CN118642412A - Self-adaptive adjustment unit sliding pressure optimizing operation control system - Google Patents

Abstract

The invention relates to the technical field of power system control, and discloses a self-adaptive adjustment unit sliding pressure optimizing operation control system, which comprises the following components: the self-adaptive data acquisition module is used for acquiring and preprocessing the operation data of the set in a high-precision and multi-dimensional manner; the real-time state monitoring module is connected with the self-adaptive data acquisition module and is used for dynamically monitoring and estimating the running state of the unit and detecting the abnormality and the change in real time; and the intelligent optimization decision module is connected with the high-efficiency execution control module and is used for making and optimizing a sliding pressure control strategy. The intelligent optimization decision module, the high-efficiency execution control module and the self-learning feedback module cooperate to realize real-time optimization of the sliding pressure control strategy, dynamic adjustment of control parameters and continuous optimization of the control strategy, improve the self-adaptive capacity and optimization effect of the system, and solve the problems of insufficient real-time performance of the optimization decision, insufficient accuracy and dynamic adjustment capacity of the control strategy and limited optimization and adjustment capacity of the control strategy in the prior art.

Description

Self-adaptive adjustment unit sliding pressure optimizing operation control system

Technical Field

The invention relates to the technical field of control of electric power systems, in particular to a self-adaptive adjustment unit sliding pressure optimizing operation control system.

Background

With the increasing global energy demand and increasingly stringent environmental regulations, the power industry is facing a dual pressure to increase power generation efficiency and reduce pollution emissions. Thermal power generating units are one of the main modes of power generation, and the operation efficiency and emission level of the thermal power generating units directly influence the overall efficiency and environmental influence of a power system. Therefore, the operation control strategy of the thermal power generating unit is optimized, the economical efficiency and the environmental protection performance of the thermal power generating unit are improved, and the thermal power generating unit becomes a hot spot of current research.

The traditional sliding pressure operation control system of the thermal power generating unit mainly depends on preset fixed parameters and simple PID control to realize the adjustment of main steam pressure, so that the steam turbine can be kept to operate efficiently under different loads. However, this approach has various limitations. First, the real-time performance and the comprehensiveness of the optimization decision are insufficient, and the conventional system usually adopts single-objective optimization, such as minimizing the heat consumption rate, so that it is difficult to comprehensively consider the power generation efficiency and the emission objective. In addition, the optimization decision is often based on a fixed model, and cannot be dynamically adjusted according to real-time working conditions, so that the operation effect is not ideal.

Aiming at the problems, the invention provides a self-adaptive adjustment unit sliding pressure optimizing operation control system.

Disclosure of Invention

Aiming at the defects of the prior art, the invention provides a self-adaptive regulation unit sliding pressure optimizing operation control system, which solves the problems that the traditional thermal power unit sliding pressure optimizing operation control system cannot be regulated in real time, the target is single, the control strategy execution accuracy and dynamic regulation capability are insufficient, and the control strategy optimizing and regulating capability is limited.

In order to achieve the above purpose, the invention is realized by the following technical scheme: an adaptively adjusted unit sliding pressure optimizing operation control system, comprising:

The self-adaptive data acquisition module is used for acquiring and preprocessing the operation data of the set in a high-precision and multi-dimensional manner;

The real-time state monitoring module is connected with the self-adaptive data acquisition module and is used for dynamically monitoring and estimating the running state of the unit and detecting the abnormality and the change in real time;

the intelligent optimization decision module is connected with the high-efficiency execution control module and is used for making and optimizing a sliding pressure control strategy so that the unit operates in an optimal state;

The high-efficiency execution control module is connected with the real-time state monitoring module and the self-learning feedback module and is used for implementing an accurate control strategy and dynamically adjusting key operation parameters;

And the self-learning feedback module is connected with the intelligent optimization decision module and is used for continuously monitoring and learning the running condition and optimizing and adjusting the control strategy.

Preferably, the adaptive data acquisition module includes:

the dynamic sampling unit is used for dynamically adjusting the sampling frequency and the sampling range according to the running state and the load change of the unit;

The multi-source data fusion unit is used for combining various sensor data to realize comprehensive monitoring of key parameters;

And the intelligent preprocessing unit is used for cleaning and processing the original data through an adaptive filtering and noise suppression algorithm.

Preferably, the real-time status monitoring module includes:

A state estimation unit for estimating a real-time operation state of the machine set using a kalman filtering and particle filtering method;

an anomaly detection unit for detecting anomalies in real time using a statistical method and a machine learning model;

And the change identification unit is used for identifying the change of the load and the working condition based on the change point detection algorithm.

Preferably, the intelligent optimization decision module includes:

The self-adaptive optimization unit is used for designing a self-adaptive dynamic programming algorithm to optimize a sliding pressure control strategy in real time;

A multi-objective optimization unit for simultaneously considering a heat rate, a power generation efficiency, and a plurality of objectives of emission and optimizing using an evolutionary algorithm;

And the online learning unit is used for continuously updating the optimization model by utilizing real-time data in combination with the deep reinforcement learning.

Preferably, the efficient execution control module includes:

the self-adaptive PID control unit is used for designing a model-based self-adaptive PID controller to dynamically adjust control parameters;

a fuzzy logic control unit for optimizing the adjustment of the main vapor pressure in combination with the fuzzy logic processing nonlinearity and uncertainty;

a coordination control unit for implementing cooperative optimization of the boiler, the steam turbine and the generator through a multivariable control strategy;

And the block chain verification unit is used for carrying out distributed storage and verification of the control instructions through a block chain technology.

Preferably, the self-learning feedback module includes:

A reinforcement learning unit for constantly optimizing a control strategy through analysis and learning of the operation data;

A data-driven modeling unit for constructing a data-driven unit operation model using a big data analysis technique and a machine learning algorithm;

and the intelligent diagnosis unit is used for intelligently diagnosing and processing the abnormality and the fault by combining an expert system and a digital twin technology.

Preferably, the dynamic sampling frequency adjustment formula in the dynamic sampling unit is:

Wherein, the method comprises the steps of, wherein, Is the sampling frequency of the time t,Is the initial sampling frequency at which the sample is to be taken,Is the sampling frequency adjustment coefficient and,Is the pressure change over the time t and,Is the reference pressure value.

Preferably, the adaptive dynamic programming optimization formula in the adaptive optimization unit combines the instant cost and the future expected cost to optimize the control strategy, and the formula is as follows:

Wherein, the method comprises the steps of, wherein, Is a function of the optimal value of the dynamic s,Is the instantaneous cost of state s and dynamic u,Is a discount factor that is used to determine the discount,Is to transition to state after action u is taken at state sIs a probability of (2).

Preferably, the adaptive PID control parameter adjustment formula in the adaptive PID control unit is:

)

=(1+

) Wherein, the method comprises the steps of, wherein, 、、Proportional, integral and differential gains of time t respectively,、、Is the initial gain of the gain control unit,、、Is the gain adjustment coefficient and e (t) is the error value for time t.

Preferably, the self-adaptive PID control unit relates to a dynamic sliding pressure set value adjusting formula, which mainly dynamically adjusts the sliding pressure set value according to load and running state, and ensures that the unit runs under the optimal working condition, and the formula is as follows:

Wherein, the method comprises the steps of, wherein, Is the slide pressure set point at time t,Is the reference sliding pressure value, the sliding pressure value is the reference sliding pressure value,Is the slip pressure adjustment coefficient, L (t) is the load at time t,Is the reference load.

Working principle: when the unit is started, the self-adaptive data acquisition module immediately starts to work. The module adjusts the frequency and the range of data acquisition according to the current load and the running state through the dynamic sampling unit so as to ensure the real-time performance and the accuracy of the acquired data. The multi-source data fusion unit receives data from various sensors and comprehensively processes the data so as to ensure the integrity and the accuracy of the data. Then, the intelligent preprocessing unit cleans and processes the original data through the self-adaptive filtering and noise suppression algorithm to remove noise and abnormal values, so that the data quality is ensured. These preprocessed data are transmitted to the real-time status monitoring module.

And after the real-time state monitoring module receives the processed data, the state estimation unit estimates the running state of the unit in real time by using a Kalman filtering and particle filtering method. The abnormality detection unit detects abnormal conditions in the data in real time through a statistical method and a machine learning model and alarms in time. When an abnormality or a state change is detected, the change recognition unit recognizes and records a change in load and operating conditions based on a change point detection algorithm. The processed state information and the abnormality detection result are transmitted to an intelligent optimization decision module and a high-efficiency execution control module.

And after the intelligent optimization decision module receives the state information, the self-adaptive optimization unit applies a self-adaptive dynamic programming algorithm according to the information to optimize the sliding pressure control strategy in real time. The multi-objective optimization unit comprehensively considers the heat consumption rate, the power generation efficiency and the emission objective, and optimizes the power generation efficiency and the emission objective through an evolutionary algorithm. The online learning unit is combined with the deep reinforcement learning method, and the real-time data is utilized to continuously update and improve the optimization model, so that the accuracy and the instantaneity of the optimization strategy are ensured. The generated optimal control strategy is transmitted to an efficient execution control module.

After the high-efficiency execution control module receives the optimization control strategy, the self-adaptive PID control unit dynamically adjusts parameters of the PID controller according to the real-time error. The fuzzy logic control unit processes the nonlinearity and uncertainty of the system, performs finer adjustment, and optimizes the adjustment of the main steam pressure. The coordination control unit cooperatively optimizes the operation of the boiler, the steam turbine and the generator through a multivariable control strategy, and ensures coordination and optimization of all parts. The block chain verification unit performs distributed storage and verification of control instructions through a block chain technology, and ensures the safety and non-tamper property of data. Meanwhile, the high-efficiency execution control module dynamically adjusts the sliding pressure set value according to the real-time load and the running state so as to ensure that the unit runs in the optimal state under different loads. The execution result and feedback information are transmitted to a self-learning feedback module and a real-time status monitoring module.

After receiving the execution result and feedback information from the learning feedback module, the data are analyzed and learned by the reinforcement learning unit, so that the control strategy is continuously optimized. The data-driven modeling unit builds and updates the unit operation model by using big data analysis and machine learning technology. The intelligent diagnosis unit is combined with an expert system and a digital twin technology to carry out intelligent diagnosis and treatment on the abnormality and the fault. The optimized model and strategy information are transmitted back to the intelligent optimization decision module to form closed loop feedback, so that the system can be ensured to be continuously optimized under different running states and loads.

The invention provides a self-adaptive adjustment unit sliding pressure optimizing operation control system. The beneficial effects are as follows:

1. According to the intelligent optimization decision module, the self-adaptive dynamic planning algorithm and the multi-objective optimization algorithm are combined, the sliding pressure control strategy is optimized in real time, the heat consumption rate, the power generation efficiency and the emission objective are comprehensively considered, the optimal overall operation effect is ensured, and the problems that the optimization decision in the prior art cannot be always adjusted in real time, the optimization objective is single, and comprehensive consideration is lacking are solved.

2. According to the invention, through the high-efficiency execution control module and the adoption of self-adaptive PID control and fuzzy logic control, the control parameters are dynamically adjusted, so that the accurate control and the dynamic adjustment of the operation parameters are realized, the unit is ensured to operate in an optimal state, and the problems of insufficient accuracy and dynamic adjustment capability of the control strategy execution in the prior art are solved.

3. The invention uses reinforcement learning and data driving modeling through a self-learning feedback module, continuously optimizes the control strategy, combines an expert system and a digital twin technology, performs intelligent diagnosis and treatment on abnormality and fault, improves the self-adaptive capacity and the optimizing effect of the system, and solves the problems that in the prior art, the optimizing and adjusting capacity of the control strategy is limited and is difficult to adapt to complex and changeable operation conditions.

Drawings

FIG. 1 is a frame diagram of a system of the present invention;

FIG. 2 is a block diagram of an adaptive data acquisition module according to the present invention;

FIG. 3 is a block diagram of a real-time status monitoring module according to the present invention;

FIG. 4 is a block diagram of an intelligent optimization decision module of the present invention;

FIG. 5 is a block diagram of an efficient execution control module according to the present invention;

fig. 6 is a frame diagram of the self-learning feedback module of the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made more apparent and fully hereinafter with reference to the accompanying drawings, in which some, but not all embodiments of the invention are shown. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

Referring to fig. 1, an embodiment of the present invention provides a self-adaptively adjusted unit sliding pressure optimizing operation control system, including:

The self-adaptive data acquisition module is used for acquiring and preprocessing the operation data of the set in a high-precision and multi-dimensional manner;

The real-time state monitoring module is connected with the self-adaptive data acquisition module and is used for dynamically monitoring and estimating the running state of the unit and detecting the abnormality and the change in real time;

the intelligent optimization decision module is connected with the high-efficiency execution control module and is used for making and optimizing a sliding pressure control strategy so that the unit operates in an optimal state;

The high-efficiency execution control module is connected with the real-time state monitoring module and the self-learning feedback module and is used for implementing an accurate control strategy and dynamically adjusting key operation parameters;

And the self-learning feedback module is connected with the intelligent optimization decision module and is used for continuously monitoring and learning the running condition and optimizing and adjusting the control strategy.

Referring to fig. 2, the adaptive data acquisition module includes:

the dynamic sampling unit is used for dynamically adjusting the sampling frequency and the sampling range according to the running state and the load change of the unit;

The multi-source data fusion unit is used for combining various sensor data to realize comprehensive monitoring of key parameters;

And the intelligent preprocessing unit is used for cleaning and processing the original data through an adaptive filtering and noise suppression algorithm.

The dynamic sampling frequency adjustment formula in the dynamic sampling unit is as follows:

Wherein, the method comprises the steps of, wherein, Is the sampling frequency of the time t,Is the initial sampling frequency at which the sample is to be taken,Is the sampling frequency adjustment coefficient and,Is the pressure change over the time t and,Is the reference pressure value.

Specifically, the dynamic sampling unit improves the real-time performance and accuracy of data acquisition, and can timely reflect the running state and load change of the unit.

According to the real-time running state and load change of the unit, the sampling frequency and the sampling range are dynamically adjusted, and timeliness and accuracy of collected data are ensured.

The unit adjusts the sampling frequency and the sampling range in real time by monitoring the running state and the load change of the unit. Specifically, when the load of the unit is greatly changed or the running state is obviously changed, the dynamic sampling unit can increase the sampling frequency, otherwise, the sampling frequency is reduced, so that resources are saved and the effectiveness of data is ensured.

Dynamic sampling frequency adjustment formula: Wherein, the method comprises the steps of, wherein, Is the sampling frequency of the time t,Is the initial sampling frequency at which the sample is to be taken,Is the sampling frequency adjustment coefficient and,Is the pressure change over the time t and,Is the reference pressure value.

The multisource data fusion unit enhances the integrity and reliability of data, avoids errors of single sensor data and improves monitoring precision.

The method combines various sensor data to comprehensively monitor key parameters of the unit and provide accurate running state information.

The unit eliminates errors from a single data source by fusing data from different sensors. The data of each sensor are combined into one comprehensive data after being weighted, so that the monitoring accuracy is improved.

The data fusion formula: x (t) =

Wherein:

x (t) is the fusion data at time t, N is the number of sensors, Is the data weight of the ith sensor at time t,Is the data of the ith sensor at time t.

The intelligent preprocessing unit improves the data quality, reduces the influence of noise and abnormal data, and ensures the accuracy of subsequent analysis and control.

The method is characterized in that collected original data is cleaned and processed through an adaptive filtering and noise suppression algorithm, and noise and abnormal values are removed.

The unit utilizes the self-adaptive filtering algorithm to automatically adjust the filtering parameters according to the change condition of the real-time data and optimize the data smoothing effect. Meanwhile, the noise suppression algorithm can identify and remove noise and abnormal values in the data, and the effectiveness and reliability of the data are improved.

An adaptive filtering formula:(t)x(t)+(1-

wherein: Is the filtered data at time tt, α (t) is the adaptive filter coefficient at time t, and x (t) is the original data at time t.

The high-precision multi-dimensional unit operation data acquisition and preprocessing are realized through the cooperative work of the dynamic sampling unit, the multi-source data fusion unit and the intelligent preprocessing unit of the self-adaptive data acquisition module, and the real-time performance, the accuracy and the reliability of the data are improved. The method provides a solid data base for subsequent real-time state monitoring, intelligent optimization decision and efficient execution control, and ensures that the system can keep an optimal running state under various working conditions.

Referring to fig. 3, the real-time status monitoring module includes:

A state estimation unit for estimating a real-time operation state of the machine set using a kalman filtering and particle filtering method;

an anomaly detection unit for detecting anomalies in real time using a statistical method and a machine learning model;

And the change identification unit is used for identifying the change of the load and the working condition based on the change point detection algorithm.

Specifically, the state estimation unit provides high-precision real-time operation state estimation, so that the monitoring capability of the system is enhanced, and the stable operation of the unit is ensured.

The method utilizes Kalman filtering and particle filtering methods to estimate the running state of the unit in real time and provides accurate state information for subsequent processing and decision.

And processing the sensor data of the unit by a Kalman filtering method and a particle filtering method, and estimating the current running state of the unit. Kalman filtering is applicable to linear systems, while particle filtering is used to deal with nonlinear and non-Gaussian systems. The combination of the two may provide a more accurate state estimate.

Kalman filtering formula:

and a prediction step:

2. Updating:

particle filter formula:

initializing particles:

particle prediction:

3. Particle weighting:

4. Particle resampling:

the abnormality detection unit timely discovers and pre-warns abnormal conditions, prevents fault expansion and improves the safety and reliability of unit operation.

And detecting abnormal conditions in the operation data in real time by using a statistical method and a machine learning model, identifying potential faults and anomalies, and sending out early warning in time.

The anomaly detection unit analyzes real-time data through a statistical method (such as Z-score) and a machine learning model (such as an isolated forest, a support vector machine and the like) to detect anomaly. The system will alert when the data deviates from the normal range or mode.

The change identification unit accurately identifies the change of the load and the working condition, and timely adjusts the control strategy to ensure the high-efficiency operation of the unit.

Based on a change point detection algorithm, the change of the load and the working condition of the unit is identified, and change information is provided for optimization decision and control adjustment.

The change identification unit analyzes the real-time data stream through a change point detection algorithm (such as CUSUM, pettitt test and the like) and detects the change point of the data, thereby identifying the change of the load and the working condition.

The high-precision estimation, the real-time abnormality detection and the load change identification of the running state of the unit are realized through the cooperative work of the state estimation unit, the abnormality detection unit and the change identification unit of the real-time state monitoring module. The functions provide accurate state information and early warning capability for intelligent optimization decision and efficient execution control of the system, and ensure that the unit can keep efficient and safe operation under various working conditions.

Referring to fig. 4, the intelligent optimization decision module includes:

The self-adaptive optimization unit is used for designing a self-adaptive dynamic programming algorithm to optimize a sliding pressure control strategy in real time;

A multi-objective optimization unit for simultaneously considering a heat rate, a power generation efficiency, and a plurality of objectives of emission and optimizing using an evolutionary algorithm;

And the online learning unit is used for continuously updating the optimization model by utilizing real-time data in combination with the deep reinforcement learning.

The self-adaptive dynamic programming optimization formula in the self-adaptive optimization unit combines the instant cost and the future expected cost to optimize the control strategy, and the formula is as follows:

Wherein, the method comprises the steps of, wherein, Is a function of the optimal value of the dynamic s,Is the instantaneous cost of state s and dynamic u,Is a discount factor that is used to determine the discount,Is to transition to state after action u is taken at state sIs a probability of (2).

Specifically, the self-adaptive optimization unit provides the capability of optimizing the sliding pressure control strategy in real time, and can keep the optimal running state of the unit under complex and changeable running conditions.

And designing a self-adaptive dynamic programming algorithm, optimizing a sliding pressure control strategy in real time, and combining the instant cost and the future expected cost to realize optimal control.

The self-adaptive optimizing unit dynamically optimizes the control strategy by a self-adaptive dynamic programming algorithm on the basis of considering the instant cost and the future expected cost. The algorithm can continuously adjust and optimize the control strategy according to the real-time data, so that the system always maintains the optimal state in the running process.

An adaptive dynamic programming optimization formula: Wherein, the method comprises the steps of, wherein, Is a function of the optimal value of the dynamic s,Is the instantaneous cost of state s and dynamic u,Is a discount factor that is used to determine the discount,Is to transition to state after action u is taken at state sIs a probability of (2).

The multi-objective optimization unit realizes multi-objective comprehensive optimization, and can simultaneously consider the heat rate, the power generation efficiency and the emission objective, thereby ensuring the optimal overall operation effect.

And an evolutionary algorithm is adopted to comprehensively optimize a plurality of targets, so that the balance of heat consumption rate, power generation efficiency and emission targets is realized.

The multi-objective optimization unit performs comprehensive optimization on a plurality of optimization objectives through an evolutionary algorithm (such as NSGA-II). The algorithm can process a plurality of conflict targets and find an optimal balance point, so that the overall operation effect of the unit is optimal.

A multi-objective optimization formula:

minF(x)=[

wherein: f (x) is the vector of the objective function, Is the i-th objective function and m is the number of objective functions.

The online learning unit improves the self-adaptive capacity and the optimization effect of the system, can continuously learn and improve the control strategy, and adapts to the continuously-changing operation working condition.

And by combining deep reinforcement learning, the real-time data is utilized to continuously update the optimization model, so that the self-adaption capability and the optimization effect of the system are enhanced.

The online learning unit continuously updates and optimizes the control model by using real-time data through deep reinforcement learning (such as DQN, DDPG and the like). The unit can continuously improve the control strategy according to the new operation data, and improve the operation performance of the system.

Reinforcement Learning Q-Learning formula:

Q(s,a)[r+

wherein:

q (s, a) is the Q value of state s and action a.

Alpha is the learning rate.

R is the instant prize.

Gamma is the discount factor.

Is the next state.

The intelligent optimization decision module is used for realizing real-time optimization of the sliding pressure control strategy, multi-objective comprehensive optimization and continuous learning improvement control strategy through the cooperative work of the self-adaptive optimization unit, the multi-objective optimization unit and the online learning unit. The self-adaptive optimizing unit optimizes the control strategy in real time through a self-adaptive dynamic programming algorithm; the multi-target optimizing unit realizes the balance of heat consumption rate, power generation efficiency and emission targets through an evolutionary algorithm; the online learning unit continuously updates the optimization model through deep reinforcement learning, and improves the self-adaption capability and the optimization effect of the system. The functions ensure that the unit always maintains the optimal running state under complex and changeable running conditions.

Referring to fig. 5, the efficient execution control module includes:

the self-adaptive PID control unit is used for designing a model-based self-adaptive PID controller to dynamically adjust control parameters;

a fuzzy logic control unit for optimizing the adjustment of the main vapor pressure in combination with the fuzzy logic processing nonlinearity and uncertainty;

a coordination control unit for implementing cooperative optimization of the boiler, the steam turbine and the generator through a multivariable control strategy;

And the block chain verification unit is used for carrying out distributed storage and verification of the control instructions through a block chain technology.

The self-adaptive PID control parameter adjusting formula in the self-adaptive PID control unit is as follows:

)

=(1+

) Wherein, the method comprises the steps of, wherein, 、、Proportional, integral and differential gains of time t respectively,、、Is the initial gain of the gain control unit,、、Is the gain adjustment coefficient and e (t) is the error value for time t.

The self-adaptive PID control unit relates to a dynamic sliding pressure set value adjusting formula, which mainly dynamically adjusts the sliding pressure set value according to the load and the running state, ensures that the unit runs in the optimal working condition, and has the following formula:

Wherein, the method comprises the steps of, wherein, Is the slide pressure set point at time t,Is the reference sliding pressure value, the sliding pressure value is the reference sliding pressure value,Is the slip pressure adjustment coefficient, L (t) is the load at time t,Is the reference load.

Specifically, the self-adaptive PID control unit improves control precision and response speed, can dynamically adapt to the change of the operation working condition, and realizes accurate control of the main steam pressure and the sliding pressure set value.

And designing a model-based self-adaptive PID controller, dynamically adjusting control parameters, and ensuring that the system operates in an optimal state under different working conditions.

Principle of:

The self-adaptive PID control unit dynamically adjusts PID control parameters according to the current system state by monitoring errors in real time, so as to realize accurate adjustment of the control system. The parameter adjustment formula of the PID controller is as follows:

)

=(1+

) Wherein, the method comprises the steps of, wherein, 、、Proportional, integral and differential gains of time t respectively,、、Is the initial gain of the gain control unit,、、Is the gain adjustment coefficient and e (t) is the error value for time t.

Dynamic sliding pressure set value adjustment formula:

Wherein, the method comprises the steps of, wherein, Is the slide pressure set point at time t,Is the reference sliding pressure value, the sliding pressure value is the reference sliding pressure value,Is the slip pressure adjustment coefficient, L (t) is the load at time t,Is the reference load.

The fuzzy logic control unit can solve the problems of nonlinearity and uncertainty, and improves the stability and control effect of the system.

And the nonlinear and uncertainty is processed by combining the fuzzy logic, so that the adjustment of the main steam pressure is optimized, and the stable operation of the system is ensured.

Principle of:

And the fuzzy logic control unit performs fuzzy reasoning and decision making according to the current system state and the operation parameters by using the fuzzy set and the fuzzy rule, and optimizes the control of the main steam pressure.

Fuzzy control rule formula: u=

Wherein:

u is the control output.

Is the weight of the ith rule.

Is the membership of input x to the ith rule.

The coordination control unit realizes the cooperative optimization of the boiler, the steam turbine and the generator, and improves the overall operation efficiency and stability.

Through a multivariable control strategy, the coordinated control and optimization of the boiler, the steam turbine and the generator are realized, and the cooperative work of all parts is ensured.

Principle of:

the coordination control unit utilizes a multivariable control strategy to comprehensively consider the running states and the demands of all parts, and realizes cooperative control through an optimization algorithm.

Coordination control optimization formula:

minJ=

wherein:

J is the objective function.

Is a weight coefficient.

Is an operational status function of the ith subsystem.

The block chain verification unit improves the safety and the non-falsifiability of the control instruction, and ensures the running reliability of the system and the integrity of data.

Distributed storage and verification of control instructions is performed through a blockchain technology, and data tampering and unauthorized modification are prevented.

Principle of:

The block chain verification unit stores the control instructions and the running data in the distributed account book in the form of blocks, and ensures the security and the non-tamper property of the data through a consensus mechanism and an encryption technology.

Block chain consensus formula: h%

Wherein:

H( Is the hash value of block i.

Is the previous block.

Is the data of the current block.

The accurate control and dynamic adjustment of the unit operation parameters are realized through the cooperative work of the self-adaptive PID control unit, the fuzzy logic control unit, the coordination control unit and the block chain verification unit of the high-efficiency execution control module. The self-adaptive PID control unit ensures the system to operate in an optimal state by dynamically adjusting PID parameters and a sliding pressure set value; the fuzzy logic control unit processes nonlinearity and uncertainty and optimizes control of the main steam pressure; the coordination control unit realizes the cooperative optimization of the boiler, the steam turbine and the generator; the blockchain verification unit ensures the security and non-tamper resistance of the control instruction. Together, the functions ensure the efficient and stable operation of the unit under various working conditions.

Referring to fig. 6, the self-learning feedback module includes:

A reinforcement learning unit for constantly optimizing a control strategy through analysis and learning of the operation data;

A data-driven modeling unit for constructing a data-driven unit operation model using a big data analysis technique and a machine learning algorithm;

and the intelligent diagnosis unit is used for intelligently diagnosing and processing the abnormality and the fault by combining an expert system and a digital twin technology.

Specifically, the reinforcement learning unit continuously optimizes the control strategy, improves the self-adaptive capacity and the running efficiency of the system, and ensures that the system can keep the optimal state under different working conditions.

Through analysis and learning of operation data, a reinforcement learning algorithm is utilized to continuously optimize a control strategy, and the response capability and the optimization effect of the system are improved.

Principle of:

The reinforcement learning unit learns the optimal control strategy from historical and real-time data using reinforcement learning algorithms (e.g., Q-learning, deep Q-network DQN, etc.). Algorithms continually adjust policies to maximize long-term return through rewards and penalty mechanisms.

The data driving modeling unit builds a high-precision unit operation model, improves the accuracy of prediction and optimization, and enhances the intelligent and fine management capability of the system.

And constructing and updating a data-driven unit operation model by utilizing a big data analysis technology and a machine learning algorithm, and providing a reliable data basis for optimization decision.

Principle of:

The data-driven modeling unit builds a unit operation model using machine learning algorithms (e.g., regression analysis, neural networks, etc.) by collecting and analyzing a large amount of historical operation data. The models can capture complex dynamic characteristics of the system and provide support for real-time optimization and control.

The intelligent diagnosis unit improves the accuracy and timeliness of fault diagnosis, reduces the fault processing time and the maintenance cost, and enhances the reliability and the safety of the system.

And the expert system and the digital twin technology are combined to carry out intelligent diagnosis and treatment on the abnormality and the fault, and accurate fault positioning and diagnosis results are provided.

Principle of:

The intelligent diagnosis unit establishes a virtual machine set model by utilizing rules and a knowledge base of an expert system and combining a digital twin technology. By comparing the actual operation data with the virtual model, the abnormality and the fault are found in time, and intelligent diagnosis and treatment are performed.

Continuous optimization, accurate modeling and intelligent diagnosis of a system control strategy are realized through cooperative work of a reinforcement learning unit, a data driving modeling unit and an intelligent diagnosis unit of the self-learning feedback module. The reinforcement learning unit is used for continuously optimizing a control strategy by analyzing the operation data, so that the self-adaptive capacity of the system is improved; the data-driven modeling unit utilizes big data analysis and machine learning to construct a high-precision operation model, and provides a reliable prediction and optimization basis; the intelligent diagnosis unit is combined with an expert system and a digital twin technology to carry out intelligent diagnosis and treatment on the abnormality and the fault, so that the reliability and the safety of the system are improved. Together, the functions ensure the efficient and stable operation of the unit under various working conditions.

Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

Claims (10)

1. An adaptively adjusted unit sliding pressure optimizing operation control system, comprising:

The self-adaptive data acquisition module is used for acquiring and preprocessing the operation data of the set in a high-precision and multi-dimensional manner;

The real-time state monitoring module is connected with the self-adaptive data acquisition module and is used for dynamically monitoring and estimating the running state of the unit and detecting the abnormality and the change in real time;

the intelligent optimization decision module is connected with the high-efficiency execution control module and is used for making and optimizing a sliding pressure control strategy so that the unit operates in an optimal state;

The high-efficiency execution control module is connected with the real-time state monitoring module and the self-learning feedback module and is used for implementing an accurate control strategy and dynamically adjusting key operation parameters;

And the self-learning feedback module is connected with the intelligent optimization decision module and is used for continuously monitoring and learning the running condition and optimizing and adjusting the control strategy.

2. The adaptively adjusted unit slide optimization run control system of claim 1, wherein the adaptive data acquisition module comprises:

the dynamic sampling unit is used for dynamically adjusting the sampling frequency and the sampling range according to the running state and the load change of the unit;

The multi-source data fusion unit is used for combining various sensor data to realize comprehensive monitoring of key parameters;

And the intelligent preprocessing unit is used for cleaning and processing the original data through an adaptive filtering and noise suppression algorithm.

3. The adaptively adjusted unit skid optimal operation control system as set forth in claim 1, wherein said real-time status monitoring module comprises:

A state estimation unit for estimating a real-time operation state of the machine set using a kalman filtering and particle filtering method;

an anomaly detection unit for detecting anomalies in real time using a statistical method and a machine learning model;

And the change identification unit is used for identifying the change of the load and the working condition based on the change point detection algorithm.

4. The adaptively adjusted unit slide optimization operation control system according to claim 1, wherein the intelligent optimization decision module comprises:

The self-adaptive optimization unit is used for designing a self-adaptive dynamic programming algorithm to optimize a sliding pressure control strategy in real time;

A multi-objective optimization unit for simultaneously considering a heat rate, a power generation efficiency, and a plurality of objectives of emission and optimizing using an evolutionary algorithm;

And the online learning unit is used for continuously updating the optimization model by utilizing real-time data in combination with the deep reinforcement learning.

5. The adaptively adjusted unit slide optimization run control system of claim 1, wherein said high efficiency execution control module comprises:

the self-adaptive PID control unit is used for designing a model-based self-adaptive PID controller to dynamically adjust control parameters;

a fuzzy logic control unit for optimizing the adjustment of the main vapor pressure in combination with the fuzzy logic processing nonlinearity and uncertainty;

a coordination control unit for implementing cooperative optimization of the boiler, the steam turbine and the generator through a multivariable control strategy;

And the block chain verification unit is used for carrying out distributed storage and verification of the control instructions through a block chain technology.

6. The adaptively adjusted unit slide optimization operation control system according to claim 1, wherein the self-learning feedback module comprises:

A reinforcement learning unit for constantly optimizing a control strategy through analysis and learning of the operation data;

A data-driven modeling unit for constructing a data-driven unit operation model using a big data analysis technique and a machine learning algorithm;

and the intelligent diagnosis unit is used for intelligently diagnosing and processing the abnormality and the fault by combining an expert system and a digital twin technology.

7. The adaptively adjusted unit sliding pressure optimizing operation control system according to claim 2, wherein the dynamic sampling frequency adjustment formula in the dynamic sampling unit is:

Wherein, the method comprises the steps of, wherein, Is the sampling frequency of the time t,Is the initial sampling frequency at which the sample is to be taken,Is the sampling frequency adjustment coefficient and,Is the pressure change over the time t and,Is the reference pressure value.

8. The adaptively adjusted unit sliding pressure optimizing operation control system according to claim 4, wherein the adaptive dynamic programming optimizing formula in the adaptive optimizing unit combines the instant cost and the future expected cost to optimize the control strategy, and the formula is:

Wherein, the method comprises the steps of, wherein, Is a function of the optimal value of the dynamic s,Is the instantaneous cost of state s and dynamic u,Is a discount factor that is used to determine the discount,Is to transition to state after action u is taken at state sIs a probability of (2).

9. The adaptively adjusted unit sliding pressure optimizing operation control system according to claim 5, wherein the adaptive PID control parameter adjustment formula in the adaptive PID control unit is:

)

=(1+

) Wherein, the method comprises the steps of, wherein, 、、Proportional, integral and differential gains of time t respectively,、、Is the initial gain of the gain control unit,、、Is the gain adjustment coefficient and e (t) is the error value for time t.

10. The adaptively adjusted unit sliding pressure optimizing operation control system according to claim 5, wherein the adaptive PID control unit relates to a dynamic sliding pressure set value adjusting formula, which mainly dynamically adjusts the sliding pressure set value according to the load and the operation state, so as to ensure that the unit operates under the optimal working condition, and the formula is as follows:

Wherein, the method comprises the steps of, wherein, Is the slide pressure set point at time t,Is the reference sliding pressure value, the sliding pressure value is the reference sliding pressure value,Is the slip pressure adjustment coefficient, L (t) is the load at time t,Is the reference load.