Scheduling method and device for coal pulverizing system of thermal power generating unit

Abstract

The invention belongs to the field of electric power, and discloses a scheduling method and device for a coal pulverizing system of a thermal power generating unit, and the method comprises the steps: obtaining a unit load instruction for the thermal power generating unit at the current moment, and inputting the unit load instruction at the current moment into a pre-established load instruction prediction model, the load instruction prediction model predicts the unit load instruction at the future moment according to the unit load instruction at the current moment; the predicted unit load instruction at the future moment is input into a pre-established starting and stopping scheduling rule of the coal pulverizing system, so that the operation number of the coal pulverizing system of the thermal power generating unit at the future moment and the starting and stopping time of each coal pulverizing system are determined; and scheduling the plurality of coal pulverizing systems in the thermal power generating unit based on the determined operation number and start-stop time. Under the condition of no human intervention, the coal pulverizing system is automatically started and stopped in the whole process, the power grid load requirement is tracked and responded, and the flexible operation capacity of a thermal power generating unit is remarkably improved.

Description

Technical Field

[0001] The invention belongs to the field of electric power, relates to a dispatching method, and in particular to a dispatching method and device for a pulverizing system of a thermal power unit. Background Art

[0002] In the context of building a new power system with new energy as the main body, new energy, mainly wind power and photovoltaic power, has become the main power supply of the power system. However, due to the strong randomness, volatility and intermittency inherent in new energy power generation, the difficulty of spatial and temporal balance of power in the power system will increase significantly after large-scale new energy is connected to the power grid. The key to ensuring the balance of power supply and demand at different time scales and the high-level consumption of new energy is to improve the flexible peak-shaving capacity of the new power system, which is also the biggest challenge facing the current construction of the new power system. At present and for a long time in the future, thermal power units are still the main force of peak-shaving in my country's power system, and the positioning of thermal power units has changed from supporting power sources to regulating power sources. Therefore, improving the rapidity and safety of start-stop conversion between various working conditions and various types of equipment during the peak-shaving process of thermal power units is the most important way to improve the flexible peak-shaving capacity of the power system.

[0003] As an important part of the operation of thermal power units, the safe and economical operation of the pulverizing system directly determines the economy and safety of the unit operation. In the current new power system structure, thermal power units need to frequently make large load changes to carry out peak regulation. During the rapid peak regulation of the unit, the output of the pulverizing system needs to match the load tracking capability of the unit in real time. The flexible peak regulation operation of the thermal power unit leads to more frequent start and stop of the pulverizing system. The start and stop of the pulverizing system not only includes the start and stop of the coal mill and coal feeder, but also includes the switch operation of its related electric doors and pneumatic doors, the automatic control of related adjustment valves and the automatic setting of the control object set value. During the startup process, it is necessary to complete the functions of warming the mill, establishing the start-up air volume, ignition, etc., and also to realize the control of the cold primary air adjustment valve, hot primary air adjustment valve, dynamic separator frequency and coal feeder speed of the coal mill. Therefore, the frequent start and stop of the powder making system leads to high intensity of manual operation, which greatly increases the risk of frequent operation and misoperation by operators. At the same time, the start and stop operation of the powder making system occupies most of the operating time of operators during the peak load regulation process, and operators often find it difficult to quickly and accurately adjust the system operating status. There are problems such as strong subjective experience in start and stop decisions, and the optimal start and stop timing has not been deeply explored. Summary of the invention

[0004] In view of this, the present invention discloses a scheduling method and device for a pulverizing system of a thermal power unit, which can solve the deficiencies existing in the related art.

[0005] To achieve the above purpose, the present invention discloses the following technical solutions: According to a first aspect of the present invention, a scheduling method for a pulverizing system of a thermal power unit is proposed, the method comprising: Obtaining a unit load instruction for a thermal power unit at a current moment, and inputting the unit load instruction at the current moment into a pre-established load instruction prediction model, so that the load instruction prediction model predicts the unit load instruction at a future moment according to the unit load instruction at the current moment; The predicted unit load instructions at the future time are input into the pre-established start-stop scheduling rules of the pulverizing system to determine the number of pulverizing systems of the thermal power unit in operation at the future time and the start-stop time of each pulverizing system; The multiple pulverizing systems in the thermal power unit are scheduled based on the determined operating quantity and start and stop time.

[0006] According to a second aspect of the present invention, a scheduling device for a pulverizing system of a thermal power unit is proposed, the device comprising: Prediction unit: obtains the unit load instruction for the thermal power unit at the current moment, and inputs the unit load instruction at the current moment into a pre-established load instruction prediction model, so that the load instruction prediction model predicts the unit load instruction at a future moment according to the unit load instruction at the current moment; Determining unit: the predicted unit load instruction at a future time is input into the pre-established start-stop scheduling rule of the pulverizing system to determine the number of running pulverizing systems of the thermal power unit at a future time and the start-stop time of each pulverizing system; Scheduling unit: Scheduling multiple pulverizing systems in the thermal power unit based on the determined operating quantity and start and stop time.

[0007] According to a third aspect of the present invention, an electronic device is provided, comprising: processor; a memory for storing processor-executable instructions; The processor implements the steps of the method described in the first aspect by running the executable instructions.

[0008] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which computer instructions are stored, and when the instructions are executed by a processor, the steps of the method described in the first aspect are implemented.

[0009] It can be seen from the above technical scheme that the scheduling method for the powder making system of the thermal power unit disclosed in the present invention predicts the unit load instructions of the thermal power unit at the future moment through the unit load instructions obtained by training, and determines the operating number of the powder making system of the thermal power unit at the future moment and the start and stop time of each powder making system according to the predicted unit load instructions at the future moment and the pre-established start and stop scheduling rules of the powder making system. In this way, without human intervention, the powder making system can be started and stopped autonomously throughout the process, track and respond to the load demand of the power grid, and significantly improve the flexible operation capability of the thermal power unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a flow chart of a scheduling method for a pulverizing system of a thermal power unit provided by an exemplary embodiment.

[0011] Figure 2 It is a schematic diagram of an automatic start-stop control system of a pulverizing system of a thermal power unit based on load forecasting provided by an exemplary embodiment.

[0012] Figure 3 It is a flow chart of a warm grinding control method of an automatic start-stop closed-loop control function module of a flour milling system provided by an exemplary embodiment.

[0013] Figure 4 It is a schematic diagram of an automatic warm grinding control logic provided by an exemplary embodiment.

[0014] Figure 5 It is a flow chart of a method for controlling the grinding of a powder-making system automatic start-stop closed-loop control function module provided by an exemplary embodiment.

[0015] Figure 6 It is a flow chart of a grinding stop control method of an automatic start-stop closed-loop control function module of a powder making system provided by an exemplary embodiment.

[0016] Figure 7 It is a schematic structural diagram of a device provided by an exemplary embodiment.

[0017] Figure 8 It is a block diagram of a scheduling device for a pulverizing system of a thermal power unit provided by an exemplary embodiment. DETAILED DESCRIPTION

[0018] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with one or more embodiments of the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of one or more embodiments of the present invention as detailed in the appended claims.

[0019] It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in the present invention. In some other embodiments, the steps included in the method may be more or less than those described in the present invention. In addition, a single step described in the present invention may be decomposed into multiple steps for description in other embodiments; and multiple steps described in the present invention may be combined into a single step for description in other embodiments.

[0020] To further illustrate the present invention, the following examples are provided: Figure 1 FIG. 1 is a flowchart of a scheduling method for a pulverizing system of a thermal power unit provided by an exemplary embodiment. Figure 1 As shown, the method may include the following steps: Step 102, obtaining the unit load instruction for the thermal power unit at the current moment, and inputting the unit load instruction at the current moment into a pre-established load instruction prediction model, so that the load instruction prediction model predicts the unit load instruction at a future moment according to the unit load instruction at the current moment.

[0021] In one embodiment, if Figure 2 As shown, the training process of the load instruction prediction model includes: obtaining an instruction training data set, each training sample in the instruction training data set corresponds to a unit load instruction of a thermal power unit at a certain moment; performing data preprocessing on the instruction training data set by a variable mode decomposition algorithm, and inputting the processed modal components into a to-be-trained model established based on a bidirectional long short-term memory neural network for training, wherein the bidirectional long short-term memory neural network is used to mine the dependency relationship between modal components in forward and reverse time series.

[0022] The load instruction training sample preprocessing of thermal power units is carried out by using variational mode decomposition to decompose the load instruction of the unit into An intrinsic mode function (IMF) with an optimal center frequency and limited bandwidth contains the nonlinear and timing characteristics of the load command time series.

[0023] A load instruction prediction model is established based on a bidirectional long short-term memory neural network (BiLSTM). The IMF obtained after VDM decomposition is input into the BiLSTM network to mine its dependencies in the forward and reverse time series. The BiLSTM network can consider both forward and backward information for each time step in the time series, thereby establishing a high-precision load instruction prediction model.

[0024] Furthermore, the variational problem can be described as: modal components Minimize the center frequency of the modal component under the constraint that the sum is equal to the original signal The optimization goal of the sum of the bandwidth is: ; ; ; ; ; ; ; ; in, , represent input and output features respectively, , , Represent the outputs of the forget gate, input gate, and output gate respectively. , Represent the candidate and updated memory outputs respectively, , Respectively represent the corresponding weight matrix and bias matrix, Output features for the reverse LSTM.

[0025] The bidirectional long short-term memory neural network introduces memory units and three gating mechanisms (forget gate, input gate, and output gate) to select whether to retain or delete information. The variable mode decomposition (VMD) algorithm is used to decompose the unit load command data, and a total of 8 groups of intrinsic mode functions (IMFs) are obtained. After obtaining the IMF features, they are normalized and input into the BiLSTM to construct a load command prediction model with a prediction length of 1 hour and a step length of 1 minute, which can accurately predict the future unit load command trend.

[0026] In this embodiment, the unit load instructions of the training samples are preprocessed based on the VMD algorithm. VMD decomposition can decompose the unit load instruction signal into a series of modal components with specific center frequencies and limited bandwidths. IMF represents unit load instruction information with different frequency characteristics.

[0027] Step 104, the predicted unit load instructions at future times are input into the pre-established start-stop scheduling rules of the pulverizing system to determine the number of pulverizing systems of the thermal power unit in operation at future times and the start-stop times of each pulverizing system.

[0028] Step 106: Scheduling multiple pulverizing systems in the thermal power unit based on the determined operating quantity and start / stop time.

[0029] In this embodiment, the unit load instructions of the thermal power units at future times are predicted through the unit load instructions obtained through training, and the number of operating powder making systems of the thermal power units at future times and the start and stop times of each powder making system are determined according to the predicted unit load instructions at future times and the pre-established start and stop scheduling rules of the powder making system. In this way, the powder making system can be started and stopped autonomously without human intervention, and the load demand of the power grid can be tracked and responded, which significantly improves the flexible operation capability of the thermal power units.

[0030] In one embodiment, the method further includes: obtaining the parameters of the thermal power unit and establishing a mathematical model of the milling system; according to the mathematical model of the milling system and the safety margin of the milling system abnormality , Time margin for equipment start and stop time deviation compensation , confidence vector for future load forecast correction Establish the start-stop scheduling rules.

[0031] To establish a mathematical model of the milling system, it is necessary to consider the primary air temperature at the mill inlet, the mill air-powder mixing temperature, the warm mill heating rate setting, and its start-up time. , grinding downtime Related coal type heat, instantaneous coal quantity of coal feeder and output capacity , unit energy consumption Formulate the autonomous decision-making control rules for the start and stop of the pulverizing system, and introduce the safety margin considering the abnormality of the unit pulverizing system based on whether the load instruction prediction model predicts the future unit load instruction trend and the total output capacity of the pulverizing system of the current unit is matched. , Time margin for equipment start and stop time deviation compensation and the confidence vector for future load forecast correction , establish autonomous decision-making control rules for starting and stopping the flour-making system.

[0032] Furthermore, the thermal power unit parameters include: mill inlet primary air temperature, mill air-powder mixing temperature, warm mill heating rate setting, mill start time , grinding downtime , coal type heat, instantaneous coal quantity of coal feeder, output capacity , unit energy consumption ; Mathematical model of the milling system Described as: ; in, is the actual coal heat, To design the heat of coal, , , They are the instantaneous coal feeding amount of the coal feeder and its upper and lower limits, is the unit energy consumption curve of coal mill, The primary air temperature at the mill inlet is: is the mixing temperature of the grinding air powder, , , are the warm grinding heating rate setting value and its upper and lower limits, respectively. , They are the sum of the action time of related equipment and valves during the start-up and shutdown processes of the grinding process.

[0033] The start-stop scheduling rules include startup scheduling rules and shutdown scheduling rules.

[0034] The start-up of the pulverizing system is mainly determined by whether the future grid load demand and the total output capacity of the pulverizing system currently operated by the unit match. The unit needs to start the next pulverizing system in advance before the current output capacity does not meet the grid load demand. On this basis, a safety margin is introduced to consider the abnormality of the unit's pulverizing system. , Time margin for equipment start and stop time deviation compensation and the confidence vector for future load forecast correction ,exist At this moment, the startup scheduling rule is described as: ; in, is the number of milling system operations, is the total load capacity of the milling system, For load command prediction output, is the startup time after time margin compensation, To start grinding time, It is the time margin for starting grinding.

[0035] The shutdown of the pulverizing system is mainly determined by whether the future grid load demand matches the total output capacity of the pulverizing system currently operated by the units. When the future grid load demand is less than the total output capacity of the pulverizing system after the mill is shut down, a pulverizing system can be shut down.

[0036] exist At this moment, the outage scheduling rules are described as: ; in, is the stop time after time margin compensation, The grinding downtime is It is the grinding downtime margin.

[0037] In one embodiment, the multiple powder making systems in the thermal power unit are scheduled based on the determined operating quantity and start and stop time, including: generating a start and stop scheduling instruction according to the determined operating quantity and start and stop time, and sending the start and stop scheduling instruction to the automatic start and stop closed-loop control function module of the powder making system; giving a start or stop token to the next preset powder making system, and calling the lower-level warm grinding, start grinding, and stop grinding sub-function groups according to the start or stop token.

[0038] The automatic start and stop closed-loop control function module of the pulverizing system is used to realize the automatic start and stop control of the pulverizing system of the coal-fired unit. It has developed from a single, decentralized and local control technology to autonomous control of the process flow and coordinated control of multiple process flows under multiple working conditions. The functional module configuration is used to encapsulate professional knowledge, operating experience and process mechanism. Combined with autonomous control technology, the functional module steps of warm grinding, startup and shutdown of the medium-speed direct-blowing pulverizing system are designed, which realizes the full autonomous control of the start and stop process of this type of pulverizing system, reducing the manual start and stop operation of the pulverizing system of the coal-fired unit under the flexible peak regulation of the power grid.

[0039] like Figure 3 As shown, the operation process of the warm grinding function module of the powder making system is as follows: Step 1, open the sealed air channel of the grinding group; Step 2, open the coal feeder and the outlet door of the coal mill; Step 3, start the dynamic separator of the coal mill, and the frequency converter of the dynamic separator of the coal mill is automatic; Step 4, open the cold air quick-closing door of the coal mill; Step 5, set the cold air regulating valve of the coal mill to a certain opening for ventilation, and open the hot air quick-closing door of the coal mill at the same time; Step 6, the cold air regulating valve of the coal mill is automatic to control the primary air volume of the mill inlet, and the hot air regulating valve of the coal mill is automatic to control the air temperature of the mill outlet.

[0040] like Figure 4 As shown, in the pulverizing system warm mill function module, the cold air gate of the coal mill controls the primary air volume at the mill inlet, and the hot air gate of the coal mill controls the mill outlet temperature as follows: In the automatic warm-up control logic, the cold and hot air damper control of the coal mill is respectively increased with a controller selection switch. During the warm-up process, the cold air damper control of the coal mill is switched to PID4, which automatically controls the primary air volume at the mill inlet. By adjusting the cold air door opening, the primary air volume at the mill inlet reaches the warm-up air volume. The hot air damper control of the coal mill is switched to PID2, which automatically controls the mill outlet temperature. The mill outlet temperature setting value is automatically increased according to the warm-up temperature rise rate preset by the operator. When the coal mill outlet air temperature rise rate is greater than the set value, the hot air door is closed, otherwise, the hot air door is opened. Thus, the warm-up rate during the warm-up process is controlled by adjusting the hot air door opening, so that the mill outlet temperature reaches the warm-up temperature. After the warm-up is completed and the coal feeder is started, the cold air damper control of the coal mill is switched to the conventional control PID3, which automatically controls the mill outlet air temperature. The hot air damper control of the coal mill is switched to the conventional control PID1, which automatically controls the primary air volume at the mill inlet.

[0041] like Figure 5 As shown in the figure, the operation process of the milling system grinding function module is as follows: Step 1, open the isolation door of the coal feeder inlet; Step 2, activate the secondary air box of this layer to adjust the valve automatically; Step 3, start the dynamic separator of the coal mill, and activate the dynamic separator inverter automatically; Step 4, set the mill start air volume, and the coal mill start permission conditions are met; Step 5, start the coal mill; Step 6, start the coal feeder, and set the minimum coal quantity for the coal feeder coal quantity instruction; Step 7, activate the coal feeder control automatically, and adjust the coal feeder coal quantity instruction to level.

[0042] like Figure 6 As shown in the figure, the operation process of the grinding stop function module of the milling system is as follows: Step 1, set the outlet temperature setting value of the coal mill to slowly decrease to the first stage temperature; Step 2, release the automatic control of the coal feeder; Step 3, set the coal quantity instruction of the coal feeder to the minimum coal quantity; Step 4, close the inlet isolation door of the coal feeder; Step 5, wait for the coal quantity feedback of the coal feeder to be less than 3t / h; Step 6, stop the coal feeder, and the outlet temperature setting value of the coal mill slowly decreases to the second stage temperature; Step 7, purge the coal mill; Step 8, stop the coal mill.

[0043] Figure 7 is a schematic structural diagram of a device provided by an exemplary embodiment. Figure 7At the hardware level, the device includes a processor 702, an internal bus 704, a network interface 706, a memory 708, and a non-volatile memory 710, and may also include hardware required for other functions. One or more embodiments of the present invention may be implemented based on software, such as the processor 702 reading the corresponding computer program from the non-volatile memory 710 into the memory 708 and then running it. Of course, in addition to the software implementation, one or more embodiments of the present invention do not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but may also be hardware or logic devices.

[0044] Please refer to Figure 8 A dispatching device for a pulverizing system of a thermal power unit can be applied to Figure 8 In the device shown, to implement the technical solution of the present invention, the device may include: The prediction unit 802 is used to obtain the unit load instruction for the thermal power unit at the current moment, and input the unit load instruction at the current moment into a pre-established load instruction prediction model, so that the load instruction prediction model predicts the unit load instruction at a future moment according to the unit load instruction at the current moment; The determination unit 804 is used to input the predicted unit load instruction at a future time into the pre-established start-stop scheduling rule of the pulverizing system to determine the number of running pulverizing systems of the thermal power unit at a future time and the start-stop time of each pulverizing system; The scheduling unit 806 is used to schedule the multiple powder making systems in the thermal power unit based on the determined operation quantity and start and stop time.

[0045] Optionally, the method further includes: The first construction unit 808 is used to obtain the parameters of the thermal power unit and establish a mathematical model of the pulverizing system; The second construction unit 810 is used to determine the safety margin of the milling system according to the milling system mathematical model and the milling system abnormality. , Time margin for equipment start and stop time deviation compensation , confidence vector for future load forecast correction Establish the start-stop scheduling rules.

[0046] Optional, The thermal power unit parameters include: mill inlet primary air temperature, mill air powder mixing temperature, warm mill heating rate setting, mill start time , grinding downtime , coal type heat, instantaneous coal quantity of coal feeder, output capacity , unit energy consumption ; Mathematical model of the milling system Described as: ; in, is the actual coal heat, To design the heat of coal, , , They are the instantaneous coal feeding amount of the coal feeder and its upper and lower limits, is the unit energy consumption curve of coal mill, The primary air temperature at the mill inlet is: is the mixing temperature of the grinding air powder, , , are the warm grinding heating rate setting value and its upper and lower limits, respectively. , They are the sum of the action time of related equipment and valves during the start-up and shutdown processes of the grinding process.

[0047] Optionally, the start-stop scheduling rule includes a start-up scheduling rule and a stop-operation scheduling rule; The startup scheduling rule is described as: ; in, is the number of milling system operations, is the total load capacity of the milling system, For load command prediction output, is the startup time after time margin compensation, To start grinding time, It is the grinding start time margin; The outage scheduling rule is described as: ; in, is the stop time after time margin compensation, The grinding downtime is It is the grinding downtime margin.

[0048] Optionally, the scheduling of multiple pulverizing systems in the thermal power unit based on the determined operation quantity and start / stop time includes: Generate a start-stop scheduling instruction according to the determined running quantity and start-stop time, and send the start-stop scheduling instruction to the automatic start-stop closed-loop control function module of the milling system; The next preset milling system is given a start or stop token, and the lower-level warm grinding, grinding start, and grinding stop sub-function groups are called according to the start or stop token.

[0049] Optionally, the training process of the load instruction prediction model includes: An acquisition unit 812 is used to acquire an instruction training data set, wherein each training sample in the instruction training data set corresponds to a unit load instruction of a thermal power unit at a certain moment; The training unit 814 is used to perform data preprocessing on the instruction training data set through a variable mode decomposition algorithm, and input the processed modal components into a to-be-trained model established based on a bidirectional long short-term memory neural network for training. The bidirectional long short-term memory neural network is used to mine the dependency relationship between the modal components in forward and reverse time sequences.

[0050] Optional, if satisfied modal components Minimize the center frequency of the modal component under the constraint that the sum is equal to the original signal The optimization goal of the sum of the bandwidth is: ; ; ; ; ; ; ; ; in, , represent the input and output features respectively, , , Represent the outputs of the forget gate, input gate, and output gate respectively. , Represent the candidate and updated memory outputs respectively, , Respectively represent the corresponding weight matrix and bias matrix, Output features for the reverse LSTM.

[0051] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer, which may be in the form of a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email transceiver, a game console, a tablet computer, a wearable device or a combination of any of these devices.

[0052] In a typical configuration, a computer includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0053] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0054] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0055] With respect to the computer-readable medium (or computer-readable storage medium) as described above or in any other form, computer instructions may be stored thereon, and when the instructions are executed by a processor, one or more of the above-mentioned embodiments are implemented, thereby realizing the technical solution of the present invention.

[0056] The present invention also proposes a computer program, which, when executed by a processor, implements one or more of the above embodiments, thereby realizing the technical solution of the present invention. The computer program may be specifically recorded in the above or any other form of computer-readable medium, and the present invention is not limited thereto.

[0057] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0058] The above describes specific embodiments of the present invention. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0059] The terms used in one or more embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of the present invention. The singular forms of "a", "said" and "the" used in one or more embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0060] It should be understood that although the terms first, second, third, etc. may be used to describe various information in one or more embodiments of the present invention, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of the present invention, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0061] The above description is merely a preferred embodiment of one or more embodiments of the present invention and is not intended to limit one or more embodiments of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of the present invention shall be included in the scope of protection of one or more embodiments of the present invention.

Claims

1. A scheduling method for a pulverizing system of a thermal power unit, characterized in that: The method comprises: Obtaining a unit load instruction for a thermal power unit at a current moment, and inputting the unit load instruction at the current moment into a pre-established load instruction prediction model, so that the load instruction prediction model predicts the unit load instruction at a future moment according to the unit load instruction at the current moment; The predicted unit load instructions at the future time are input into the pre-established start-stop scheduling rules of the pulverizing system to determine the number of pulverizing systems of the thermal power unit in operation at the future time and the start-stop time of each pulverizing system; The multiple pulverizing systems in the thermal power unit are scheduled based on the determined operating quantity and start and stop time.

2. The method according to claim 1, characterized in that: The method further comprises: Obtain the parameters of the thermal power unit and establish a mathematical model of the pulverizing system; According to the milling system mathematical model and the safety margin of the milling system abnormality , Time margin for equipment start and stop time deviation compensation , confidence vector for future load forecast correction Establish the start-stop scheduling rules.

3. The method according to claim 2, characterized in that The thermal power unit parameters include: mill inlet primary air temperature, mill air powder mixing temperature, warm mill heating rate setting, mill start time , grinding downtime , coal type heat, instantaneous coal quantity of coal feeder, output capacity , unit energy consumption ; Mathematical model of the milling system Described as: ； in, is the actual coal calorific value, To design the heat of coal, , , They are the instantaneous coal feeding amount of the coal feeder and its upper and lower limits, is the unit energy consumption curve of coal mill, The primary air temperature at the mill inlet is: is the mixing temperature of the grinding air powder, , , are the warm grinding heating rate setting value and its upper and lower limits, respectively. , They are the sum of the action time of related equipment and valves during the start-up and shutdown processes of the grinding process.

4. The method according to claim 2, characterized in that: The start-stop scheduling rules include start-up scheduling rules and shutdown scheduling rules; The startup scheduling rule is described as: ； in, is the number of milling system operations, is the total load capacity of the milling system, For load command prediction output, is the startup time after time margin compensation, To start grinding time, It is the grinding start time margin; The outage scheduling rule is described as: ； in, is the stop time after time margin compensation, The grinding downtime is It is the grinding downtime margin.

5. The method according to claim 1, characterized in that The method of scheduling the plurality of pulverizing systems in the thermal power unit based on the determined operation quantity and start / stop time includes: Generate a start-stop scheduling instruction according to the determined running quantity and start-stop time, and send the start-stop scheduling instruction to the automatic start-stop closed-loop control function module of the milling system; The next preset milling system is given a start or stop token, and the lower-level warm grinding, grinding start, and grinding stop sub-function groups are called according to the start or stop token.

6. The method according to claim 1, characterized in that The training process of the load instruction prediction model includes: Acquire an instruction training data set, wherein each training sample in the instruction training data set corresponds to a unit load instruction of a thermal power unit at a certain moment; The instruction training data set is preprocessed by a variable mode decomposition algorithm, and the processed modal components are input into a training model based on a bidirectional long short-term memory neural network for training. The bidirectional long short-term memory neural network is used to mine the dependency relationship between modal components in forward and reverse time sequences.

7. The method according to claim 6, characterized in that In satisfying modal components Minimize the center frequency of the modal component under the constraint that the sum is equal to the original signal The optimization goal of the sum of the bandwidth is: ； ； ； ； ； ； ； ； in, , represent the input and output features respectively, , , Represent the outputs of the forget gate, input gate, and output gate respectively. , Represent the candidate and updated memory outputs respectively, , Respectively represent the corresponding weight matrix and bias matrix, Output features for the reverse LSTM.

8. A dispatching device for a pulverizing system of a thermal power unit, characterized in that: The device comprises: Prediction unit: obtains the unit load instruction for the thermal power unit at the current moment, and inputs the unit load instruction at the current moment into a pre-established load instruction prediction model, so that the load instruction prediction model predicts the unit load instruction at a future moment according to the unit load instruction at the current moment; Determining unit: the predicted unit load instruction at a future time is input into the pre-established start-stop scheduling rule of the pulverizing system to determine the number of running pulverizing systems of the thermal power unit at a future time and the start-stop time of each pulverizing system; Scheduling unit: Scheduling multiple pulverizing systems in the thermal power unit based on the determined operating quantity and start and stop time.

9. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor implements the steps of the method according to any one of claims 1 to 7 by running the executable instructions.

10. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images