Multi-energy output control method and system for gas-electric dual-drive system

Abstract

The present invention relates to the technical field of energy output control. The present invention discloses a multi-energy output control method and system for a steam-electric dual-drive system, including obtaining real-time working data of a generator and kinetic energy input data of a steam turbine, calculating a driving ratio according to the real-time working data and the kinetic energy input data, driving an induced draft fan based on a steam-electric hybrid driving mode and a driving ratio, obtaining real-time load data of the induced draft fan, calculating a fluctuation coefficient based on the real-time load data, inputting the real-time load data into a pre-built load prediction model to obtain predicted load data, and determining whether to drive the induced draft fan in a steam turbine direct drive mode or in a steam-driven power generation mode according to the predicted load data and the fluctuation coefficient. The present invention can timely control and adaptively adjust the driving mode according to actual monitoring conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of energy output control, and more specifically, to a multi-energy output control method and system for a gas-electric dual-drive system. Background Art

[0002] The "steam-electric dual-drive" induced draft fan exhaust steam heating technology refers to the use of a back-pressure small steam turbine with industrial frequency generator speed regulation to drive the fan system and generator set to achieve efficient energy utilization. During the system startup phase, the electric motor / generator operates in motor mode to drive the induced draft fan, thereby simplifying the fan startup conditions and eliminating the starting steam source, saving initial investment costs. When the steam parameters meet the requirements of the small steam turbine, the induced draft fan is switched to the small steam turbine drive mode. This technology uses a back-pressure machine to drive the boiler induced draft fan and uses the steam exhausted by the back-pressure machine for external heating. Although the existing technology involves technical content about "steam-electric dual-drive", there are still certain problems.

[0003] For example, the Chinese patent with publication number CN113279992A provides a boiler fan dual-drive control system and method based on a 3S coupling. When the back-pressure steam turbine cannot provide sufficient driving force, the boiler fan is driven by the drive motor and the back-pressure steam turbine together to ensure the normal operation of the boiler fan; the Chinese patent with publication number CN110159559A provides a steam-electric dual-drive induced draft fan system and its operation control method. This patent reduces the throttling loss of the steam turbine and can maintain high-efficiency operation under different loads.

[0004] Although the above patents all involve technical content about "steam-electric dual drive", since multiple operating drive modes are suitable for different scenarios, for example, the steam turbine direct drive mode is suitable for occasions with large and long loads, sufficient steam supply, and the need for efficient direct drive, while the steam-driven power generation mode is suitable for occasions with large load changes. The power distribution can be flexibly adjusted through power generation. Therefore, in the existing technology, it is usually impossible to timely control and adaptively adjust the drive mode according to actual monitoring conditions.

[0005] In view of this, the present invention proposes a multi-energy output control method and system for a gas-electric dual-drive system to solve the above-mentioned problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a multi-energy output control method and system for a gas-electric dual-drive system.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A multi-energy output control method for a gas-electric dual-drive system includes:

[0009] S10: When the induced draft fan is in the startup phase, the induced draft fan is driven by the generator, and real-time status data of the induced draft fan and working record data of the steam turbine are obtained during the startup phase, and the transition to S20 or S30 is determined based on the real-time status data and working record data;

[0010] S20: acquiring real-time working data of the generator and kinetic energy input data of the steam turbine, calculating a driving ratio according to the real-time working data and the kinetic energy input data, and driving the induced draft fan based on a steam-electric hybrid driving mode and the driving ratio;

[0011] S30: acquiring real-time load data of the induced draft fan, calculating a fluctuation coefficient based on the real-time load data, and inputting the real-time load data into a pre-built load prediction model to obtain predicted load data;

[0012] S40: Determine whether to drive the induced draft fan in a steam turbine direct drive mode or in a steam drive power generation mode according to the predicted load data and the fluctuation coefficient.

[0013] Further, the method for determining whether to proceed to S20 or S30 based on the real-time status data and the work record data includes:

[0014] Determine whether the real-time status data meets the preset requirements. When the preset requirements are met, calculate the fault impact score based on the work record data, and further determine whether the fault impact score is greater than the preset score threshold. If so, proceed to S20, if not, proceed to S30.

[0015] Furthermore, the method for determining whether the real-time status data meets the preset requirements includes:

[0016] Traverse M groups of sub-status data, and determine whether the sub-status data meets the preset rated interval. When there are N consecutive groups of sub-status data that all meet the preset rated interval, it is determined that the real-time status data meets the preset requirements. The real-time status data includes M groups of sub-status data, and M is greater than N. Both M and N are integers greater than 0. The sub-status data includes fan current value, fan vibration value and fan speed value.

[0017] Furthermore, the work record data includes total operating time, maintenance frequency value, startup vibration value and pressure abnormal change value. The method for calculating the fault impact score based on the work record data includes:

[0018] FIS= ;

[0019] Where FIS is the fault impact score, is the total running time, is the abnormal pressure change value, To start the vibration value, To maintain the frequency value, is a logarithmic function with base 3, is the inverse sine function, is the hyperbolic cosine function, is the inverse tangent function, is a constant greater than 0.

[0020] Furthermore, the method for calculating the driving ratio according to the real-time working data and the kinetic energy input data includes:

[0021] The first load is determined according to the generator current value and a preset first corresponding relationship, the second load is determined according to the steam flow value and a preset second corresponding relationship, and the ratio of the difference between the first load and the second load to the second load is used as the driving ratio, and the first load is greater than the second load.

[0022] Furthermore, the real-time load data includes outlet pressure, pipeline resistance, primary air flow rate and secondary air flow rate. The method of obtaining pipeline resistance includes:

[0023] PR= ;

[0024] Where PR is the pipeline resistance, is the pipe length, is the pipe diameter, is the fluid density, is the fluid flow rate, is the friction factor.

[0025] Furthermore, the method for calculating the fluctuation coefficient based on the real-time load data includes:

[0026] Traverse Q groups of sub-load data, calculate the corresponding sub-load coefficient based on the sub-load data, and use the standard deviation of Q sub-load coefficients as the fluctuation coefficient. The real-time load data includes Q groups of sub-load data, and the sub-load data includes outlet pressure, pipeline resistance, primary air flow and secondary air flow.

[0027] Further, the method for calculating the corresponding sub-load coefficient based on the sub-load data includes:

[0028] FLC= ;

[0029] Where FLC is the subload factor, is the outlet pressure, is the primary air flow rate, is the secondary air flow rate, Converted total pressure efficiency of the induced draft fan.

[0030] Furthermore, the method for constructing the load prediction model includes:

[0031] A historical data set, sliding step and sliding window length are preset, and the historical data set includes G groups of historical load data; the historical data set is converted into multiple training samples using a sliding window method, and the training samples are used as the input of the load prediction model, and the historical load data after the predicted sliding step is used as the output. The subsequent historical load data of each training sample is used as the prediction target, and the prediction accuracy is used as the training target to train the load prediction model; a load prediction model is generated that predicts the load data at future moments based on the real-time load data.

[0032] Furthermore, the method for judging based on the predicted load data and the fluctuation coefficient includes:

[0033] Determine whether the fluctuation coefficient is greater than the preset fluctuation coefficient threshold. If it is greater than, directly use the steam-driven power generation mode to drive the induced draft fan. If it is less than or equal to, further calculate the predicted load coefficient based on the predicted load data to determine whether the predicted load coefficient is within the preset load range. If it is within the preset load range, use the steam turbine direct drive mode to drive the induced draft fan. If it is not within the preset load range, use the steam-driven power generation mode to drive the induced draft fan.

[0034] A multi-energy output control system for a gas-electric dual-drive system, which is used to implement the above-mentioned multi-energy output control method for a gas-electric dual-drive system, comprises:

[0035] Judgment module: used to drive the induced draft fan through the generator when it is in the startup stage, obtain the real-time status data of the induced draft fan and the working record data of the steam turbine during the startup stage, and judge whether to switch to the hybrid drive module or the prediction module based on the real-time status data and the working record data;

[0036] Hybrid drive module: used to obtain the real-time working data of the generator and the kinetic energy input data of the steam turbine, calculate the drive ratio according to the real-time working data and the kinetic energy input data, and drive the induced draft fan based on the steam-electric hybrid drive mode and the drive ratio;

[0037] Prediction module: used to obtain the real-time load data of the induced draft fan, calculate the fluctuation coefficient based on the real-time load data, input the real-time load data into the pre-built load prediction model, and obtain the predicted load data;

[0038] Processing module: used to determine whether to drive the induced draft fan in steam turbine direct drive mode or steam drive power generation mode according to the predicted load data and fluctuation coefficient.

[0039] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the multi-energy output control method of the gas-electric dual-drive system.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] The present invention obtains the real-time working data of the generator and the kinetic energy input data of the steam turbine, calculates the driving ratio according to the real-time working data and the kinetic energy input data, drives the induced draft fan based on the steam-electric hybrid driving mode and the driving ratio, obtains the real-time load data of the induced draft fan, calculates the fluctuation coefficient based on the real-time load data, inputs the real-time load data into a pre-built load prediction model to obtain predicted load data, and determines whether to drive the induced draft fan in the steam turbine direct drive mode or in the steam drive power generation mode according to the predicted load data and the fluctuation coefficient. The present invention can effectively switch between the steam turbine direct drive mode and the steam drive power generation mode through real-time monitoring and data analysis, thereby ensuring the efficient operation of the system under different load conditions, extending the equipment life and improving the energy utilization rate, and can timely control and adaptively adjust the drive mode according to the actual monitoring situation, thereby solving the deficiencies in the prior art and improving the adaptability and efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flow chart of the multi-energy output control method of the steam-electric dual-drive system in the present invention;

[0043] Figure 2 It is a schematic diagram of a multi-energy output control system of a gas-electric dual-drive system in the present invention;

[0044] Figure 3 is a schematic diagram of an electronic device in the present invention;

[0045] Figure 4 A schematic diagram of a computer-readable storage medium in the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] Example 1

[0048] See also Figure 1 As shown, this embodiment discloses a multi-energy output control method for a steam-electric dual-drive system, which is applied to a steam-electric dual-drive system, wherein the steam-electric dual-drive system includes a steam turbine, a generator, and an induced draft fan, including:

[0049] S10: When the induced draft fan is in the startup phase, the induced draft fan is driven by the generator, and real-time status data of the induced draft fan and working record data of the steam turbine are obtained during the startup phase, and the transition to S20 or S30 is determined based on the real-time status data and working record data;

[0050] In this embodiment, during the starting stage of the induced draft fan, the generator operates in the form of an electric motor, and the induced draft fan is driven by the electric motor, thereby simplifying the starting conditions of the induced draft fan, eliminating the starting steam source, and saving the initial investment cost. At this time, the electric energy of the generator comes from the factory's power grid system, and the real-time status data includes but is not limited to the fan current value, fan vibration value and fan speed value. The fan current value, fan vibration value and fan speed value can all be obtained through detection by corresponding sensors, and this embodiment does not go into too much detail.

[0051] It should be added that the work record data includes but is not limited to the total operating time, maintenance frequency value, startup vibration value and abnormal pressure change value. The total operating time refers to the total operating time of the steam turbine. The maintenance frequency value can be the average monthly maintenance frequency of the steam turbine, or the average maintenance frequency of several months. The startup vibration value is the maximum vibration value detected when the steam turbine was last started. The abnormal pressure change value refers to the abnormal pressure change value of the valve connected to the steam turbine. It can be understood that the valve controls the steam to enter the interior of the steam turbine, and the valve pressure has a standard range. The difference beyond the standard range is used as the abnormal valve pressure change value. If there are several valves, the average value is taken as the abnormal valve pressure change value. The valve pressure can be obtained through the corresponding pressure sensor, and this embodiment does not go into too much detail.

[0052] The method for determining whether to transfer to S20 or S30 based on the real-time status data and the work record data includes:

[0053] Determine whether the real-time status data meets the preset requirements. When the preset requirements are met, calculate the fault impact score based on the work record data, and further determine whether the fault impact score is greater than the preset score threshold. If so, proceed to S20, if not, proceed to S30.

[0054] It should be noted that, in this embodiment, the induced draft fan is first judged whether it has entered the stable working stage from the startup stage according to the real-time status data, and then the risk of the steam turbine failure is determined according to the fault impact score, and then the subsequent operation drive mode is selected. For example, when the risk of the steam turbine failure is relatively high, the steam-electric hybrid drive mode should be selected as the operation drive mode, because the steam-electric hybrid drive mode is driven by the steam turbine and the generator. When the steam turbine fails, the generator can ensure that the system can operate stably.

[0055] Methods for determining whether the real-time status data meets the preset requirements include:

[0056] Traverse M groups of sub-state data, and determine whether the sub-state data meets the preset rated interval. When there are N consecutive groups of sub-state data that all meet the preset rated interval, it is determined that the real-time state data meets the preset requirements. The real-time state data includes M groups of sub-state data, and M is greater than N, and both M and N are integers greater than 0.

[0057] It can be understood that the sub-state data also includes the fan current value, the fan vibration value and the fan speed value. The M groups of sub-state data are acquired according to the preset time step, for example, a group of sub-state data is acquired every 15 seconds. When the fan current value, the fan vibration value and the fan speed value in the sub-state data are all within the corresponding rated interval, it can be determined that the group of sub-state data meets the preset rated interval.

[0058] Methods for calculating Failure Impact Scores based on work record data include:

[0059] FIS= ;

[0060] Where FIS is the fault impact score, is the total running time, is the abnormal pressure change value, To start the vibration value, To maintain the frequency value, is a logarithmic function with base 3, is the inverse sine function, is the hyperbolic cosine function, is the inverse tangent function, is a constant greater than 0.

[0061] In this embodiment, the total operating time and the maintenance frequency value are used for explanation. It can be understood that the greater the total operating time, the higher the probability of a steam turbine failure; the greater the maintenance frequency value, the smaller the probability of a steam turbine failure. Therefore, it can be seen from the above content that the fault impact score is positively correlated with the probability of a steam turbine failure, that is, the greater the fault impact score, the higher the probability of a steam turbine failure.

[0062] S20: acquiring real-time working data of the generator and kinetic energy input data of the steam turbine, calculating a driving ratio according to the real-time working data and the kinetic energy input data, and driving the induced draft fan based on a steam-electric hybrid driving mode and the driving ratio;

[0063] In this embodiment, the real-time working data includes at least the generator current value, and the kinetic energy input data includes at least the steam flow value. The generator current value refers to the current value when the induced draft fan is driven only by the generator to the stable working stage, and the steam flow value refers to the steam flow value entering the steam turbine. Since the steam enters the steam turbine through a pipeline, the steam flow value is detected by providing a corresponding flow sensor in the pipeline.

[0064] The method for calculating the drive ratio based on the real-time working data and kinetic energy input data includes:

[0065] The first load is determined according to the generator current value and a preset first corresponding relationship, the second load is determined according to the steam flow value and a preset second corresponding relationship, and the ratio of the difference between the first load and the second load to the second load is used as the driving ratio, and the first load is greater than the second load.

[0066] It should be noted that the first load and the second load mentioned above both refer to the load of the induced draft fan. Since the induced draft fan is directly driven by the generator during the startup phase, when the induced draft fan enters the stable working phase from the startup phase, it is necessary to consider driving the induced draft fan through a steam-electric hybrid drive mode. The steam-electric hybrid drive mode is driven by both the generator and the steam turbine, so it is necessary to adjust the drive ratio between the generator and the steam turbine.

[0067] It can be understood that the first load mentioned above represents the load when the induced draft fan enters the stable working stage. At this time, the induced draft fan is only driven by the generator. Therefore, there is a corresponding relationship between the generator current value and the first load, that is, the larger the generator current value, the larger the corresponding first load. The specific corresponding relationship can be obtained from expert experience or experiments; and when the generator and the steam turbine need to be driven together, then the load borne by the generator needs to be distributed to the steam turbine, and the steam turbine can be directly mechanically connected to the induced draft fan. The kinetic energy of the steam turbine comes from the steam. The larger the steam flow value, the stronger the kinetic energy of the steam turbine. Therefore, this embodiment determines the second load according to the steam flow value and the preset second corresponding relationship. In this embodiment, the larger the steam flow value, the larger the second load that the steam turbine can bear. In this way, the steam turbine can be used to drive the induced draft fan to the maximum extent, and the power consumed by the generator can be reduced accordingly.

[0068] It should be added that, normally the first load is greater than the second load, but when the steam flow value is too large, the second load will be greater than the first load, that is, the steam turbine can drive the induced draft fan alone. At this time, the generator can be set to standby mode. When the steam turbine fails, the generator can be quickly enabled. The generator drives the induced draft fan in the form of an electric motor to ensure the stable operation of the entire system.

[0069] S30: acquiring real-time load data of the induced draft fan, calculating a fluctuation coefficient based on the real-time load data, and inputting the real-time load data into a pre-built load prediction model to obtain predicted load data;

[0070] In this embodiment, real-time load data includes but is not limited to outlet pressure, pipeline resistance, primary air flow rate and secondary air flow rate. The outlet pressure refers to the gas pressure value detected at the outlet of the induced draft fan, the pipeline resistance refers to the resistance value inside the pipeline between the induced draft fan and the boiler, the primary air flow rate refers to the air flow rate value directly delivered to the boiler furnace, and the secondary air flow rate refers to the air flow rate value injected into the boiler furnace during the combustion process or after combustion. It can be understood that the induced draft fan delivers air to the boiler through a pipeline. The above-mentioned outlet pressure, primary air flow rate and secondary air flow rate can all be directly obtained through corresponding sensors, and this embodiment does not go into details about this.

[0071] Methods for obtaining pipeline resistance include:

[0072] PR= ;

[0073] Where PR is the pipeline resistance, is the pipe length, is the pipe diameter, is the fluid density, is the fluid flow rate, is the friction factor.

[0074] Methods for calculating the fluctuation coefficient based on real-time load data include:

[0075] Traverse Q groups of sub-load data, calculate the corresponding sub-load coefficient based on the sub-load data, and use the standard deviation of Q sub-load coefficients as the fluctuation coefficient. The real-time load data includes Q groups of sub-load data, and the sub-load data includes outlet pressure, pipeline resistance, primary air flow and secondary air flow.

[0076] Methods for calculating corresponding subload factors based on subload data include:

[0077] FLC= ;

[0078] Where FLC is the subload factor, is the outlet pressure, is the primary air flow rate, is the secondary air flow rate, Converted total pressure efficiency of the induced draft fan.

[0079] It should be noted that Q groups of sub-load data can be obtained according to the preset time step, and the sub-load coefficients corresponding to the Q groups of sub-load data can be calculated respectively. The sub-load coefficient represents the load state of the induced draft fan. When the sub-load coefficient is larger, the load state of the induced draft fan is more serious. Then, when the fluctuation coefficient is larger, it indicates that the degree of change in the load state of the induced draft fan is greater. The above-mentioned method for calculating the standard deviation is a prior art, and this embodiment will not go into details about it.

[0080] The load forecasting model construction method includes:

[0081] Preset the historical data set, sliding step length and sliding window length, the historical data set includes G groups of historical load data; convert the historical data set into multiple training samples using the sliding window method, use the training samples as the input of the load prediction model, and use the historical load data after the predicted sliding step length as the output. The subsequent historical load data of each training sample is used as the prediction target, and the prediction accuracy is used as the training target to train the load prediction model; generate a load prediction model that predicts the load data at future moments based on the real-time load data, and the load prediction model is an LSTM model;

[0082] It should be noted that the sliding window method is a conventional technical means of the LSTM model, and the present invention will not be further explained in principle here; however, in order to facilitate the implementation of the present invention, the present invention provides the following example of the sliding window method:

[0083] Assume that we want to use historical data [1,2,3,4,5,6] to train an LSTM model. In this embodiment, we take the prediction time step as 1 as an example, set the sliding step to 1, and set the sliding window length to 3; then three groups of training samples and corresponding prediction target data are generated: [1,2,3], [2,3,4], and [3,4,5] as training samples, and [4], [5], and [6] as prediction targets respectively;

[0084] The prediction accuracy can be measured using mean square error or mean absolute error as the loss function, and the weights and biases of the model are updated through the back-propagation algorithm to generate a load prediction model.

[0085] S40: Determine whether to drive the induced draft fan in a steam turbine direct drive mode or in a steam drive power generation mode according to the predicted load data and the fluctuation coefficient.

[0086] Methods based on predicted load data and fluctuation coefficients include:

[0087] Determine whether the fluctuation coefficient is greater than the preset fluctuation coefficient threshold. When it is greater than the preset fluctuation coefficient threshold, directly use the steam-driven power generation mode to drive the induced draft fan. When it is less than or equal to the preset fluctuation coefficient threshold, further calculate the predicted load coefficient based on the predicted load data to determine whether the predicted load coefficient is within the preset load range. If it is within the preset load range, use the steam turbine direct drive mode to drive the induced draft fan. If it is not within the preset load range, use the steam-driven power generation mode to drive the induced draft fan.

[0088] It should be noted that the steam-driven power generation mode refers to the use of steam to drive the steam turbine, generate electricity through the generator, and use this electricity to drive the induced draft fan. The steam turbine direct-drive mode refers to the driving of the steam turbine and the induced draft fan through a mechanical connection. The advantage of the steam-driven power generation mode is that it can be flexibly adjusted according to changes in load conditions. The advantage of the steam turbine direct-drive mode is that it is suitable for long-term high-load operation and can maintain high efficiency. Therefore, when the fluctuation coefficient is greater than the preset fluctuation coefficient threshold, it indicates that the degree of change in the load state of the induced draft fan is large, so the steam-driven power generation mode is directly adopted.

[0089] It should be added that the method for calculating the predicted load coefficient based on the predicted load data is the same as the method for calculating the corresponding sub-load coefficient based on the sub-load data. The predicted load data also includes several groups of predicted sub-load data. Therefore, this embodiment first calculates the predicted sub-load coefficients corresponding to several groups of predicted sub-load data, and takes the average value of several predicted sub-load coefficients as the predicted load coefficient. Therefore, when the predicted load coefficient is in the preset load range, it represents that the load state of the induced draft fan at a future moment is relatively serious. Therefore, the steam turbine direct drive mode is adopted. It can be understood that the fluctuation coefficient threshold and the load range are set by personnel in this field according to actual conditions, and this embodiment does not limit this.

[0090] During the startup phase, this embodiment obtains the real-time status data of the induced draft fan and the working record data of the steam turbine, determines whether to enter S20 or S30 based on the real-time status data and the working record data, obtains the real-time working data of the generator and the kinetic energy input data of the steam turbine, calculates the driving ratio according to the real-time working data and the kinetic energy input data, drives the induced draft fan based on the steam-electric hybrid driving mode and the driving ratio, obtains the real-time load data of the induced draft fan, calculates the fluctuation coefficient based on the real-time load data, inputs the real-time load data into a pre-built load prediction model to obtain predicted load data, determines whether to drive the induced draft fan in the steam turbine direct drive mode or in the steam drive power generation mode according to the predicted load data and the fluctuation coefficient. This embodiment can timely control and adaptively adjust the driving mode according to actual monitoring conditions.

[0091] Example 2

[0092] like Figure 2 As shown, this embodiment provides a multi-energy output control system for a gas-electric dual-drive system based on the first embodiment, including:

[0093] Judgment module: used to drive the induced draft fan through the generator when it is in the startup stage, obtain the real-time status data of the induced draft fan and the working record data of the steam turbine during the startup stage, and judge whether to switch to the hybrid drive module or the prediction module based on the real-time status data and the working record data;

[0094] In this embodiment, during the starting stage of the induced draft fan, the generator operates in the form of an electric motor, and the induced draft fan is driven by the electric motor, thereby simplifying the starting conditions of the induced draft fan, eliminating the starting steam source, and saving the initial investment cost. At this time, the electric energy of the generator comes from the factory's power grid system, and the real-time status data includes but is not limited to the fan current value, fan vibration value and fan speed value. The fan current value, fan vibration value and fan speed value can all be obtained through detection by corresponding sensors, and this embodiment does not go into too much detail.

[0095] It should be added that the work record data includes but is not limited to the total operating time, maintenance frequency value, startup vibration value and abnormal pressure change value. The total operating time refers to the total operating time of the steam turbine. The maintenance frequency value can be the average monthly maintenance frequency of the steam turbine, or the average maintenance frequency of several months. The startup vibration value is the maximum vibration value detected when the steam turbine was last started. The abnormal pressure change value refers to the abnormal pressure change value of the valve connected to the steam turbine. It can be understood that the valve controls the steam to enter the interior of the steam turbine, and the valve pressure has a standard range. The difference beyond the standard range is used as the abnormal valve pressure change value. If there are several valves, the average value is taken as the abnormal valve pressure change value. The valve pressure can be obtained through the corresponding pressure sensor, and this embodiment does not go into too much detail.

[0096] The method for determining whether to switch to a hybrid drive module or a prediction module based on real-time status data and work record data includes:

[0097] Determine whether the real-time status data meets the preset requirements. When the preset requirements are met, calculate the fault impact score based on the work record data, and further determine whether the fault impact score is greater than the preset score threshold. If so, enter the hybrid drive module, if not, enter the prediction module.

[0098] It should be noted that, in this embodiment, the induced draft fan is first judged whether it has entered the stable working stage from the startup stage according to the real-time status data, and then the risk of the steam turbine failure is determined according to the fault impact score, and then the subsequent operation drive mode is selected. For example, when the risk of the steam turbine failure is relatively high, the steam-electric hybrid drive mode should be selected as the operation drive mode, because the steam-electric hybrid drive mode is driven by the steam turbine and the generator. When the steam turbine fails, the generator can ensure that the system can operate stably.

[0099] Methods for determining whether the real-time status data meets the preset requirements include:

[0100] Traverse M groups of sub-state data, and determine whether the sub-state data meets the preset rated interval. When there are N consecutive groups of sub-state data that all meet the preset rated interval, it is determined that the real-time state data meets the preset requirements. The real-time state data includes M groups of sub-state data, and M is greater than N, and both M and N are integers greater than 0.

[0101] It can be understood that the sub-state data also includes the fan current value, the fan vibration value and the fan speed value. M groups of sub-state data can be acquired according to a preset time step. For example, a group of sub-state data is acquired every 15 seconds. When the fan current value, the fan vibration value and the fan speed value in the sub-state data are all within the corresponding rated interval, it can be determined that the group of sub-state data meets the preset rated interval.

[0102] Methods for calculating Failure Impact Scores based on work record data include:

[0103] FIS= ;

[0104] Where FIS is the fault impact score, is the total running time, is the abnormal pressure change value, To start the vibration value, To maintain the frequency value, is a logarithmic function with base 3, is the inverse sine function, is the hyperbolic cosine function, is the inverse tangent function, is a constant greater than 0.

[0105] In this embodiment, the total operating time and the maintenance frequency value are used for explanation. It can be understood that the greater the total operating time, the higher the probability of the steam turbine failure, and the greater the maintenance frequency value, the smaller the probability of the steam turbine failure. Therefore, it can be seen from the above content that the fault impact score is positively correlated with the probability of the steam turbine failure, that is, the greater the fault impact score, the higher the probability of the steam turbine failure.

[0106] Hybrid drive module: used to obtain the real-time working data of the generator and the kinetic energy input data of the steam turbine, calculate the drive ratio according to the real-time working data and the kinetic energy input data, and drive the induced draft fan based on the steam-electric hybrid drive mode and the drive ratio;

[0107] In this embodiment, the real-time working data includes at least the generator current value, and the kinetic energy input data includes at least the steam flow value. The generator current value refers to the current value when the induced draft fan is driven only by the generator to the stable working stage, and the steam flow value refers to the steam flow value entering the steam turbine. Since the steam enters the steam turbine through a pipeline, the steam flow value is detected by providing a corresponding flow sensor in the pipeline.

[0108] The method for calculating the drive ratio based on the real-time working data and kinetic energy input data includes:

[0109] The first load is determined according to the generator current value and a preset first corresponding relationship, the second load is determined according to the steam flow value and a preset second corresponding relationship, and the ratio of the difference between the first load and the second load to the second load is used as the driving ratio, and the first load is greater than the second load.

[0110] It should be noted that the first load and the second load mentioned above both refer to the load of the induced draft fan. Since the induced draft fan is directly driven by the generator during the startup phase, when the induced draft fan enters the stable working phase from the startup phase, it is necessary to consider driving the induced draft fan through a steam-electric hybrid drive mode. The steam-electric hybrid drive mode is driven by both the generator and the steam turbine, so it is necessary to adjust the drive ratio between the generator and the steam turbine.

[0111] Prediction module: used to obtain the real-time load data of the induced draft fan, calculate the fluctuation coefficient based on the real-time load data, input the real-time load data into the pre-built load prediction model, and obtain the predicted load data;

[0112] In this embodiment, real-time load data includes but is not limited to outlet pressure, pipeline resistance, primary air flow rate and secondary air flow rate. The outlet pressure refers to the gas pressure value detected at the outlet of the induced draft fan, the pipeline resistance refers to the resistance value inside the pipeline between the induced draft fan and the boiler, the primary air flow rate refers to the air flow rate value directly delivered to the boiler furnace, and the secondary air flow rate refers to the air flow rate value injected into the boiler furnace during the combustion process or after combustion. It can be understood that the induced draft fan delivers air to the boiler through a pipeline. The above-mentioned outlet pressure, primary air flow rate and secondary air flow rate can all be directly obtained through corresponding sensors, and this embodiment does not go into details about this.

[0113] Methods for obtaining pipeline resistance include:

[0114] PR= ;

[0115] Where PR is the pipeline resistance, is the pipe length, is the pipe diameter, is the fluid density, is the fluid flow rate, is the friction factor.

[0116] Methods for calculating the fluctuation coefficient based on real-time load data include:

[0117] Traverse Q groups of sub-load data, calculate the corresponding sub-load coefficient based on the sub-load data, and use the standard deviation of Q sub-load coefficients as the fluctuation coefficient. The real-time load data includes Q groups of sub-load data, and the sub-load data includes outlet pressure, pipeline resistance, primary air flow and secondary air flow.

[0118] Methods for calculating corresponding subload factors based on subload data include:

[0119] FLC= ;

[0120] Where FLC is the subload factor, is the outlet pressure, is the primary air flow rate, is the secondary air flow rate, Converted total pressure efficiency of the induced draft fan.

[0121] It should be noted that Q groups of sub-load data can be obtained according to the preset time step, and the sub-load coefficients corresponding to the Q groups of sub-load data can be calculated respectively. The sub-load coefficient represents the load state of the induced draft fan. When the sub-load coefficient is larger, the load state of the induced draft fan is more serious. Then, when the fluctuation coefficient is larger, it indicates that the degree of change in the load state of the induced draft fan is greater. The above-mentioned method for calculating the standard deviation is a prior art, and this embodiment will not go into details about it.

[0122] The load forecasting model construction method includes:

[0123] Preset the historical data set, sliding step length and sliding window length, the historical data set includes G groups of historical load data; convert the historical data set into multiple training samples using the sliding window method, use the training samples as the input of the load prediction model, and use the historical load data after the predicted sliding step length as the output. The subsequent historical load data of each training sample is used as the prediction target, and the prediction accuracy is used as the training target to train the load prediction model; generate a load prediction model that predicts the load data at future moments based on the real-time load data, and the load prediction model is an LSTM model;

[0124] It should be noted that the sliding window method is a conventional technical means of the LSTM model, and the present invention will not be further explained in principle here; however, in order to facilitate the implementation of the present invention, the present invention provides the following example of the sliding window method:

[0125] Assume that we want to use historical data [1,2,3,4,5,6] to train an LSTM model. In this embodiment, we take the prediction time step as 1 as an example, set the sliding step to 1, and set the sliding window length to 3; then three groups of training samples and corresponding prediction target data are generated: [1,2,3], [2,3,4], and [3,4,5] as training samples, and [4], [5], and [6] as prediction targets respectively;

[0126] The prediction accuracy can be measured using mean square error or mean absolute error as the loss function, and the weights and biases of the model are updated through the back-propagation algorithm to generate a load prediction model.

[0127] Processing module: used to determine whether to drive the induced draft fan in steam turbine direct drive mode or steam drive power generation mode according to the predicted load data and fluctuation coefficient.

[0128] Methods based on predicted load data and fluctuation coefficients include:

[0129] Determine whether the fluctuation coefficient is greater than the preset fluctuation coefficient threshold. When it is greater than the preset fluctuation coefficient threshold, the steam-driven power generation mode is directly used to drive the induced draft fan. When it is less than or equal to the preset fluctuation coefficient threshold, the predicted load coefficient is further calculated based on the predicted load data to determine whether the predicted load coefficient is within the preset load range. If it is within the preset load range, the steam turbine direct drive mode is used to drive the induced draft fan. If it is not within the preset load range, the steam-driven power generation mode is used to drive the induced draft fan.

[0130] It should be noted that the steam-driven power generation mode refers to the use of steam to drive the steam turbine, generate electricity through the generator, and use this electricity to drive the induced draft fan. The steam turbine direct-drive mode refers to the driving of the steam turbine and the induced draft fan through a mechanical connection. The advantage of the steam-driven power generation mode is that it can be flexibly adjusted according to changes in load conditions. The advantage of the steam turbine direct-drive mode is that it is suitable for long-term high-load operation and can maintain high efficiency. Therefore, when the fluctuation coefficient is greater than the preset fluctuation coefficient threshold, it indicates that the degree of change in the load state of the induced draft fan is large, so the steam-driven power generation mode is directly adopted.

[0131] Example 3

[0132] like Figure 3As shown, this embodiment discloses an electronic device, including a power supply, an interface, a keyboard, a memory, a central processing unit, and a computer program stored in the memory and executable on the central processing unit. When the central processing unit executes the computer program, the multi-energy output control method of the gas-electric dual-drive system provided by the above methods is implemented. The interface includes a network interface and a data interface. The network interface includes a wired or wireless interface, and the data interface includes an input or output interface.

[0133] Since the electronic device introduced in this embodiment is an electronic device used to implement the multi-energy output control method of the gas-electric dual-drive system in the embodiment of this application, based on the multi-energy output control method of the gas-electric dual-drive system introduced in the embodiment of this application, the technical personnel of this field can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as the technical personnel of this field implement the electronic device used in the multi-energy output control method of the gas-electric dual-drive system in the embodiment of this application, it belongs to the scope of protection of this application.

[0134] Example 4

[0135] like Figure 4 As shown, the present embodiment discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, the multi-energy output control method of the gas-electric dual-drive system is implemented.

[0136] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0137] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0138] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0139] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0140] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0141] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0142] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0143] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0144] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A multi-energy output control method for a steam-electric dual-drive system, applied to a steam-electric dual-drive system, wherein the steam-electric dual-drive system includes a steam turbine, a generator and an induced draft fan, and is characterized in that: include: S10: When the induced draft fan is in the startup phase, the induced draft fan is driven by the generator, and real-time status data of the induced draft fan and working record data of the steam turbine are obtained during the startup phase, and the transition to S20 or S30 is determined based on the real-time status data and working record data; S20: acquiring real-time working data of the generator and kinetic energy input data of the steam turbine, calculating a driving ratio according to the real-time working data and the kinetic energy input data, and driving the induced draft fan based on a steam-electric hybrid driving mode and the driving ratio; S30: acquiring real-time load data of the induced draft fan, calculating a fluctuation coefficient based on the real-time load data, and inputting the real-time load data into a pre-built load prediction model to obtain predicted load data; S40: Determine whether to drive the induced draft fan in a steam turbine direct drive mode or in a steam drive power generation mode according to the predicted load data and the fluctuation coefficient; The method for determining whether to transfer to S20 or S30 based on the real-time status data and the work record data includes: Determine whether the real-time status data meets the preset requirements. When the preset requirements are met, calculate the fault impact score based on the work record data, and further determine whether the fault impact score is greater than the preset score threshold. If so, proceed to S20, if not, proceed to S30.

2. The multi-energy output control method of the gas-electric dual-drive system according to claim 1 is characterized in that: Methods for determining whether the real-time status data meets the preset requirements include: Traverse M groups of sub-status data, and determine whether the sub-status data meets the preset rated interval. When there are N consecutive groups of sub-status data that all meet the preset rated interval, it is determined that the real-time status data meets the preset requirements. The real-time status data includes M groups of sub-status data, and M is greater than N. Both M and N are integers greater than 0. The sub-status data includes fan current value, fan vibration value and fan speed value.

3. The multi-energy output control method of the gas-electric dual-drive system according to claim 1 is characterized in that: The work record data includes the total operating time, maintenance frequency value, startup vibration value and abnormal pressure change value. The method for calculating the fault impact score based on the work record data includes: FIS= ; Where FIS is the fault impact score, is the total running time, is the abnormal pressure change value, To start the vibration value, To maintain the frequency value, is a logarithmic function with base 3, is the inverse sine function, is the hyperbolic cosine function, is the inverse tangent function, is a constant greater than 0.

4. The multi-energy output control method of the gas-electric dual-drive system according to claim 1 is characterized in that: The method for calculating the drive ratio based on the real-time working data and kinetic energy input data includes: The first load is determined according to the generator current value and a preset first corresponding relationship, the second load is determined according to the steam flow value and a preset second corresponding relationship, and the ratio of the difference between the first load and the second load to the second load is used as the driving ratio, and the first load is greater than the second load.

5. The multi-energy output control method of the gas-electric dual-drive system according to claim 1 is characterized in that: Real-time load data includes outlet pressure, pipe resistance, primary air flow and secondary air flow. Methods for obtaining pipe resistance include: PR= ; Where PR is the pipeline resistance, is the pipe length, is the pipe diameter, is the fluid density, is the fluid flow rate, is the friction factor.

6. The multi-energy output control method of the gas-electric dual-drive system according to claim 5 is characterized in that: Methods for calculating the fluctuation coefficient based on real-time load data include: Traverse Q groups of sub-load data, calculate the corresponding sub-load coefficient based on the sub-load data, and use the standard deviation of Q sub-load coefficients as the fluctuation coefficient. The real-time load data includes Q groups of sub-load data, and the sub-load data includes outlet pressure, pipeline resistance, primary air flow and secondary air flow.

7. The multi-energy output control method of the gas-electric dual-drive system according to claim 6 is characterized in that: Methods for calculating corresponding subload factors based on subload data include: FLC= ; Where FLC is the subload factor, is the outlet pressure, is the primary air flow rate, is the secondary air flow rate, Converted total pressure efficiency of the induced draft fan.

8. The multi-energy output control method of the gas-electric dual-drive system according to claim 1 is characterized in that: The load forecasting model construction method includes: A historical data set, sliding step and sliding window length are preset, and the historical data set includes G groups of historical load data; the historical data set is converted into multiple training samples using a sliding window method, and the training samples are used as the input of the load prediction model, and the historical load data after the predicted sliding step is used as the output. The subsequent historical load data of each training sample is used as the prediction target, and the prediction accuracy is used as the training target to train the load prediction model; a load prediction model is generated that predicts the load data at future moments based on the real-time load data.

9. The multi-energy output control method of the gas-electric dual-drive system according to claim 1, characterized in that: Methods based on predicted load data and fluctuation coefficients include: Determine whether the fluctuation coefficient is greater than the preset fluctuation coefficient threshold. If it is greater than, directly use the steam-driven power generation mode to drive the induced draft fan. If it is less than or equal to, further calculate the predicted load coefficient based on the predicted load data to determine whether the predicted load coefficient is within the preset load range. If it is within the preset load range, use the steam turbine direct drive mode to drive the induced draft fan. If it is not within the preset load range, use the steam-driven power generation mode to drive the induced draft fan.

10. A multi-energy output control system for a gas-electric dual-drive system, which is used to implement a multi-energy output control method for a gas-electric dual-drive system according to any one of claims 1 to 9, characterized in that: include: Judgment module: used to drive the induced draft fan through the generator when it is in the startup stage, obtain the real-time status data of the induced draft fan and the working record data of the steam turbine during the startup stage, and judge whether to switch to the hybrid drive module or the prediction module based on the real-time status data and the working record data; Hybrid drive module: used to obtain the real-time working data of the generator and the kinetic energy input data of the steam turbine, calculate the drive ratio according to the real-time working data and the kinetic energy input data, and drive the induced draft fan based on the steam-electric hybrid drive mode and the drive ratio; Prediction module: used to obtain the real-time load data of the induced draft fan, calculate the fluctuation coefficient based on the real-time load data, input the real-time load data into the pre-built load prediction model, and obtain the predicted load data; Processing module: used to determine whether to drive the induced draft fan in steam turbine direct drive mode or steam drive power generation mode according to the predicted load data and fluctuation coefficient.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the multi-energy output control method of the gas-electric dual-drive system according to any one of claims 1 to 9 is implemented.

Images