A deep peak regulation control system and method for a thermal power plant

Abstract

The present invention belongs to the technical field of thermal power peak load regulation control, and discloses a deep peak load regulation control system and method for a thermal power plant, wherein the system comprises: a thermal power unit, comprising: a boiler and a coal feeding unit, wherein the coal feeding unit is used to convey coal powder to the boiler; a main control unit, comprising: a controller and a frequency converter, wherein the frequency converter is electrically connected to the controller, and the frequency converter is used to control the coal feeding unit to adjust the coal feeding amount of conveying coal powder to the combustion chamber of the boiler according to the coal feeding control instruction generated by the controller; a monitoring unit, which is electrically connected to the controller, and is used to monitor the real-time main steam pressure value and the real-time coal feeding amount of the boiler in real time, and upload the monitored real-time main steam pressure value and the real-time coal feeding amount of the boiler to the controller. The present invention realizes the adjustment of the combustion efficiency of the boiler, and then can quickly adjust the main steam pressure, thereby improving the load response speed and stability of the unit, and improving the safety and economy of the unit operation.

Description

Technical Field

[0001] The present invention belongs to the technical field of thermal power peak regulation control, and in particular relates to a deep peak regulation control system and method for a thermal power plant. Background Art

[0002] With the continuous development of technology, the installed capacity and scale of new energy in my country are growing continuously. New energy power generation has the advantages of cleanliness, environmental protection, renewability and economy. Therefore, with the multiple advantages of new energy power stations, it can promote the transformation of energy structure and achieve sustainable development of energy.

[0003] New energy power stations, such as wind and solar power, are greatly affected by weather conditions, and their power generation will fluctuate with changes in wind speed and sunshine intensity. This volatility will lead to an imbalance in the supply and demand of the power grid, affecting the stable operation of the power grid. Due to the volatility of new energy, it will be difficult for the power grid to adjust quickly to cope with changes in load. As a traditional energy source, thermal power can quickly respond to the needs of the power grid, adjust the power, and ensure the instantaneous power balance of the power grid.

[0004] For example, during the day or seasonal peak hours, renewable energy generation may exceed the grid's demand, resulting in excess power; while at night or during bad weather, renewable energy generation decreases, which may lead to power shortages. Thermal power can increase generation when needed and reduce generation when renewable energy generation is in excess, thereby balancing the supply and demand of the grid.

[0005] As the largest power source in my country's total energy, the peak-shaving depth of large-capacity units in thermal power plants is less than 50%, and the peak-shaving depth of thermal power units in the northern centralized heating area is only 10% to 20%. Therefore, in order to achieve the strategic development of gradually increasing the proportion of new energy access to the grid, it is necessary to explore the technical route to achieve deep peak-shaving of thermal power units to meet the evolving energy strategic needs.

[0006] All existing thermal power units use the DCS system (Distributed Control System), and large thermal power units are equipped with a coordinated control system. In order to ensure the safety and economy of the unit operation, improve the flexibility and deep peak-shaving capability of the thermal power unit, there are high requirements for the coordinated control system of the thermal power unit. During the deep peak-shaving process, the most important indicators and parameters affecting the power supply quality of the unit include: the load response speed and stability of the unit, the main steam pressure, the main steam temperature, etc., and these indicators and parameters are affected by the pure delay and high-order inertia link characteristics of the thermal process of the thermal power unit boiler. The existing control algorithms and control strategies in the DCS coordinated control system cannot achieve satisfactory control effects. Summary of the invention

[0007] The purpose of the present invention is to provide a deep peak regulation control system and method for a thermal power plant, so as to solve the problem that the existing control algorithms and control strategies in the DCS coordinated control system cannot obtain satisfactory control effects due to the influence of pure delay and high-order inertia link characteristics of the thermal process of the existing thermal power unit boiler.

[0008] In order to achieve the above object, the present invention adopts the following technical solutions:

[0009] In a first aspect, the present invention provides a deep peak regulation control system for a thermal power plant, the system comprising:

[0010] A thermal power unit, comprising: a boiler and a coal feeding unit, wherein the coal feeding unit is used to transport pulverized coal to the boiler;

[0011] The main control unit includes: a controller and a frequency converter, wherein the frequency converter is electrically connected to the controller, and the frequency converter is used to control the coal feeding unit to adjust the coal feeding amount of the coal powder transported to the combustion chamber of the boiler according to the coal feeding control instruction generated by the controller;

[0012] The monitoring unit is electrically connected to the controller and is used for real-time monitoring of the real-time main steam pressure value and the real-time coal feeding amount of the boiler, and uploading the monitored real-time main steam pressure value and the real-time coal feeding amount of the boiler to the controller, wherein the controller is used for: determining the main steam pressure change based on the real-time main steam pressure value and the main steam pressure setting value, and generating the coal feeding target value of the boiler according to the main steam pressure change, wherein the main steam pressure setting value is determined based on the load value of the thermal power unit during peak load regulation; generating a coal feeding deviation value and a coal feeding deviation change based on the coal feeding target value and the real-time coal feeding amount; and using the coal feeding deviation value and the coal feeding deviation change as input values ​​of a PID control module, wherein the PID control module outputs a coal feeding control instruction, and sends the coal feeding control instruction to the frequency converter.

[0013] Preferably, the monitoring unit comprises:

[0014] A pressure sensor is electrically connected to the controller and is used to monitor the real-time main steam pressure value of the boiler in real time;

[0015] The pulverized coal monitor is electrically connected to the controller and is used to monitor the real-time coal supply amount of the boiler in real time.

[0016] Preferably, the system further comprises: a remote control terminal wirelessly connected to the controller of the main control unit for displaying the operating data of the monitoring unit, the operating data of the control unit and the operating data of the thermal power unit.

[0017] In a second aspect, the present invention provides a method for deep peak regulation control in a thermal power plant, the method comprising:

[0018] Obtaining a real-time main steam pressure value, a real-time coal supply, and a main steam pressure setting value of the boiler, wherein the main steam pressure setting value is determined based on a load value of the thermal power unit during peak load regulation;

[0019] Based on the real-time main steam pressure value and the main steam pressure setting value, the main steam pressure change is determined, and the coal supply target value of the boiler is generated according to the main steam pressure change;

[0020] Based on the coal feeding target value and the real-time coal feeding amount, a coal feeding deviation value and a coal feeding deviation change amount are generated;

[0021] The coal feeding deviation value and the coal feeding deviation variation are used as input values ​​of the PID control module, and the PID control module outputs a coal feeding control instruction, and the coal feeding unit is controlled by the coal feeding control instruction to adjust the coal feeding amount of the coal powder delivered to the combustion chamber of the boiler.

[0022] Preferably, the method further comprises: before the coal feeding deviation value and the coal feeding deviation variation are input into the PID control module, performing real-time correction on the control parameters of the PID control module.

[0023] Preferably, the control parameters of the PID control module are corrected in real time, including:

[0024] The coal feeding deviation value and the coal feeding deviation variation are input into a pre-built parameter correction model for processing to obtain a correction amount; wherein the correction amount includes: a proportional coefficient correction amount, an integral coefficient correction amount and a differential coefficient correction amount, and the parameter correction model is constructed based on a fuzzy neural network algorithm;

[0025] The control parameters of the PID control module are corrected in real time based on the correction amount to obtain corrected control parameters, wherein the corrected control parameters include: a corrected proportional coefficient, a corrected integral coefficient and a corrected differential coefficient.

[0026] Preferably, the structure of the parameter correction model includes: an input layer, a variable function construction layer, a fitness layer, a normalization layer and an output layer, the input layer has a number of nodes, and a fuzzy rule is deployed on each node.

[0027] Preferably, the coal feeding deviation value and the coal feeding deviation variation are input into a pre-built parameter correction model for processing to obtain a correction amount, including:

[0028] The coal feeding deviation value and the coal feeding deviation variation are respectively input to each node of the input layer, and the coal feeding deviation value is fuzzified based on the fuzzy rules deployed at each node to obtain a number of first fuzzy variables, and the coal feeding deviation variation is fuzzified based on the fuzzy rules deployed at each node to obtain a number of second fuzzy variables;

[0029] Inputting a plurality of first fuzzy variables and a plurality of second fuzzy variables into a variable function construction layer, and constructing a variable function according to the first fuzzy variable of each node and the second fuzzy variable of each node;

[0030] The output value of the variable function is input into the fitness layer, and the fitness of each node is calculated based on the output value of the variable function;

[0031] The fitness of each node is input into the normalization layer, and the fitness of each node is normalized to obtain the normalized output value of each node;

[0032] The normalized output value, coal feeding deviation value and coal feeding deviation variation of each node are input to the output layer, and the output layer outputs the correction value.

[0033] Preferably, the types of the parameter correction model include: a proportional coefficient correction sub-model, an integral coefficient correction sub-model and a differential coefficient correction sub-model;

[0034] The proportional coefficient correction sub-model is used to take the coal feeding deviation value and the coal feeding deviation variation as input, and output the proportional coefficient correction value;

[0035] The integral coefficient correction sub-model is used to take the coal feeding deviation value and the coal feeding deviation variation as input, and output the integral coefficient correction value;

[0036] The differential coefficient correction sub-model is used to take the coal feeding deviation value and the coal feeding deviation change as input, and output the differential coefficient correction value.

[0037] Preferably, the method further comprises: constructing a parameter correction model based on a fuzzy neural network algorithm, comprising:

[0038] Acquire training samples, wherein the training samples include: a plurality of input samples and output samples corresponding to each input sample;

[0039] The training samples are input into the fuzzy neural network for training until the fuzzy neural network converges to obtain a trained fuzzy neural network, which is used as a parameter correction model.

[0040] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned deep peak regulation control method for a thermal power plant when executing the computer program.

[0041] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned deep peak regulation control method for a thermal power plant.

[0042] Beneficial effects:

[0043] When the thermal power unit of the present invention is in a deep peak-shaving operation state, the main steam pressure setting value of the thermal power unit is determined according to different power loads, and the real-time main steam pressure value and the real-time coal supply of the boiler are monitored in real time by a monitoring unit, and the coal supply is controlled by a PID control module to adjust the combustion efficiency of the boiler, thereby enabling rapid adjustment of the main steam pressure, improving the load response speed and stability of the unit, and improving the safety and economy of the operation of the unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0045] Figure 1 It is a block diagram of a deep peak regulation control system for a thermal power plant provided by an embodiment of the present invention;

[0046] Figure 2 It is a flow chart of a deep peak regulation control method for a thermal power plant provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0048] Embodiment 1

[0049] Figure 1 is a block diagram of a deep peak regulation control system for a thermal power plant provided by an embodiment of the present invention, such as Figure 1 As shown, this embodiment provides a deep peak regulation control system for a thermal power plant, the system comprising: a thermal power unit, a main control unit and a monitoring unit;

[0050] The thermal power unit includes: a boiler and a coal feeding unit, wherein the coal feeding unit is used to convey pulverized coal to the boiler, and the boiler coal feeding unit adjusts the amount of coal conveyed to the boiler to thereby adjust the combustion efficiency of the boiler, and by adjusting the combustion efficiency, the main steam pressure is adjusted to achieve load adjustment of the thermal power unit;

[0051] The main control unit includes: a controller and a frequency converter, the frequency converter is electrically connected to the controller, and the frequency converter is used to control the coal feeding unit to adjust the coal feeding amount of the coal powder transported to the combustion chamber of the boiler according to the coal feeding control instruction generated by the controller;

[0052] The monitoring unit is electrically connected to the controller, and the monitoring unit is used to monitor the real-time main steam pressure value and the real-time coal feeding amount of the boiler in real time, and upload the monitored real-time main steam pressure value and the real-time coal feeding amount of the boiler to the controller, and the controller is used to: determine the main steam pressure change based on the real-time main steam pressure value and the main steam pressure setting value, and generate the coal feeding target value of the boiler according to the main steam pressure change, wherein the main steam pressure setting value is determined based on the load value of the thermal power unit during peak regulation; generate a coal feeding deviation value and a coal feeding deviation change based on the coal feeding target value and the real-time coal feeding amount; use the coal feeding deviation value and the coal feeding deviation change as input values ​​of a PID (Proportional-Integral-Derivative) control module, and the PID control module outputs a coal feeding control instruction, and sends the coal feeding control instruction to the frequency converter.

[0053] In the present embodiment, the controller preferably adopts a PLC controller (Programmable Logic Controller). In the thermal power unit of the present embodiment, the main steam pressure setting value of the thermal power unit is determined according to different power loads when the thermal power unit is in a deep peak-shaving operation state, and the main steam pressure of the current thermal power unit needs to be adjusted to the main steam pressure setting value. The present invention adjusts the combustion efficiency of the boiler by adjusting the coal feeding amount of the coal feeding unit, and adjusts the main steam pressure by adjusting the combustion efficiency. Therefore, the present invention uses a monitoring unit to monitor the real-time main steam pressure value and the real-time coal feeding amount of the boiler in real time, and then controls the coal feeding amount through a PID control module to adjust the combustion efficiency of the boiler, thereby enabling rapid adjustment of the main steam pressure, thereby improving the load response speed and stability of the unit, and improving the safety and economy of the unit operation.

[0054] As a further optimization of this embodiment, the monitoring unit includes: a pressure sensor and a coal powder monitor;

[0055] The pressure sensor and the pulverized coal monitor are both electrically connected to the controller. The pressure sensor is used to monitor the real-time main steam pressure value of the boiler in real time; the pulverized coal monitor is used to monitor the real-time coal feed amount of the boiler in real time.

[0056] In this embodiment, multiple pressure sensors can be arranged on the main steam pipeline for multi-point detection to improve the accuracy of main steam pressure detection; similarly, multiple coal powder monitors can be arranged at the outlet of the pulverizer and the air-powder pipeline to improve the accuracy of coal feed detection.

[0057] As a further optimization of this embodiment, the system also includes: a remote control terminal, which is wirelessly connected to the controller of the main control unit, and is used to display the operating data of the monitoring unit, the operating data of the control unit and the operating data of the thermal power unit; wherein the operating data of the monitoring unit includes: real-time coal feed rate, real-time main steam pressure, status of the pressure sensor, power and other operating data; the operating data of the control unit includes: relevant data of the controller and relevant data of the frequency converter; the operating data of the thermal power unit includes: generator related data, turbine related data, coal feeding unit related data, boiler combustion status related data, etc.

[0058] In this embodiment, the remote control terminal can be connected to the controller of the main control unit by wired means such as RS485, and can also be connected to the controller of the main control unit wirelessly through wireless communication methods such as WiFi and ZigBee; secondly, the remote control terminal can also be used to remotely control the controller of the main control unit, such as issuing adjustment instructions.

[0059] Embodiment 2

[0060] Figure 2 is a flow chart of a deep peak regulation control method for a thermal power plant provided by an embodiment of the present invention, such as Figure 2 As shown, this embodiment provides a deep peak regulation control method for a thermal power plant, the method is implemented based on the deep peak regulation control system of the thermal power plant in embodiment 1, and the method includes:

[0061] Step S10: obtaining the real-time main steam pressure value, the real-time coal supply and the main steam pressure setting value of the boiler, wherein the main steam pressure setting value is determined based on the load value of the thermal power unit during peak load regulation.

[0062] In this embodiment, a monitoring unit is used to monitor the real-time main steam pressure value and real-time coal supply of the boiler in real time. The monitoring unit includes: a pressure sensor and a pulverized coal monitor. The pressure sensor is used to monitor the real-time main steam pressure value of the boiler in real time. The pulverized coal monitor is used to monitor the real-time coal supply of the boiler in real time. The real-time output of the pressure sensor and the pulverized coal monitor is obtained to obtain the real-time main steam pressure value and real-time coal supply of the boiler.

[0063] In this embodiment, since the main steam pressure setting value is determined based on the load value of the thermal power unit during peak load regulation, different power loads (i.e., load values ​​during peak load regulation) have corresponding main steam pressure requirements. The corresponding relationship between the power load and the main steam pressure setting value can be directly obtained from the DCS system.

[0064] Step S20: Based on the real-time main steam pressure value and the main steam pressure setting value, determine the main steam pressure change, and generate the coal supply target value of the boiler according to the main steam pressure change.

[0065] In this embodiment, when the thermal power unit is in peak load regulation operation, the output load of the thermal power unit will be adjusted synchronously with the power load of the power grid. Therefore, the main steam pressure change can be determined according to the difference between the real-time main steam pressure value and the main steam pressure setting value; and the main steam pressure is adjusted by adjusting the combustion efficiency of the boiler, and the combustion efficiency of the boiler is adjusted by adjusting the coal feeding amount of the coal feeding unit to adjust the combustion efficiency of the boiler. Therefore, the main steam pressure is indirectly adjusted by adjusting the coal feeding amount of the coal feeding unit. Therefore, the combustion efficiency of the boiler can be calculated according to the coal feeding amount, and then the main steam pressure of the boiler can be calculated according to the combustion efficiency of the boiler; therefore, the coal feeding target value can be calculated according to the main steam pressure change.

[0066] Step S30: Generate a coal feeding deviation value and a coal feeding deviation change based on the coal feeding target value and the real-time coal feeding amount.

[0067] In this embodiment, after the coal feeding target value is calculated in step S20, the coal feeding deviation value and the coal feeding deviation change are calculated according to the real-time coal feeding amount detected by the coal powder monitor; wherein the coal feeding deviation value is the difference between the real-time coal feeding amount at the current sampling moment and the coal feeding target value; the coal feeding deviation change is the variance of the coal feeding deviation value within a sampling period (a sampling period has multiple sampling moments, for example, one sampling moment per millisecond, and one sampling period per second, that is, all sampling moments within the previous second of the current sampling moment); secondly, the coal feeding deviation value can also be the change value between the coal feeding deviation value at the current sampling moment and the coal feeding deviation value at the previous sampling moment.

[0068] Step S40: using the coal feeding deviation value and the coal feeding deviation variation as input values ​​of the PID control module, the PID control module outputs a coal feeding control instruction, and using the coal feeding control instruction to control the coal feeding unit to adjust the coal feeding amount of the pulverized coal delivered to the combustion chamber of the boiler.

[0069] In this embodiment, the PID control module is used to process the PID algorithm, the coal feeding deviation value and the coal feeding deviation change, and a PID control output instruction can be obtained. The PID control output instruction is used as the coal feeding control instruction. The controller sends the coal feeding control instruction to the inverter of the coal feeding unit. The inverter controls the coal feeding unit to adjust the coal feeding amount through the coal feeding control instruction; the combustion efficiency of the boiler is adjusted, and the main steam pressure can be quickly adjusted. After the main steam pressure is adjusted, the power output of the generator is adjusted, thereby improving the load response speed and stability of the unit, as well as improving the safety and economy of the unit operation.

[0070] As a further optimization of this embodiment, in order to further improve the adjustment response rate of the main steam pressure and further reduce the influence of the pure delay and high-order inertia link characteristics of the thermal process of the boiler of the thermal power unit; the method also includes: before the coal feeding deviation value and the coal feeding deviation change are input into the PID control module, the control parameters of the PID control module are corrected in real time. This embodiment reduces the adjustment time, overshoot and static error of the PID control module by correcting the control parameters in real time, thereby further improving the adjustment response rate of the main steam pressure and being able to further improve the load response speed of the unit.

[0071] Specifically, the control parameters of the PID control module are corrected in real time, including:

[0072] Step A10: input the coal feeding deviation value and the coal feeding deviation variation into a pre-built parameter correction model for processing to obtain a correction amount; wherein the correction amount includes: a proportional coefficient correction amount, an integral coefficient correction amount and a differential coefficient correction amount, and the parameter correction model is constructed based on a fuzzy neural network algorithm;

[0073] Step A20: Based on the correction amount, the control parameters of the PID control module are corrected in real time to obtain corrected control parameters, wherein the corrected control parameters include: a corrected proportional coefficient, a corrected integral coefficient and a corrected differential coefficient.

[0074] In this embodiment, the structure of the parameter correction model includes: an input layer, a variable function construction layer, a fitness layer, a normalization layer and an output layer. The input layer has a number of nodes, each of which is deployed with a fuzzy rule. The fuzzy rule is expressed in the form of IF-THEN, wherein the IF part is the conditional part and the THEN part is the conclusion part. These rules are automatically determined or adjusted through the training sample set during the training process; and the types of the parameter correction model include: three types: proportional coefficient correction sub-model, integral coefficient correction sub-model and differential coefficient correction sub-model. The proportional coefficient correction sub-model is used to take the coal feeding deviation value and the coal feeding deviation change as input, and output the proportional coefficient correction amount; the integral coefficient correction sub-model is used to take the coal feeding deviation value and the coal feeding deviation change as input, and output the integral coefficient correction amount; the differential coefficient correction sub-model is used to take the coal feeding deviation value and the coal feeding deviation change as input, and output the differential coefficient correction amount.

[0075] In this embodiment, at each sampling moment, the parameter correction model is used to generate the current coal deviation value and the correction amount corresponding to the coal feed deviation change, so as to realize real-time correction of the control parameters of the PID control module.

[0076] Specifically, the coal feeding deviation value and the coal feeding deviation variation are input into a pre-built parameter correction model for processing to obtain a correction amount, including:

[0077] Step a01: Input the coal feeding deviation value and the coal feeding deviation change into each node of the input layer respectively, perform fuzzy processing on the coal feeding deviation value based on the fuzzy rules deployed at each node to obtain a number of first fuzzy variables, perform fuzzy processing on the coal feeding deviation change based on the fuzzy rules deployed at each node to obtain a number of second fuzzy variables.

[0078] Step a02: input a plurality of first fuzzy variables and a plurality of second fuzzy variables into a variable function construction layer, and construct a variable function according to the first fuzzy variable of each node and the second fuzzy variable of each node.

[0079] In this embodiment, the variable function Y 1,ij The expression is:

[0080]

[0081] In the formula, x1 is the coal feeding deviation value, x2 is the coal feeding deviation change, A i is the first fuzzy variable of the coal feeding deviation value at the i-th node, B j is the second fuzzy variable of the coal feeding deviation change at the jth node, is the membership degree of x1 as the first fuzzy variable, x2 is the membership degree of the second fuzzy variable.

[0082] Step a03: Input the output value of the variable function to the fitness layer, and calculate the fitness of each node based on the output value of the variable function.

[0083] In this embodiment, the fitness of each node w ij The calculation expression is:

[0084]

[0085] The fitness w of each node in this embodiment is ij For input and The product of .

[0086] Step a04: Input the fitness of each node to the normalization layer, normalize the fitness of each node, and obtain the normalized output value of each node.

[0087] In this embodiment, the normalized output value of each node is The calculation expression is:

[0088]

[0089] In the formula, w1 is the sum of the membership of the coal feeding deviation value at all nodes i, and w2 is the sum of the membership of the coal feeding deviation change at all nodes j.

[0090] Step a05: input the normalized output value, coal feeding deviation value and coal feeding deviation variation of each node into the output layer, and the output layer outputs the correction value.

[0091] In this embodiment, the calculation expression of the correction amount output by the output layer is:

[0092]

[0093] In the formula, p i is the first coefficient corresponding to the coal feeding deviation value of the i-th node, q j is the second coefficient corresponding to the change in coal feeding deviation of the jth node, r i is the third coefficient of the i-th node.

[0094] In this embodiment, steps a01 to a05 are used to calculate the corresponding correction amounts for the proportional coefficient correction submodel, the integral coefficient correction submodel and the differential coefficient correction submodel, respectively. At this time, the proportional coefficient correction amount, the integral coefficient correction amount and the differential coefficient correction amount can be obtained. Then, the proportional coefficient correction amount, the integral coefficient correction amount and the differential coefficient correction amount are used to perform real-time correction on the proportional coefficient, the integral coefficient and the differential coefficient of the PID control module, respectively, to obtain the corrected proportional coefficient, the corrected integral coefficient and the corrected differential coefficient.

[0095] As a further optimization of this embodiment, the method further includes: constructing a parameter correction model based on a fuzzy neural network algorithm, including:

[0096] Step b01: obtaining training samples, wherein the training samples include: a number of input samples and output samples corresponding to each input sample;

[0097] Step b02: input the training samples into the fuzzy neural network for training until the fuzzy neural network converges to obtain a trained fuzzy neural network, and use the trained fuzzy neural network as a parameter correction model.

[0098] After the training is completed, the main steam pressure of the thermal power unit is adjusted by the method of steps S10 to S40, thereby adjusting the output power of the generator of the thermal power unit to perform the deep peak regulation operation of the thermal power unit.

[0099] When the thermal power unit of the present invention is in a deep peak-shaving operation state, the main steam pressure setting value of the thermal power unit is determined according to different power loads, and the real-time main steam pressure value and the real-time coal supply of the boiler are monitored in real time by a monitoring unit, and the coal supply is controlled by a PID control module to adjust the combustion efficiency of the boiler, thereby enabling rapid adjustment of the main steam pressure, improving the load response speed and stability of the unit, and improving the safety and economy of the operation of the unit.

[0100] Embodiment 3

[0101] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the deep peak regulation control method for a thermal power plant of Embodiment 2 is implemented.

[0102] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the deep peak regulation control method of a thermal power plant of the second embodiment is implemented.

[0103] When the thermal power unit of the present invention is in a deep peak-shaving operation state, the main steam pressure setting value of the thermal power unit is determined according to different power loads, and the real-time main steam pressure value and the real-time coal supply of the boiler are monitored in real time by a monitoring unit, and the coal supply is controlled by a PID control module to adjust the combustion efficiency of the boiler, thereby enabling rapid adjustment of the main steam pressure, improving the load response speed and stability of the unit, and improving the safety and economy of the operation of the unit.

[0104] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0105] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0106] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A deep peak regulation control system for thermal power plants, It is characterized in that The system comprises: A thermal power unit, comprising: a boiler and a coal feeding unit, wherein the coal feeding unit is used to transport pulverized coal to the boiler; The main control unit includes: a controller and a frequency converter, wherein the frequency converter is electrically connected to the controller, and the frequency converter is used to control the coal feeding unit to adjust the coal feeding amount of the coal powder transported to the combustion chamber of the boiler according to the coal feeding control instruction generated by the controller; A monitoring unit is electrically connected to the controller and is used to monitor the real-time main steam pressure value and the real-time coal feeding amount of the boiler in real time, and upload the monitored real-time main steam pressure value and the real-time coal feeding amount of the boiler to the controller; the controller is used to: determine the main steam pressure variation based on the real-time main steam pressure value and the main steam pressure setting value, and generate the coal feeding target value of the boiler according to the main steam pressure variation, wherein the main steam pressure setting value is determined based on the load value of the thermal power unit during peak load regulation; generate a coal feeding deviation value and a coal feeding deviation variation based on the coal feeding target value and the real-time coal feeding amount; use the coal feeding deviation value and the coal feeding deviation variation as input values ​​of the PID control module, the PID control module outputs a coal feeding control instruction, and sends the coal feeding control instruction to the frequency converter; Before the coal feeding deviation value and the coal feeding deviation variation are input into the PID control module, the controller is further used to: perform real-time correction on the control parameters of the PID control module, specifically, input the coal feeding deviation value and the coal feeding deviation variation into a pre-built parameter correction model for processing to obtain a correction amount; wherein the correction amount includes: a proportional coefficient correction amount, an integral coefficient correction amount and a differential coefficient correction amount, and the parameter correction model is constructed based on a fuzzy neural network algorithm; Based on the correction amount, the control parameters of the PID control module are corrected in real time to obtain corrected control parameters, wherein the corrected control parameters include: a corrected proportional coefficient, a corrected integral coefficient, and a corrected differential coefficient; The structure of the parameter correction model includes: an input layer, a variable function construction layer, a fitness layer, a normalization layer and an output layer, wherein the input layer has a plurality of nodes, and a fuzzy rule is deployed on each node; The coal feeding deviation value and the coal feeding deviation variation are input into the pre-built parameter correction model for processing to obtain the correction amount, which is specifically: The coal feeding deviation value and the coal feeding deviation variation are respectively input to each node of the input layer, and the coal feeding deviation value is fuzzified based on the fuzzy rules deployed at each node to obtain a number of first fuzzy variables, and the coal feeding deviation variation is fuzzified based on the fuzzy rules deployed at each node to obtain a number of second fuzzy variables; Inputting a plurality of first fuzzy variables and a plurality of second fuzzy variables into a variable function construction layer, and constructing a variable function according to the first fuzzy variable of each node and the second fuzzy variable of each node; The variable function The expression is: ； In the formula, is the coal feeding deviation value, is the change of coal feeding deviation, A i The coal feeding deviation value is i The first fuzzy variable of the node, B j is the change of coal feeding deviation in the j The second fuzzy variable of the node, yes is the membership degree of the first fuzzy variable, yes is the membership degree of the second fuzzy variable; The output value of the variable function is input into the fitness layer, and the fitness of each node is calculated based on the output value of the variable function; The fitness of each node The calculation expression is: ； The fitness of each node For input and The product of The fitness of each node is input into the normalization layer, and the fitness of each node is normalized to obtain the normalized output value of each node; The normalized output value, coal feeding deviation value and coal feeding deviation variation of each node are input to the output layer, and the output layer outputs the correction value.

2. The deep peak regulation control system of a thermal power plant according to claim 1, It is characterized in that The monitoring unit comprises: A pressure sensor is electrically connected to the controller and is used to monitor the real-time main steam pressure value of the boiler in real time; The pulverized coal monitor is electrically connected to the controller and is used to monitor the real-time coal supply amount of the boiler in real time.

3. The deep peak regulation control system of a thermal power plant according to claim 1, It is characterized in that The system further comprises: a remote control terminal wirelessly connected to the controller of the main control unit for displaying the operating data of the monitoring unit, the operating data of the control unit and the operating data of the thermal power unit.

4. A deep peak regulation control method for thermal power plants, It is characterized in that The method comprises: Obtaining a real-time main steam pressure value, a real-time coal supply, and a main steam pressure setting value of the boiler, wherein the main steam pressure setting value is determined based on a load value of the thermal power unit during peak load regulation; Based on the real-time main steam pressure value and the main steam pressure setting value, the main steam pressure change is determined, and the coal supply target value of the boiler is generated according to the main steam pressure change; Based on the coal feeding target value and the real-time coal feeding amount, a coal feeding deviation value and a coal feeding deviation change amount are generated; The coal feeding deviation value and the coal feeding deviation variation are used as input values ​​of the PID control module, and the PID control module outputs a coal feeding control instruction, and the coal feeding unit is controlled by the coal feeding control instruction to adjust the coal feeding amount of the pulverized coal transported into the combustion chamber of the boiler; The method further comprises: before the coal feeding deviation value and the coal feeding deviation variation are input into the PID control module, performing real-time correction on the control parameters of the PID control module; Real-time correction of the control parameters of the PID control module, including: The coal feeding deviation value and the coal feeding deviation variation are input into a pre-built parameter correction model for processing to obtain a correction amount; wherein the correction amount includes: a proportional coefficient correction amount, an integral coefficient correction amount and a differential coefficient correction amount, and the parameter correction model is constructed based on a fuzzy neural network algorithm; Based on the correction amount, the control parameters of the PID control module are corrected in real time to obtain corrected control parameters, wherein the corrected control parameters include: a corrected proportional coefficient, a corrected integral coefficient, and a corrected differential coefficient; The structure of the parameter correction model includes: an input layer, a variable function construction layer, a fitness layer, a normalization layer and an output layer, wherein the input layer has a plurality of nodes, and a fuzzy rule is deployed on each node; The coal feeding deviation value and the coal feeding deviation variation are input into the pre-built parameter correction model for processing to obtain the correction amount, including: The coal feeding deviation value and the coal feeding deviation variation are respectively input to each node of the input layer, and the coal feeding deviation value is fuzzified based on the fuzzy rules deployed at each node to obtain a number of first fuzzy variables, and the coal feeding deviation variation is fuzzified based on the fuzzy rules deployed at each node to obtain a number of second fuzzy variables; Inputting a plurality of first fuzzy variables and a plurality of second fuzzy variables into a variable function construction layer, and constructing a variable function according to the first fuzzy variable of each node and the second fuzzy variable of each node; The variable function The expression is: ； In the formula, is the coal feeding deviation value, is the change of coal feeding deviation, A i The coal feeding deviation value is i The first fuzzy variable of the node, B j is the change of coal feeding deviation in the j The second fuzzy variable of the node, yes is the membership degree of the first fuzzy variable, yes is the membership degree of the second fuzzy variable; The output value of the variable function is input into the fitness layer, and the fitness of each node is calculated based on the output value of the variable function; The fitness of each node The calculation expression is: ； The fitness of each node For input and The product of The fitness of each node is input into the normalization layer, and the fitness of each node is normalized to obtain the normalized output value of each node; The normalized output value, coal feeding deviation value and coal feeding deviation variation of each node are input to the output layer, and the output layer outputs the correction value.

5. The deep peak regulation control method for a thermal power plant according to claim 4, It is characterized in that The types of parameter correction models include: proportional coefficient correction sub-model, integral coefficient correction sub-model and differential coefficient correction sub-model; The proportional coefficient correction sub-model is used to take the coal feeding deviation value and the coal feeding deviation variation as input, and output the proportional coefficient correction value; The integral coefficient correction sub-model is used to take the coal feeding deviation value and the coal feeding deviation variation as input, and output the integral coefficient correction value; The differential coefficient correction sub-model is used to take the coal feeding deviation value and the coal feeding deviation change as input, and output the differential coefficient correction value.

6. The deep peak regulation control method for a thermal power plant according to claim 5, It is characterized in that The method further comprises: constructing a parameter correction model based on a fuzzy neural network algorithm, comprising: Acquire training samples, wherein the training samples include: a plurality of input samples and output samples corresponding to each input sample; The training samples are input into the fuzzy neural network for training until the fuzzy neural network converges to obtain a trained fuzzy neural network, which is used as a parameter correction model.

Images