An intelligent start-stop energy-saving control method for auxiliary machine groups of a thermal power unit

Abstract

The application discloses a kind of intelligent start-stop energy-saving control methods of thermal power unit auxiliary machine group, it includes: S1: real-time or periodic collection thermal power unit auxiliary machine operation data;S2: based on thermal power unit auxiliary machine operation data establishes auxiliary machine group energy consumption model, auxiliary machine group energy consumption model with unit load as main input variable, calculates total plant power consumption under different auxiliary machine combination operation mode;S3: with minimization plant power rate as objective function constructs auxiliary machine start-stop optimization model;S4: according to unit load and operation demand, determine auxiliary machine optimal operation combination and start-stop sequence;S5: generate and issue start-stop control instruction, and then execute start-stop control instruction;S6: feedback to execution result, and dynamically correct auxiliary machine start-stop optimization model, realize real-time optimization control.The method can effectively reduce auxiliary machine system energy consumption, avoid frequent start-stop, improve unit operation economy and equipment service life.

Description

Technical Field

[0001] This invention relates to the field of thermal power generation technology, and in particular to an intelligent start-stop energy-saving control method for auxiliary equipment groups of thermal power units. Background Technology

[0002] During the operation of thermal power units, auxiliary systems (such as fans, pumps, and coal mills) consume a large amount of plant power, and their operation directly affects the overall economic efficiency of the unit. Traditional auxiliary system operation methods typically rely on fixed configurations or manual experience-based control, which suffers from problems such as suboptimal operating combinations, unreasonable start-up and shutdown strategies, and excessively high plant power consumption. Therefore, it is necessary to propose an intelligent auxiliary system optimization control method. Summary of the Invention

[0003] This invention provides an intelligent start-stop energy-saving control method for auxiliary equipment groups of thermal power units, in order to solve the technical problems existing in the prior art.

[0004] To achieve the above objectives, the present invention provides an intelligent start-stop energy-saving control method for auxiliary equipment groups of thermal power units, comprising: S1: Real-time or periodic acquisition of auxiliary equipment operation data of thermal power units; S2: Based on the operating data of auxiliary equipment of thermal power units, establish an auxiliary equipment group energy consumption model. The auxiliary equipment group energy consumption model takes the unit load as the main input variable and calculates the total power consumption of the plant under different auxiliary equipment combination operation modes. S3: Construct an auxiliary machine start-stop optimization model with minimizing plant power consumption as the objective function; S4: Determine the optimal operating combination and start-up / shutdown sequence of auxiliary equipment based on unit load and operating requirements; S5: Generate and issue start / stop control commands, and then execute the start / stop control commands; S6: Provide feedback on the execution results and dynamically correct the auxiliary machine start-stop optimization model to achieve real-time optimization control.

[0005] In one embodiment of the present invention, optionally, the auxiliary machine operation data of the thermal power unit collected in step S1 includes the following (1)-(3): (1) Operating status and real-time power of each blower, induced draft fan, primary air fan, circulating water pump, condensate pump and coal mill; (2) Current load of the unit; (3) Auxiliary machine outlet pressure, flow rate, and current.

[0006] In one embodiment of the present invention, optionally, in step S1, data acquisition is completed through a distributed control system or a plant-level monitoring information system, and the sampling period is 1-10 seconds.

[0007] In one embodiment of the present invention, optionally, in step S2, the auxiliary machine group energy consumption model includes a mechanism-data hybrid model and a neural network model, wherein: Mechanism-data hybrid model: Energy consumption is calculated based on the auxiliary machine characteristic curve and the current operating point. The auxiliary machine characteristic curve is the flow-power characteristic curve and / or the air volume-power characteristic curve. Neural network model: The model takes the unit load, ambient temperature, and auxiliary equipment combination code as inputs and outputs the total energy consumption.

[0008] In one embodiment of the present invention, optionally, in step S3, the objective function as follows:

[0009] in, Indicates the first Auxiliary machines, where n is the total number of auxiliary machines and W is the generating power of the unit; For the first The power of the auxiliary machine. The sampling period.

[0010] In one embodiment of the present invention, optionally, the constraints of the objective function include the following (1)-(4): (1) Load balance constraint: The total output of auxiliary equipment must meet the air volume, water volume and coal volume requirements of the unit under the current load; (2) Minimum operating time constraint of equipment: The auxiliary machine must run for at least T after startup. min Time, T min It needs to be set in advance; (3) Minimum equipment downtime constraint: After the auxiliary machine is shut down, it must wait for T off,min,I It will take minutes to restart, T off,min,I It needs to be set in advance; (4) Logical constraints: including the requirement that at least one blower and one induced draft fan be in operation, and the requirement that the number of coal mills be matched with the load.

[0011] In one embodiment of the present invention, optionally, the auxiliary machine start-stop optimization model adopts linear programming or a heuristic algorithm, including genetic algorithm, particle swarm optimization algorithm, differential evolution algorithm and / or dynamic programming.

[0012] In one embodiment of the present invention, the optimal start-stop command determined in step S4 is optionally converted into a command format that the distributed control system can recognize and sent to the distributed control system via OPC, Modbus or industrial Ethernet interface. The distributed control system automatically executes the start, stop or standby switching operations of the auxiliary machine in a predetermined order. For important auxiliary machines, a "start first, stop later" strategy is adopted to avoid power interruption.

[0013] In one embodiment of the present invention, optionally, in step S6, after executing the start-stop command, the actual auxiliary machine power and unit load data after execution are collected and compared with the predicted value of the auxiliary machine group energy consumption model in step S2, and the model prediction error is calculated. When the error exceeds the set threshold T, the model parameters are corrected. The correction methods include: updating the regression model coefficients using the sliding window least squares method, correcting the model state online using Kalman filtering, and for neural network models, using incremental learning or online fine-tuning. The revised auxiliary machine group energy consumption model is used for the next round of optimization, forming a closed-loop control of "perception-optimization-execution-feedback-correction".

[0014] In one embodiment of the present invention, T is optionally 5%.

[0015] The intelligent start-stop energy-saving control method for auxiliary equipment groups of thermal power units provided by this invention has the following beneficial technical effects: (1) Achieve optimized configuration of auxiliary equipment group operation; (2) Reduce plant power consumption rate and improve economic efficiency; (3) Avoid frequent start-ups and shutdowns to extend equipment life; (4) Improve the level of automated operation of the unit. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a structural diagram of an intelligent start-stop energy-saving control system for auxiliary equipment groups of thermal power units according to an embodiment of the present invention; Figure 2 This is a flowchart illustrating the start-stop optimization process according to an embodiment of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] First embodiment: like Figure 1The diagram shown is a structural diagram of an intelligent start-stop energy-saving control system for auxiliary units of a thermal power unit according to an embodiment of the present invention. Steps S1-S6 of the present invention correspond to... Figure 1 The layers in the model are as follows: step S1 corresponds to the data acquisition layer, step S2 corresponds to the energy consumption model layer, step S3 corresponds to the optimization model layer, steps S4 and S5 correspond to the start / stop control command layer, and step S6 corresponds to the feedback correction layer. Figure 1 In E represents the energy consumption of auxiliary equipment (such as power, electricity consumption, coal consumption, etc.), P represents the unit load / output (process load), T represents the temperature (such as ambient temperature, medium temperature), and Q represents the flow rate (such as medium flow rate, air volume, water volume). This indicates the mapping relationship between energy consumption and operating parameters.

[0020] This invention provides an intelligent start-stop energy-saving control method for auxiliary equipment groups of thermal power units, comprising: S1: Real-time or periodic acquisition of auxiliary equipment operation data of thermal power units; The auxiliary equipment operation data of the thermal power unit collected in step S1 may include, for example, the following (1)-(3): (1) Operating status (running / stopping) and real-time power (kW) of each blower, induced draft fan, primary air fan, circulating water pump, condensate pump and coal mill; (2) Current load of the unit (MW); (3) Auxiliary machine outlet pressure, flow rate, and current.

[0021] In step S1, data acquisition can be accomplished, for example, through a distributed control system (DCS) or a plant-level monitoring information system (SIS), with a sampling period of 1-10 seconds. In other embodiments, data acquisition can be performed by other systems, and the sampling period can be adjusted adaptively. This invention is not limited to the systems and sampling periods listed above.

[0022] In other embodiments, the auxiliary equipment operation data of thermal power units can be added to or subtracted from the above data, and the present invention is not limited to the data listed above.

[0023] S2: Based on the operating data of auxiliary equipment of thermal power units, establish an auxiliary equipment group energy consumption model. The auxiliary equipment group energy consumption model takes the unit load as the main input variable and calculates the total power consumption of the plant under different auxiliary equipment combination operation modes. In step S2, the auxiliary equipment group energy consumption model may include, for example, a mechanism-data hybrid model and a neural network model, wherein: Mechanism-data hybrid model: Energy consumption is calculated based on the auxiliary machine characteristic curve and the current operating point. The auxiliary machine characteristic curve is the flow-power characteristic curve and / or the air volume-power characteristic curve. Neural network model: The model takes the unit load, ambient temperature, and auxiliary equipment combination code as inputs and outputs the total energy consumption.

[0024] S3: Construct an auxiliary machine start-stop optimization model with minimizing plant power consumption as the objective function; In step S3, the objective function as follows:

[0025] in, Indicates the first Auxiliary machines, where n is the total number of auxiliary machines and W is the generating power of the unit; For the first The power of the auxiliary machine. The sampling period.

[0026] The constraints of the objective function include the following (1)-(4): (1) Load balance constraint: The total output of auxiliary equipment must meet the air volume, water volume and coal volume requirements of the unit under the current load; (2) Minimum operating time constraint of equipment: The auxiliary machine must run for at least T after startup. min Time, T min It needs to be set in advance; (3) Minimum equipment downtime constraint: After the auxiliary machine is shut down, it must wait for T off,min,I It will take minutes to restart, T off,min,I It needs to be set in advance; (4) Logical constraints: including the requirement that at least one blower and one induced draft fan be in operation, and the requirement that the number of coal mills be matched with the load.

[0027] S4: Determine the optimal operating combination and start-up / shutdown sequence of auxiliary equipment based on unit load and operating requirements; Based on the current unit load and the short-term load forecast (e.g., in the next 5-15 minutes), the auxiliary machine start-stop optimization model in step S3 is invoked to solve for the optimal operating combination: determining whether each auxiliary machine should be in a running or stopped state. Start-up and shutdown sequence: When it is necessary to change the combination, give the specific start-up and shutdown sequence. For example, before starting an additional coal mill, the corresponding sealing fan should be started first, or before shutting down a circulating water pump, it should be confirmed that the other pump is running stably.

[0028] The start-stop sequence also takes into account the principle of avoiding frequent start-stops: if a certain auxiliary machine is in Tmin,i If the device has already been started and stopped once within the specified time, its status will be locked in this optimization and it will not participate in the switching process to reduce device wear and tear.

[0029] S5: Generate and issue start / stop control commands, and then execute the start / stop control commands; S6: Provide feedback on the execution results and dynamically correct the auxiliary machine start / stop optimization model to achieve real-time optimization control, such as... Figure 2 The diagram shown is a start-stop optimization flowchart according to an embodiment of the present invention.

[0030] In one embodiment of the present invention, optionally, the auxiliary machine start-stop optimization model adopts linear programming or a heuristic algorithm, including genetic algorithm, particle swarm optimization algorithm, differential evolution algorithm and / or dynamic programming.

[0031] In one embodiment of the present invention, the optimal start-stop command determined in step S4 is optionally converted into a command format that the distributed control system can recognize and sent to the distributed control system via OPC, Modbus or industrial Ethernet interface. The distributed control system automatically executes the start, stop or standby switching operations of the auxiliary machine in a predetermined order. For important auxiliary machines, a "start first, stop later" strategy is adopted to avoid power interruption.

[0032] In one embodiment of the present invention, optionally, in step S6, after executing the start-stop command, the actual auxiliary machine power and unit load data after execution are collected and compared with the predicted value of the auxiliary machine group energy consumption model in step S2, and the model prediction error is calculated. When the error exceeds a set threshold T (T is, for example, 5%), the model parameters are corrected. The correction methods include: updating the regression model coefficients using the sliding window least squares method, using Kalman filtering to correct the model state online, and for neural network models, using incremental learning or online fine-tuning. The revised auxiliary machine group energy consumption model is used for the next round of optimization, forming a closed-loop control of "perception-optimization-execution-feedback-correction".

[0033] The intelligent start-stop energy-saving control method for auxiliary equipment groups of thermal power units provided by this invention is applicable to different loads and operating conditions. This method can reduce plant power consumption and improve the economic operation of the unit.

[0034] Second embodiment: Taking a subcritical 300MW thermal power unit as an example, its auxiliary equipment includes: 2 forced draft fans (A / B), 2 induced draft fans (A / B), 3 coal mills (A / B / C), and 2 circulating water pumps (A / B). When the unit load increases from 150MW to 250MW, the system executes the following steps: Data collected: Current load is 150MW, and the operating configuration is: 1 forced draft fan, 1 induced draft fan, 2 coal mills, 1 circulating water pump, with a total auxiliary power of 4.2MW.

[0035] Energy consumption model: Based on the regression model established from historical data, the total power is predicted to be 6.1MW if 1 forced draft fan, 1 induced draft fan, 3 coal mills and 2 circulating water pumps are maintained at 250MW; if 2 forced draft fans, 2 induced draft fans, 3 coal mills and 2 circulating water pumps are used, the total power is 7.5MW.

[0036] Optimized solution: Considering the minimum running time constraint (coal mill ≥ 30 minutes), the heuristic algorithm recommends the following combination: 2 forced draft fans, 2 induced draft fans, 3 coal mills, and 1 circulating water pump, with a total power of 6.8MW and the lowest plant power consumption.

[0037] Determine the sequence: first start the second forced draft fan (delay for 10 seconds), then start the second induced draft fan, and then start the third coal mill; maintain a single circulating water pump in operation.

[0038] Command issuance: The above sequence is executed automatically via DCS, with a total time of approximately 2 minutes.

[0039] Feedback correction: After execution, the actual total power is 6.9MW, the model error is 1.6%, which is less than 5%, so no correction is triggered. The system continues to the next optimization cycle.

[0040] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of one embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing the present invention.

[0041] Those skilled in the art will understand that the modules in the apparatus of the embodiments can be distributed in the apparatus of the embodiments as described in the embodiments, or they can be located in one or more devices different from this embodiment with corresponding changes. The modules of the above embodiments can be combined into one module, or they can be further divided into multiple sub-modules.

[0042] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligent start-stop energy-saving control of auxiliary equipment groups in thermal power units, characterized in that, include: S1: Real-time or periodic acquisition of auxiliary equipment operation data of thermal power units; S2: Based on the operating data of auxiliary equipment of thermal power units, establish an auxiliary equipment group energy consumption model. The auxiliary equipment group energy consumption model takes the unit load as the main input variable and calculates the total power consumption of the plant under different auxiliary equipment combination operation modes. S3: Construct an auxiliary machine start-stop optimization model with minimizing plant power consumption as the objective function; S4: Determine the optimal operating combination and start-up / shutdown sequence of auxiliary equipment based on unit load and operating requirements; S5: Generate and issue start / stop control commands, and then execute the start / stop control commands; S6: Provide feedback on the execution results and dynamically correct the auxiliary machine start-stop optimization model to achieve real-time optimization control.

2. The intelligent start-stop energy-saving control method for auxiliary equipment groups of thermal power units according to claim 1, characterized in that, The auxiliary equipment operation data of the thermal power unit collected in step S1 includes the following (1)-(3): (1) Operating status and real-time power of each blower, induced draft fan, primary air fan, circulating water pump, condensate pump and coal mill; (2) Current load of the unit; (3) Auxiliary machine outlet pressure, flow rate, and current.

3. The intelligent start-stop energy-saving control method for auxiliary equipment groups of thermal power units according to claim 1, characterized in that, In step S1, data acquisition is completed through a distributed control system or a plant-level monitoring information system, with a sampling period of 1-10 seconds.

4. The intelligent start-stop energy-saving control method for auxiliary equipment groups of thermal power units according to claim 1, characterized in that, In step S2, the auxiliary equipment group energy consumption model includes a mechanism-data hybrid model and a neural network model, wherein: Mechanism-data hybrid model: Energy consumption is calculated based on the auxiliary machine characteristic curve and the current operating point. The auxiliary machine characteristic curve is the flow-power characteristic curve and / or the air volume-power characteristic curve. Neural network model: The model takes the unit load, ambient temperature, and auxiliary equipment combination code as inputs and outputs the total energy consumption.

5. The intelligent start-stop energy-saving control method for auxiliary equipment groups of thermal power units according to claim 1, characterized in that, In step S3, the objective function as follows: in, Indicates the first Auxiliary machines, where n is the total number of auxiliary machines and W is the generating power of the unit; For the first The power of the auxiliary machine. The sampling period.

6. The intelligent start-stop energy-saving control method for auxiliary equipment groups of thermal power units according to claim 5, characterized in that, The constraints of the objective function include the following (1)-(4): (1) Load balance constraint: The total output of auxiliary equipment must meet the air volume, water volume and coal volume requirements of the unit under the current load; (2) Minimum operating time constraint of equipment: The auxiliary machine must run for at least T after startup. min Time, T min It needs to be set in advance; (3) Minimum equipment downtime constraint: After the auxiliary machine is shut down, it must wait for T off,min,I It will take minutes to restart, T off,min,I It needs to be set in advance; (4) Logical constraints: including the requirement that at least one blower and one induced draft fan be in operation, and the requirement that the number of coal mills be matched with the load.

7. The intelligent start-stop energy-saving control method for auxiliary equipment groups of thermal power units according to claim 6, characterized in that, The auxiliary machine start-stop optimization model adopts linear programming or heuristic algorithms, including genetic algorithms, particle swarm optimization, differential evolution algorithms and / or dynamic programming.

8. The intelligent start-stop energy-saving control method for auxiliary equipment groups of thermal power units according to claim 7, characterized in that, The optimal start / stop command determined in step S4 is converted into a command format that the distributed control system can recognize and sent to the distributed control system via OPC, Modbus or industrial Ethernet interface. The distributed control system automatically executes the start, stop or standby switching operations of the auxiliary machine in a predetermined order. For important auxiliary machines, a "start first, stop later" strategy is adopted to avoid power interruption.

9. The intelligent start-stop energy-saving control method for auxiliary equipment groups of thermal power units according to claim 1, characterized in that, In step S6, after executing the start / stop command, the actual auxiliary machine power and unit load data after execution are collected and compared with the predicted values ​​of the auxiliary machine group energy consumption model in step S2 to calculate the model prediction error. When the error exceeds the set threshold T, the model parameters are corrected. The correction methods include: updating the regression model coefficients using the sliding window least squares method, correcting the model state online using Kalman filtering, and for neural network models, using incremental learning or online fine-tuning. The revised auxiliary machine group energy consumption model is used for the next round of optimization, forming a closed-loop control of "perception-optimization-execution-feedback-correction".

10. The intelligent start-stop energy-saving control method for auxiliary equipment groups of thermal power units according to claim 9, characterized in that, T is 5%.

Images