computing platform;

[0193] A second receiving module 94 is configured to receive the deviation of the measured data and the deviation of the unmeasured data sent by the computing platform;

[0194] The correction module 95 is used to correct the predicted values ​​of the measured data and the predicted values ​​of the unmeasured data output by the online model according to the deviation of the measured data and the deviation of the unmeasured data.

[0195] Furthermore, in a possible implementation of the embodiment of the present invention, the first processing module 91 is further configured to:

[0196] The environmental data is input into the online model so that the online model predicts the measured data and the unmeasured data based on the target formula; wherein the target formula includes the energy conservation formula and the set thermodynamic formula.

[0197] Furthermore, in a possible implementation of an embodiment of the present invention, the environmental data includes at least: ambient temperature, ambient pressure, inlet guide vane IGV angle, fuel quantity, and rotational speed; the measured data includes at least: compressor outlet pressure, compressor outlet temperature, and turbine outlet temperature; the unmeasured data includes at least: compressor efficiency, turbine efficiency, combustion chamber efficiency, air flow, surge margin, and flame temperature.

[0198] Based on the above embodiments, the present invention further provides a possible implementation of a gas turbine control device. Figure 10 This is a schematic structural diagram of another gas turbine control device provided by an embodiment of the present invention. Based on the previous embodiment, the gas turbine control device further includes: a second processing module 96.

[0199] The second processing module 96 is configured to use the corrected predicted values ​​of the measured data and the predicted values ​​of the unmeasured data as control boundaries of the control algorithm.

[0200] A gas turbine control device according to an embodiment of the present invention acquires environmental data, inputs the environmental data into an online model to predict measured data and unmeasured data to obtain predicted values ​​of the measured data and unmeasured data, and measures the measured data using a measuring device to obtain measured values ​​of the measured data. The device then transmits the measured and predicted values ​​of the measured data to a computing platform. After receiving the measured and unmeasured data deviations from the computing platform, the device corrects the predicted values ​​of the measured and unmeasured data output by the online model based on the measured and unmeasured data deviations. Thus, by receiving the measured and unmeasured data deviations from the computing platform and correcting the predicted values ​​of the measured and unmeasured data output by the online model based on the measured and unmeasured data deviations, the accuracy of the online model can be effectively improved, thereby optimizing control performance.

[0201] In order to implement the above embodiments, the present invention also proposes an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the gas turbine control method proposed in any of the above embodiments of the present invention.

[0202] Figure 11 A schematic structural diagram of an electronic device provided in an embodiment of the present invention.

[0203] It should be noted that Figure 11 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0204] like Figure 11 As shown, the electronic device may include: a housing 1101, a processor 1102, a memory 1103, a circuit board 1104 and a power supply circuit 1105, wherein the circuit board 1104 is placed inside the space enclosed by the housing 1101, and the processor 1102 and the memory 1103 are arranged on the circuit board 1104; the power supply circuit 1105 is used to supply power to various circuits or devices of the above-mentioned electronic device; the memory 1103 is used to store executable program code; the processor 1102 runs a program corresponding to the executable program code by reading the executable program code stored in the memory 1103, so as to execute the gas turbine control method proposed in any of the above-mentioned embodiments of the present invention.

[0205] For details on the specific execution process of the above steps by the processor 1102 and the steps further executed by the processor 1102 by running the executable program code, please refer to the present invention. Figure 1-5 The description of the illustrated method embodiment will not be repeated here.

[0206] In order to implement the above embodiments, the present invention further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the gas turbine control method proposed in any of the above embodiments of the present invention.

[0207] In order to implement the above embodiments, the present invention further proposes a computer program product, comprising a computer program, which, when executed by a processor, implements the gas turbine control method proposed in any of the above embodiments of the present invention.

[0208] In the description of this specification, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0209] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0210] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0211] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0212] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0213] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0214] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing module, or each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

[0215] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and are not to be construed as limiting the present invention. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A gas turbine control method, applied to a computing platform, characterized in that: The following steps are involved: Receive the measured values ​​and predicted values ​​of the measured data sent by the control platform; Inputting the measured value and the predicted value of the measured data into a Kalman filter for optimal estimation to obtain a deviation of the measured data; Determining the deviation of the unmeasured data using a machine learning algorithm based on the deviation of the measured data, including: using the deviation of the measured data as an input to the machine learning algorithm, and outputting the deviation of the unmeasured data based on a mapping relationship between the deviation of the measured data and the deviation of the unmeasured data; sending the deviation of the measured data and the deviation of the unmeasured data to an online model of the gas turbine to correct the predicted values ​​of the measured data and the predicted values ​​of the unmeasured data output by the online model; Also includes: Obtaining the training deviation of measured data and the training deviation of unmeasured data; The machine learning algorithm is trained with the training deviation of the measured data as input and the training deviation of the unmeasured data as output, so that the machine learning algorithm learns the mapping relationship between the deviation of the measured data and the deviation of the unmeasured data.

2. The method according to claim 1, characterized in that The measured data includes at least: compressor outlet pressure, compressor outlet temperature, turbine outlet temperature; the unmeasured data includes at least: compressor efficiency, turbine efficiency, combustion chamber efficiency, air flow, surge margin, and flame temperature.

3. A gas turbine control method, applied to a control platform, characterized in that: The following steps are involved: Acquiring environmental data, and inputting the environmental data into an online model to predict measured data and unmeasured data, so as to obtain predicted values ​​of the measured data and the unmeasured data; Measuring the measured data using a measuring device to obtain a measurement value of the measured data; sending the measured values ​​and predicted values ​​of the measured data to a computing platform; Receiving the deviation of the measured data and the deviation of the unmeasured data sent by the computing platform, comprising: using the deviation of the measured data as an input to a machine learning algorithm, and outputting the deviation of the unmeasured data based on a mapping relationship between the deviation of the measured data and the deviation of the unmeasured data; Correcting the predicted values ​​of the measured data and the predicted values ​​of the unmeasured data output by the online model according to the deviation of the measured data and the deviation of the unmeasured data; Also includes: Obtaining the training deviation of measured data and the training deviation of unmeasured data; The machine learning algorithm is trained with the training deviation of the measured data as input and the training deviation of the unmeasured data as output, so that the machine learning algorithm learns the mapping relationship between the deviation of the measured data and the deviation of the unmeasured data.

4. The method according to claim 3, characterized in that Inputting the environmental data into an online model to predict measured data and unmeasured data to obtain predicted values ​​of the measured data and the unmeasured data includes: The environmental data is input into an online model so that the online model predicts the measured data and the unmeasured data based on a target formula; wherein the target formula includes an energy conservation formula and a set thermodynamic formula.

5. The method according to claim 4, characterized in that The method comprises: The corrected predicted values ​​of the measured data and the predicted values ​​of the unmeasured data are used as control boundaries of a control algorithm.

6. The method according to any one of claims 3 to 5, characterized in that: The environmental data includes at least: ambient temperature, ambient pressure, inlet guide vane (IGV) angle, fuel quantity, and rotation speed; the measured data includes at least: compressor outlet pressure, compressor outlet temperature, and turbine outlet temperature; the unmeasured data includes at least: compressor efficiency, turbine efficiency, combustion chamber efficiency, air flow, surge margin, and flame temperature.

7. A gas turbine control system, characterized in that: include: Control platform and computing platform; Wherein, the control platform includes a gas turbine, an online model and a control algorithm module, for executing the method according to any one of claims 3 to 6; The computing platform includes a Kalman filter and a machine learning algorithm module, and is used to execute the method according to any one of claims 1 to 2.

8. A gas turbine control device, characterized in that: include: A first receiving module is used to receive the measured values ​​and predicted values ​​of the measured data sent by the control platform; an optimal estimation module, configured to input the measured value and the predicted value of the measured data into a Kalman filter for optimal estimation to obtain a deviation of the measured data; a determination module, configured to determine a deviation amount of unmeasured data using a machine learning algorithm based on the deviation amount of the measured data; a first sending module, configured to send the deviation of the measured data and the deviation of the unmeasured data to an online model of the gas turbine, so as to correct the predicted values ​​of the measured data and the predicted values ​​of the unmeasured data output by the online model; The determining module is specifically configured to: Using the deviation of the measured data as an input of the machine learning algorithm, and outputting the deviation of the unmeasured data according to a mapping relationship between the deviation of the measured data and the deviation of the unmeasured data; Also includes: An acquisition module, used to acquire a training deviation of measured data and a training deviation of unmeasured data; A training module is used to train the machine learning algorithm with the training deviation of the measured data as input and the training deviation of the unmeasured data as output, so that the machine learning algorithm learns the mapping relationship between the deviation of the measured data and the deviation of the unmeasured data.

9. The device according to claim 8, characterized in that The measured data includes at least: compressor outlet pressure, compressor outlet temperature, turbine outlet temperature; the unmeasured data includes at least: compressor efficiency, turbine efficiency, combustion chamber efficiency, air flow, surge margin, and flame temperature.

10. A gas turbine control device, characterized in that: include: A first processing module is configured to obtain environmental data and input the environmental data into an online model to predict measured data and unmeasured data, so as to obtain predicted values ​​of the measured data and the unmeasured data; a measuring module, configured to measure the measured data using a measuring device to obtain a measurement value of the measured data; A second sending module, configured to send the measured values ​​and predicted values ​​of the measured data to a computing platform; a second receiving module, configured to receive the deviation of the measured data and the deviation of the unmeasured data sent by the computing platform, comprising: using the deviation of the measured data as an input to a machine learning algorithm, and outputting the deviation of the unmeasured data based on a mapping relationship between the deviation of the measured data and the deviation of the unmeasured data; a correction module, configured to correct the predicted values ​​of the measured data and the predicted values ​​of the unmeasured data output by the online model according to the deviation of the measured data and the deviation of the unmeasured data; Also includes: Obtaining the training deviation of measured data and the training deviation of unmeasured data; The machine learning algorithm is trained with the training deviation of the measured data as input and the training deviation of the unmeasured data as output, so that the machine learning algorithm learns the mapping relationship between the deviation of the measured data and the deviation of the unmeasured data.

11. The device according to claim 10, characterized in that The first processing module is further configured to: The environmental data is input into an online model so that the online model predicts the measured data and the unmeasured data based on a target formula; wherein the target formula includes an energy conservation formula and a set thermodynamic formula.

12. The device according to claim 11, characterized in that The device comprises: The second processing module is configured to use the corrected predicted value of the measured data and the predicted value of the unmeasured data as control boundaries of a control algorithm.

13. The device according to any one of claims 10 to 12, characterized in that: The environmental data includes at least: ambient temperature, ambient pressure, inlet guide vane (IGV) angle, fuel quantity, and rotation speed; the measured data includes at least: compressor outlet pressure, compressor outlet temperature, and turbine outlet temperature; the unmeasured data includes at least: compressor efficiency, turbine efficiency, combustion chamber efficiency, air flow, surge margin, and flame temperature.

14. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method according to any one of claims 1-2, or the method according to any one of claims 3-6.

15. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable the computer to execute the method according to any one of claims 1 to 2, or to execute the method according to any one of claims 3 to 6.

16. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method according to any one of claims 1 to 2, or the method according to any one of claims 3 to 6.

Images