A main steam temperature optimization control system based on particle swarm intelligence algorithm
Optimizing the main steam temperature control system through the particle swarm intelligent algorithm, the problem of poor adaptability of main steam temperature control in the existing technology when load changes or working conditions changes is solved, and the stability and rapid response of main steam temperature is achieved, ensuring the temperature operation within a reasonable range.
Patent Information
- Application Number
- CN202410610379.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-16
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-05-16
AI Technical Summary
The existing main steam temperature control strategy cannot adapt to the load changes or operating conditions, resulting in the unsatisfactory main steam temperature control effect and problems such as exceeding the limit or excessive fluctuations.
The main steam temperature optimization control system based on particle swarm intelligent algorithm is adopted. Through the linkage between the primary temperature reduction module and the secondary temperature reduction module, the main steam temperature APC control model is established, and the particle swarm algorithm is iteratively optimized to find the optimal model. and controller parameters to achieve stable control of main steam temperature.
It improves the stable control effect of main steam temperature, can quickly respond to changes in combustion factors, reduce temperature hysteresis, realize adaptive control of main steam temperature, and ensure that the temperature operates within a reasonable range.
Smart Images

Figure CN118391659B_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of boiler main steam temperature control, and in particular relates to a main steam temperature optimization control system based on a particle swarm intelligent algorithm. Background Art
[0002] The main steam temperature of the boiler is an important monitoring parameter in a thermal power plant. If the main steam temperature is too high or too low, it will affect the safe and economical operation of the unit. Therefore, the main steam temperature must be controlled within a reasonable range.
[0003] At present, the existing main steam temperature control strategies basically adopt the classical control theory of proportional-integral-differential control. The adjustment of control parameters cannot achieve the ideal control effect, especially when the load changes or working conditions change. It cannot adapt to the load changes or working conditions change, which makes the main steam temperature control effect unsatisfactory, and there will be over-limit or excessive fluctuations. Therefore, it is necessary to find an intelligent control strategy that can make the main steam temperature control adaptive and achieve the ideal stable control effect. Summary of the invention
[0004] The main purpose of the present invention is to provide a main steam temperature optimization control system based on a particle swarm intelligent algorithm. After the primary cooling module and the secondary cooling module are linked to establish a main steam temperature APC control model, the particle swarm algorithm is continuously iterated and optimized to find the optimal model and controller parameters, thereby improving the stability of the main steam temperature control.
[0005] To achieve the above purpose, the present invention provides a main steam temperature optimization control system based on particle swarm intelligence algorithm, comprising a primary cooling module and a secondary cooling module, wherein the primary cooling module is used for coarse adjustment of the main steam temperature and the secondary cooling module is used for fine adjustment of the main steam temperature, wherein:
[0006] The primary cooling module is used to control the secondary inlet temperature. The primary cooling module includes a primary cooling water valve and a primary cooling APC control model (algorithm). The primary cooling APC control model obtains the measured value of the secondary inlet temperature after measurement and processing in real time and adjusts the primary cooling water volume of the primary cooling water valve in real time according to the temperature change of the measured value, so as to maintain the stability of the secondary inlet temperature. At the same time, the primary cooling APC control model obtains the smoke temperature change of the combustion factor and adjusts the primary cooling water valve in advance, so as to overcome the hysteresis of the main steam temperature change. As long as the measured value of the secondary inlet temperature does not reach the set value, the primary cooling APC control model will continue to change, and the optimal value of the opening of the primary cooling water valve will be obtained through the APC algorithm, and the primary cooling water volume will be continuously changed until the secondary inlet temperature reaches the set value.
[0007] The secondary cooling module is used to control the main steam temperature. The secondary cooling module includes a secondary cooling water valve and a main steam temperature APC control model (algorithm). The main steam temperature APC control model obtains the measured value of the main steam temperature after measurement and processing in real time and adjusts the secondary cooling water volume of the secondary cooling water valve in real time according to the temperature change of the measured value, so as to maintain the main steam temperature stable; at the same time, the main steam temperature APC control model obtains the smoke temperature change of the combustion factor, and adjusts the secondary cooling water valve in advance, so as to overcome the lag of the main steam temperature change. As long as the measured value of the main steam temperature does not reach the set value, the main steam temperature APC control model will continue to change, and the optimal value of the opening of the secondary cooling water valve will be obtained through the APC algorithm, and the secondary cooling water volume will be continuously changed until the main steam temperature reaches the set value.
[0008] As a further preferred technical solution of the above technical solution, for the APC algorithm, the APC control model parameters are optimized by the particle swarm intelligent algorithm to improve the regulation performance of the APC, which is achieved by the following formula:
[0009]
[0010] Among them, pbest i The current individual optimal position, gbest i Global optimal position;
[0011] is the new velocity of the particle, ω is the inertia weight, is the current speed of the particle, c1 and c2 are learning factors, r1 and r2 are random numbers, is the current location, It's a new location.
[0012] As a further preferred technical solution of the above technical solution, the particle swarm intelligence algorithm is specifically implemented as follows:
[0013] Step S1: Initialization, setting the size, initial position and initial velocity of the particle swarm;
[0014] Step S2: Calculate the objective function of each ion, find the current individual extreme value of each particle, and thus find the current global optimal solution of the entire particle group;
[0015] Step S3: Update the speed and position of each particle.
[0016] As a further preferred technical solution of the above technical solution, for step S3, the optimization is continuously iterated to find the optimal model parameters.
[0017] As a further preferred technical solution of the above technical solution, step S3 further includes step S4: judging whether the termination condition is met, and if so, outputting the optimal solution, otherwise continuing to execute step S2. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 It is a schematic diagram of a primary temperature reduction module of a main steam temperature optimization control system based on a particle swarm intelligent algorithm of the present invention.
[0019] Figure 2 It is a schematic diagram of a secondary temperature reduction module of a main steam temperature optimization control system based on a particle swarm intelligent algorithm of the present invention.
[0020] Figure 3 It is a particle swarm intelligent algorithm flow chart of a main steam temperature optimization control system based on a particle swarm intelligent algorithm of the present invention. DETAILED DESCRIPTION
[0021] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.
[0022] In the preferred embodiment of the present invention, those skilled in the art should note that the main steam temperature and the like involved in the present invention may be regarded as prior art.
[0023] Preferred embodiments.
[0024] like Figure 1-3 As shown, the present invention discloses a main steam temperature optimization control system based on a particle swarm intelligence algorithm, comprising a primary temperature reduction module and a secondary temperature reduction module, wherein the primary temperature reduction module is used for coarse adjustment of the main steam temperature and the secondary temperature reduction module is used for fine adjustment of the main steam temperature, wherein:
[0025] The primary cooling module is used to control the secondary inlet temperature. The primary cooling module includes a primary cooling water valve and a primary cooling APC control model (algorithm). The primary cooling APC control model obtains the measured value of the secondary inlet temperature after measurement and processing in real time and adjusts the primary cooling water volume of the primary cooling water valve in real time according to the temperature change of the measured value, so as to maintain the stability of the secondary inlet temperature. At the same time, the primary cooling APC control model obtains the smoke temperature change of the combustion factor and adjusts the primary cooling water valve in advance, so as to overcome the hysteresis of the main steam temperature change. As long as the measured value of the secondary inlet temperature does not reach the set value, the primary cooling APC control model will continue to change, and the optimal value of the opening of the primary cooling water valve will be obtained through the APC algorithm, and the primary cooling water volume will be continuously changed until the secondary inlet temperature reaches the set value.
[0026] The secondary cooling module is used to control the main steam temperature. The secondary cooling module includes a secondary cooling water valve and a main steam temperature APC control model (algorithm). The main steam temperature APC control model obtains the measured value of the main steam temperature after measurement and processing in real time and adjusts the secondary cooling water volume of the secondary cooling water valve in real time according to the temperature change of the measured value, so as to maintain the main steam temperature stable; at the same time, the main steam temperature APC control model obtains the smoke temperature change of the combustion factor, and adjusts the secondary cooling water valve in advance, so as to overcome the lag of the main steam temperature change. As long as the measured value of the main steam temperature does not reach the set value, the main steam temperature APC control model will continue to change, and the optimal value of the opening of the secondary cooling water valve will be obtained through the APC algorithm, and the secondary cooling water volume will be continuously changed until the main steam temperature reaches the set value.
[0027] Specifically, for the APC algorithm, the APC control model parameters are optimized by the particle swarm intelligent algorithm to improve the regulation performance of the APC, which is achieved through the following formula:
[0028] In the boiler process index optimization module, the particle swarm intelligent algorithm is used to dynamically optimize the optimization objective function. The particle swarm algorithm is applied to the main steam temperature control APC algorithm. The particle swarm intelligent algorithm is used to optimize the APC model and controller parameters to improve the APC regulation performance.
[0029] The particle swarm algorithm is a type of swarm intelligence algorithm, which is designed by simulating the predation behavior of bird flocks. Assuming that there is only one piece of food in the area (that is, the optimal solution in the usual optimization problem), the task of the bird flock is to find this food source. During the entire search process, the bird flock transmits each other's information to let other birds know their location. Through such collaboration, they can determine whether they have found the optimal solution, and at the same time, they also transmit the information of the optimal solution to the entire bird flock. Finally, the entire bird flock can gather around the food source, which is what we call finding the optimal solution, that is, the problem converges.
[0030]
[0031] Among them, pbest i The current individual optimal position, gbedt i Global optimal position;
[0032] is the new velocity of the particle, ω is the inertia weight, is the current speed of the particle, c1 and c2 are learning factors, r1 and r2 are random numbers, is the current location, It's a new location.
[0033] More specifically, the particle swarm intelligence algorithm is implemented as follows:
[0034] Step S1: Initialization, setting the size, initial position and initial velocity of the particle swarm;
[0035] Step S2: Calculate the objective function of each ion, find the current individual extreme value of each particle, and thus find the current global optimal solution of the entire particle group;
[0036] Step S3: Update the speed and position of each particle.
[0037] Furthermore, for step S3, the optimization is performed iteratively to find the optimal model parameters.
[0038] Furthermore, step S3 further includes step S4: judging whether the termination condition is met, and if so, outputting the optimal solution, otherwise, continuing to execute step S2.
[0039] For the present invention:
[0040] The main steam temperature is stably controlled by automatically adjusting the cooling water valve. After the main steam temperature APC control model is established, the particle swarm algorithm is used to continuously iterate and optimize to find the optimal model and controller parameters, thereby improving the stability of the main steam temperature control.
[0041] By adjusting the desuperheating water output through the cascade loop, the reaction rate is enhanced with the combustion factor flue gas temperature as the feedforward quantity, and the main steam temperature is accurately tracked. When the combustion conditions in the furnace change, the combustion factor flue gas temperature directly reflects the combustion changes, and the flue gas temperature is used as a feedforward adjustment to act on the main steam temperature control in advance. Then, through the faster convergence speed and better global search ability of the particle swarm, the feedforward + particle swarm APC algorithm can achieve rapid response adjustment of the main steam temperature.
[0042] When the combustion factor flue gas temperature changes, the input to the flue gas temperature-valve position feedforward model takes effect, and the valve position also moves in advance according to the flue gas temperature change amplitude and change rate. The combustion factor feedforward compensates the state variable, improves the time response characteristics of the main steam temperature, and makes the main steam temperature control more stable.
[0043] It is worth mentioning that the technical features such as the main steam temperature involved in the patent application of this invention should be regarded as the prior art. The specific structure, working principle and possible control method and spatial layout method of these technical features can be selected by conventional methods in the field, and should not be regarded as the inventive point of this patent. This patent will not be further elaborated.
[0044] For those skilled in the art, it is still possible to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A main steam temperature optimization control system based on particle swarm intelligence algorithm, characterized in that: It includes a primary cooling module and a secondary cooling module, wherein the primary cooling module is used for coarse adjustment of the main steam temperature and the secondary cooling module is used for fine adjustment of the main steam temperature, wherein: The primary cooling module is used to control the secondary inlet temperature. The primary cooling module includes a primary cooling water valve and a primary cooling APC control model. The primary cooling APC control model obtains the measured value of the secondary inlet temperature after measurement and processing in real time and adjusts the primary cooling water volume of the primary cooling water valve in real time according to the temperature change of the measured value, so as to maintain the stability of the secondary inlet temperature. At the same time, the primary cooling APC control model obtains the smoke temperature change of the combustion factor and adjusts the primary cooling water valve in advance, so as to overcome the hysteresis of the main steam temperature change. As long as the measured value of the secondary inlet temperature does not reach the set value, the primary cooling APC control model will continue to change, and the optimal value of the opening of the primary cooling water valve will be obtained through the APC algorithm, and the primary cooling water volume will be continuously changed until the secondary inlet temperature reaches the set value. The secondary cooling module is used to control the main steam temperature. The secondary cooling module includes a secondary cooling water valve and a main steam temperature APC control model. The main steam temperature APC control model obtains the measured value of the main steam temperature after measurement and processing in real time and adjusts the secondary cooling water volume of the secondary cooling water valve in real time according to the temperature change of the measured value, so as to maintain the main steam temperature stable; at the same time, the main steam temperature APC control model obtains the smoke temperature change of the combustion factor, and adjusts the secondary cooling water valve in advance, so as to overcome the lag of the main steam temperature change. As long as the measured value of the main steam temperature does not reach the set value, the main steam temperature APC control model will continue to change, and the optimal value of the opening of the secondary cooling water valve will be obtained through the APC algorithm, and the secondary cooling water volume will be continuously changed until the main steam temperature reaches the set value.
2. The main steam temperature optimization control system based on particle swarm intelligence algorithm according to claim 1 is characterized in that: For the APC algorithm, the APC control model parameters are optimized by the particle swarm intelligent algorithm to improve the regulation performance of APC, which is achieved through the following formula: Among them, pbest i The current individual optimal position, gbest i Global optimal position; is the new velocity of the particle, ω is the inertia weight, is the current speed of the particle, c1 and c2 are learning factors, r1 and r2 are random numbers, is the current location, It's a new location.
3. The main steam temperature optimization control system based on particle swarm intelligence algorithm according to claim 2 is characterized in that: The particle swarm intelligence algorithm is implemented in the following steps: Step S1: Initialization, setting the size, initial position and initial velocity of the particle swarm; Step S2: Calculate the objective function of each ion, find the current individual extreme value of each particle, and thus find the current global optimal solution of the entire particle group; Step S3: Update the speed and position of each particle.
4. The main steam temperature optimization control system based on particle swarm intelligence algorithm according to claim 3 is characterized in that: For step S3, the optimization is performed iteratively to find the optimal model parameters.
5. The main steam temperature optimization control system based on particle swarm intelligence algorithm according to claim 4 is characterized in that: Step S3 also includes step S4: judging whether the termination condition is met, if so, outputting the optimal solution, otherwise continuing to execute step S2.
