Temperature and pressure intelligent adjusting method and system for thermal power plant

Abstract

The invention relates to the technical field of thermal power plant parameter regulation and control, in particular to an intelligent temperature and pressure regulation method and system for a thermal power plant, and the method comprises the following steps: collecting temperature, pressure and flow data based on heat transfer and flow channels among a boiler, a steam turbine, a condenser and heat exchanger equipment in the thermal power plant; constructing a network structure representing interaction between devices, evaluating heat exchange characteristics of nodes, and constructing heat flow path structure matrix information; according to the method, the complex interaction among the boiler, the steam turbine, the condenser and the heat exchanger equipment is accurately quantified by constructing the heat flow path network structure among the equipment and evaluating the heat exchange characteristics of the nodes. Thermal inertia feedback matrix information is introduced, and transient changes of temperature and pressure are monitored in real time, so that delay and inertia effects in heat transfer and fluid flowing between equipment can be more accurately captured, and the response speed and precision to different loads and working conditions are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of parameter control in thermal power plants, and in particular to a method and system for intelligently adjusting temperature and pressure in thermal power plants. Background Art

[0002] The field of thermal power plant parameter control involves the monitoring and control of various key parameters in the operation of thermal power plants, including the automatic adjustment and optimization management of variables such as temperature, pressure, flow, combustion, fuel delivery, etc. With the development of industrial automation and intelligent control technology, the parameter control of thermal power plants can achieve precise control and optimization of various operating parameters through sensors, control algorithms, real-time data analysis and feedback mechanisms.

[0003] Among them, the temperature and pressure intelligent adjustment method used in thermal power plants is a specific application of thermal power plant parameter control technology. It accurately adjusts the temperature and pressure of equipment such as boilers and steam turbines according to the real-time operating conditions of the thermal power plant, enabling the system to operate under optimal operating conditions, thereby improving power generation efficiency and reducing fuel consumption and environmental pollution.

[0004] The existing technology mainly relies on direct feedback control of real-time parameters of equipment such as boilers and steam turbines in regulating temperature and pressure in thermal power plants. When faced with complex interactions between equipment, it is difficult to fully consider the inertia and delay effects in the heat exchange process, resulting in the system's regulation response not being timely and accurate when the load fluctuates or the operating conditions change. In addition, the existing technology is prone to large temperature and pressure fluctuations under high load or transient changes, and there is instability. Although the existing technology can be adjusted by monitoring temperature and pressure parameters, it is difficult to accurately identify the heat transfer mode and pressure loss between equipment. The regulation process ignores the transient response under the current complex dynamic conditions, resulting in reduced system energy efficiency, increased equipment wear, and increased fuel consumption and operating costs. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a temperature and pressure intelligent regulation method and system for a thermal power plant.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a temperature and pressure intelligent regulation method for a thermal power plant, comprising the following steps:

[0007] S1: Based on the heat transfer and flow channels between boilers, turbines, condensers, and heat exchangers in thermal power plants, collect temperature, pressure, and flow data, build a network structure representing the interaction between devices, evaluate the heat exchange characteristics of nodes, and build heat flow path structure matrix information;

[0008] S2: Analyze the influence of boiler output steam on the steam turbine and the heat exchanger according to the heat flow path structure matrix information, monitor the feedback data of the condenser water flow, evaluate the response characteristics under various loads and working conditions, and generate thermal inertia feedback matrix information;

[0009] S3: Analyze the influence of transient changes in temperature and pressure on heat exchange and flow patterns among the boiler, the steam turbine and the condenser according to the thermal inertia feedback matrix information, predict the temperature and pressure change trends, and generate transient temperature and pressure change trend prediction results;

[0010] S4: Based on the transient temperature and pressure change trend prediction results, a probability distribution model is established to identify the degree of uncertainty of the equipment under each load state and generate an optimized parameter set for working condition adaptability;

[0011] S5: According to the working condition adaptability optimization parameter set and the transient temperature and pressure change trend prediction result, the real-time data is compared with the change range of the transient trend prediction, and an adjustment instruction is generated according to the deviation to obtain a dynamic control instruction set;

[0012] S6: According to the dynamic control instruction set, the combustion rate of the boiler, the steam valve of the turbine, the water pump flow of the condenser and the fluid flow rate of the heat exchanger are linked to adjust to obtain the real-time control result of temperature and pressure linkage.

[0013] The present invention has improvements in that the heat flow path structure matrix information includes the connection relationship of the heat exchange paths between devices, the direction matrix of the fluid flow and the temperature difference data between the devices; the thermal inertia feedback matrix information includes the thermal delay time of the equipment, the heat capacity change and the heat transfer efficiency coefficient; the transient temperature and pressure change trend prediction results include the temperature change rate, the amplitude of the pressure increase or decrease, and the fluid flow pattern change under the transient response; the operating condition adaptability optimization parameter set includes the optimal combustion rate adjustment range of the boiler, the adjustment ratio of the turbine steam flow and the optimization coefficient of the condenser water flow; the dynamic control instruction set includes real-time adjustment of the boiler combustion rate, adjustment of the opening of the turbine steam valve and control of the flow of the condenser water pump; the temperature and pressure linkage real-time control result includes the dynamic correction of the heat exchange rate between the synchronous adjustment boiler, the turbine, the condenser and the heat exchanger.

[0014] The present invention is improved in that, based on the heat transfer and flow channels between boilers, turbines, condensers, and heat exchangers in thermal power plants, temperature, pressure, and flow data are collected to construct a network structure representing the interaction between devices, and the heat exchange characteristics of the nodes are evaluated. The specific steps of constructing the heat flow path structure matrix information are as follows:

[0015] S101: Based on the heat transfer and flow channels between boilers, turbines, condensers and heat exchangers, collect temperature, pressure and flow data, classify and organize the data, generate a network connection structure according to device nodes, mark the interactions between devices, and generate a device interaction network;

[0016] S102: Based on the equipment interaction network, according to the heat exchange characteristics of the boiler pipe, the turbine blade, and the condenser inlet node, the flow direction and the heat transfer path of the fluid are analyzed, the heat flow direction is marked and the path is confirmed, and the flow and heat transfer path information is generated;

[0017] S103: Based on the flow and heat transfer path information, by analyzing the temperature difference and pressure information of the device nodes, a heat exchange path between nodes and a node connection matrix are constructed, and the heat flow relationship between devices is structured in combination with the heat transfer path to generate heat flow path structure matrix information.

[0018] The present invention is improved in that, according to the heat flow path structure matrix information, the influence of the boiler output steam on the steam turbine and the heat exchanger is analyzed, and the feedback data of the condenser water flow is monitored at the same time, and the response characteristics under various loads and working conditions are evaluated. The specific steps of generating the thermal inertia feedback matrix information are as follows:

[0019] S201: Based on the heat flow path structure matrix information, calculate the flow rate and pressure changes of the boiler output steam to the turbine and the heat exchanger, analyze the pressure loss of the steam in the flow, determine the steam loss by comparing the flow rate and pressure, and generate steam flow rate and pressure loss data;

[0020] S202: Based on the steam flow rate and pressure loss data, analyzing the feedback data of the condenser water flow, combining the heat capacity and heat transfer coefficient between the devices, evaluating the delay and response of the fluid flow, calibrating the device response time, and generating the device heat transfer and flow feedback information;

[0021] S203: Based on the heat transfer and flow feedback information of the equipment, by analyzing the heat transfer delay data between equipment nodes, analyzing the thermal inertia response caused by load changes, and matrixing by accumulating load and thermal inertia parameters to generate thermal inertia feedback matrix information.

[0022] The present invention is improved in that, according to the thermal inertia feedback matrix information, the influence of transient changes of temperature and pressure on the heat exchange and flow pattern between the boiler, the turbine and the condenser is analyzed, and the temperature and pressure change trends are predicted. The specific steps of generating the transient temperature and pressure change trend prediction results are as follows:

[0023] S301: Based on the thermal inertia feedback matrix information, referring to the temperature and pressure data between the current boiler, steam turbine, condenser, and heat exchanger, the transient change data is classified and marked, the transient response during load change and cooling failure is extracted, and transient temperature and pressure change data is generated;

[0024] S302: Based on the transient temperature and pressure change data, analyze the impact of transient changes in temperature and pressure on heat exchange and flow patterns between the boiler, the turbine and the condenser, extract influencing factors by comparing the change trend with historical data, and generate heat exchange pattern change information;

[0025] S303: Based on the heat exchange mode change information, analyze the temperature and pressure change trends, calculate the predicted value under each working condition, and compare it with the current data to predict the future temperature and pressure change trends and generate transient temperature and pressure change trend prediction results.

[0026] The present invention is improved in that, according to the transient temperature and pressure change trend prediction results, a probability distribution model is established to identify the uncertainty degree of the equipment under each load state, and the specific steps of generating a working condition adaptability optimization parameter set are as follows:

[0027] S401: Based on the transient temperature and pressure change trend prediction result, the temperature, pressure and flow data of the boiler, steam turbine, condenser and heat exchanger are screened and classified according to the working conditions, and key data points are extracted according to the corresponding working conditions. The key data points are the temperature change rate, pressure fluctuation amplitude and flow peak value, and the working condition data set is generated;

[0028] S402: Based on the working condition data set, a state model is established for each working condition, input and output conditions of each working condition are set through the model structure, key data points are input, the entropy value of the equipment in the current state is analyzed, uncertainty information in working condition fluctuations is extracted, and abnormal information of the load state is generated;

[0029] S403: Based on the abnormal information of the load state, analyze the influence of the temperature, pressure and flow parameters of the equipment under each working condition on the operating efficiency and stability of the equipment itself, extract the optimal operating parameters under the load and working condition, and generate a working condition adaptability optimization parameter set.

[0030] The present invention is improved in that, for the entropy value of the analysis device in the current state, the formula is adopted:

[0031]

[0032] Calculate the entropy value S of the current state of the device;

[0033] Among them, q i is the probability distribution of the i-th feature data point, T iis the temperature change rate of the i-th characteristic data point, X i is the pressure fluctuation amplitude of the i-th characteristic data point, F i is the traffic peak value of the i-th feature data point, and n is the total number of feature data points.

[0034] The present invention is improved in that, according to the working condition adaptability optimization parameter set and the transient temperature and pressure change trend prediction result, the real-time data is compared with the change amplitude of the transient trend prediction, and the adjustment instruction is generated according to the deviation situation. The specific steps of obtaining the dynamic control instruction set are as follows:

[0035] S501: Based on the operating condition adaptability optimization parameter set and the transient temperature and pressure change trend prediction result, read the real-time temperature, pressure and flow data of the boiler, steam turbine, condenser and heat exchanger, summarize them by time and equipment classification, and generate real-time equipment status data;

[0036] S502: Based on the real-time equipment status data, the real-time temperature, pressure, and flow are compared with the transient temperature and pressure change trend prediction results, and the anomalies and deviations in equipment operation are identified by calculating the deviation values ​​of temperature, pressure, and flow, and equipment deviation information is generated;

[0037] S503: Based on the equipment deviation information, analyze the degree of deviation of temperature, pressure and flow of each device, and determine the upper and lower limits of the adjustment parameters according to the equipment performance standards, which are the safe temperature range of the equipment, the maximum and minimum pressure values ​​that the equipment can withstand, the minimum and maximum flow rates when the equipment is running, and the reaction speed of the equipment when adjusting parameters, and generate a dynamic control instruction set.

[0038] The present invention is improved in that, according to the dynamic control instruction set, the combustion rate of the boiler, the steam valve of the steam turbine, the water pump flow of the condenser and the fluid flow rate of the heat exchanger are linked to adjust the specific steps of obtaining the temperature and pressure linkage real-time control result as follows:

[0039] S601: Based on the dynamic control instruction set, the boiler combustion rate, the turbine steam valve, the condenser water pump flow rate, and the heat exchanger fluid flow rate are adjusted in real time to generate equipment linkage adjustment feedback results;

[0040] S602: Based on the feedback result of the linkage adjustment of the equipment, the temperature and pressure changes are recorded in real time, the response speed and adjustment effectiveness of the equipment are detected, and the temperature and pressure adjustment response data are generated;

[0041] S603: Based on the temperature and pressure adjustment response data, determine whether the temperature and pressure of the equipment return to the preset range, analyze the linkage control effect, perform secondary fine-tuning on the parameters that do not meet expectations, and generate real-time temperature and pressure linkage control results.

[0042] A temperature and pressure intelligent regulation system for a thermal power plant, the system comprising:

[0043] The heat flow path construction module is based on the heat transfer and flow channels between boilers, turbines, condensers, and heat exchangers in thermal power plants. It collects temperature, pressure, and flow data, builds a network structure that reflects the heat exchange and flow characteristics between devices, evaluates the heat exchange characteristics, and generates heat flow path structure matrix information in combination with fluid flow direction and heat transfer path.

[0044] The equipment response evaluation module analyzes the influence of boiler output steam on the steam turbine and the heat exchanger based on the heat flow path structure matrix information, monitors the feedback data of the condenser water flow, combines the heat capacity, heat transfer coefficient and flow delay information between the equipment, evaluates the equipment response characteristics under various loads and working conditions, and generates thermal inertia feedback matrix information;

[0045] The transient change analysis module monitors the temperature and pressure transient changes of the boiler, steam turbine, condenser and heat exchanger in real time based on the thermal inertia feedback matrix information, analyzes the transient response during load fluctuation and cooling failure, predicts the temperature and pressure change trends, and generates transient temperature and pressure change trend prediction results;

[0046] Based on the prediction results of the transient temperature and pressure change trend, the operating condition optimization module classifies the temperature, pressure and flow data of the boiler, steam turbine, condenser and heat exchanger according to the operating conditions, establishes a probability distribution model, identifies the operating uncertainty of the equipment under various load conditions, and generates an operating condition adaptability optimization parameter set;

[0047] Based on the operating condition adaptability optimization parameter set and the transient temperature and pressure change trend prediction results, the linkage control module reads the real-time temperature, pressure and flow data, compares them with the prediction results, identifies the deviation of the current state of the equipment, and linkage-adjusts the boiler combustion rate, turbine steam valve, condenser water pump flow and heat exchanger fluid flow rate to obtain the temperature and pressure linkage real-time control results.

[0048] Compared with the prior art, the advantages and positive effects of the present invention are:

[0049] In the present invention, by constructing a network structure of heat flow paths between devices and evaluating the heat exchange characteristics of nodes, accurate quantification of complex interactions between boilers, turbines, condensers and heat exchangers is achieved. The introduction of thermal inertia feedback matrix information and real-time monitoring of transient changes in temperature and pressure can more accurately capture the delay and inertia effects in heat transfer and fluid flow between devices, and improve the response speed and accuracy to different loads and working conditions. Under high load or changing conditions, the heat exchange mode between each device can be quickly fed back, providing data support for the overall regulation of the system. By predicting transient temperature and pressure changes, combined with the dynamic cumulative effect of thermal inertia when the load changes, it is ensured that the fluctuations in temperature and pressure can be adjusted in real time, reducing the risk of excessive fluctuations. Through the temperature and pressure linkage control between devices, the temperature and pressure control of the system under various working conditions is more efficient and accurate, improving power generation efficiency and reducing equipment wear and energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a flow chart of the present invention;

[0051] Figure 2 This is a detailed flow chart of step S1 of the present invention;

[0052] Figure 3 This is a detailed flow chart of step S2 of the present invention;

[0053] Figure 4 This is a detailed flow chart of step S3 of the present invention;

[0054] Figure 5 This is a detailed flow chart of step S4 of the present invention;

[0055] Figure 6 This is a detailed flow chart of step S5 of the present invention;

[0056] Figure 7 This is a detailed flow chart of step S6 of the present invention;

[0057] Figure 8 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0059] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0060] See also Figure 1 The present invention provides a technical solution: a temperature and pressure intelligent adjustment method for a thermal power plant, comprising the following steps:

[0061] S1: Based on the heat transfer and flow channels between boilers, turbines, condensers, and heat exchangers in thermal power plants, collect temperature, pressure, and flow data, build a network structure representing the interaction between devices, evaluate the heat exchange characteristics of nodes, including boiler pipes, turbine blades, and condenser inlets, calculate the fluid flow direction and heat transfer path, and build the heat flow path structure matrix information;

[0062] S2: Based on the heat flow path structure matrix information, analyze the impact of boiler output steam on the turbine and heat exchanger, calculate the steam flow rate and pressure loss, and monitor the feedback data of the condenser water flow. Combine the heat capacity, heat transfer coefficient and flow delay information between equipment to evaluate various loads, including high load, partial load and low load, and operating conditions, including the response characteristics under startup, stable operation and shutdown. By calculating the heat transfer and fluid flow delay accumulation between equipment nodes, quantify the thermal inertia effect of different links, and generate thermal inertia feedback matrix information;

[0063] S3: Based on the thermal inertia feedback matrix information, the transient change information of temperature and pressure between the boiler, turbine, condenser and heat exchanger is obtained through real-time monitoring, including transient response during load changes and cooling failures, and the impact of transient changes on heat exchange and flow patterns between the boiler, turbine and condenser is analyzed to predict the temperature and pressure change trends and generate transient temperature and pressure change trend prediction results;

[0064] S4: Based on the prediction results of transient temperature and pressure change trends, the temperature, pressure and flow data of boilers, turbines, condensers and heat exchangers under various working conditions are used as input, and a corresponding probability distribution model is established for each working condition. The entropy value of the current state is calculated, the degree of uncertainty of the equipment under each load state is identified, and an optimization parameter set for working condition adaptability is generated;

[0065] S5: According to the working condition adaptability optimization parameter set and the transient temperature and pressure change trend prediction results, read the current temperature, pressure and flow data, compare the real-time data with the change range of the transient trend prediction, identify the deviation of the equipment in the current state, generate adjustment instructions according to the deviation, and obtain a dynamic control instruction set;

[0066] S6: According to the dynamic control instruction set, the combustion rate of the boiler, the steam valve of the turbine, the water pump flow of the condenser and the fluid flow rate of the heat exchanger are adjusted in a linked manner, including automatically increasing the cooling water flow of the condenser when the steam temperature rises, and synchronously adjusting the fluid exchange rate of the heat exchanger to prevent excessive fluctuations in temperature and pressure, and obtain real-time temperature and pressure linkage control results.

[0067] The heat flow path structure matrix information includes the connection relationship of the heat exchange path between devices, the direction matrix of fluid flow and the temperature difference data between devices. The thermal inertia feedback matrix information includes the thermal delay time of the equipment, the change in heat capacity and the heat transfer efficiency coefficient. The transient temperature and pressure change trend prediction results include the temperature change rate, the amplitude of pressure increase or decrease, and the change in fluid flow pattern under transient response. The operating condition adaptability optimization parameter set includes the optimal combustion rate adjustment range of the boiler, the adjustment ratio of the turbine steam flow and the optimization coefficient of the condenser water flow. The dynamic control instruction set includes real-time adjustment of the boiler combustion rate, adjustment of the opening of the turbine steam valve and control of the flow of the condenser water pump. The temperature and pressure linkage real-time control results include the dynamic correction of the heat exchange rate between the synchronous adjustment boiler, turbine, condenser and heat exchanger.

[0068] See also Figure 2 Based on the heat transfer and flow channels between boilers, turbines, condensers, and heat exchangers in thermal power plants, the temperature, pressure, and flow data are collected to build a network structure representing the interaction between devices, evaluate the heat exchange characteristics of the nodes, and build the heat flow path structure matrix information. The specific steps are as follows:

[0069] S101: Based on the heat transfer and flow channels between boilers, turbines, condensers and heat exchangers, collect temperature, pressure and flow data, classify and organize the data, generate a network connection structure according to device nodes, mark the interactions between devices, and generate a device interaction network;

[0070] Based on the heat transfer and flow channels between boilers, turbines, condensers and heat exchangers, the real-time temperature, pressure and flow data of each device node are first obtained through temperature sensors (such as thermocouples), pressure sensors (such as piezoresistive sensors) and flow sensors (such as turbine flowmeters). The sensors are installed at key positions of the equipment, such as the steam outlet of the boiler, the inlet of the turbine blades, and the inlet and outlet of the condenser. The median filtering method is used to eliminate outliers (such as extreme data caused by interference or sensor failure). Then, the data cleaning algorithm is used to classify and organize the collected data, and multiple node data of the same device are merged and sorted in chronological order. Then, the adjacency matrix is ​​used to construct the connection relationship between device nodes, and the network topology structure is generated according to the correlation between the physical connection and function of the equipment. Finally, the interaction between devices is analyzed through graph algorithms (such as BFS or DFS) and the interacting nodes are marked.

[0071] S102: Based on the equipment interaction network, according to the heat exchange characteristics of boiler pipes, turbine blades, and condenser inlet nodes, the flow direction and heat transfer path of the fluid are analyzed, the heat flow direction is marked and the path is confirmed, and the flow and heat transfer path information is generated;

[0072] First, based on the surface heat distribution information of boilers, turbines and condensers detected by infrared thermal imagers, the temperature data of the equipment surface is obtained, and based on the high-temperature resistant thermocouple sensors installed at key positions of pipelines and heat exchangers, the temperature data inside the equipment is obtained in real time. The heat transfer analysis of the equipment is carried out through the collected temperature data, and the temperature distribution diagram of the equipment is drawn using data visualization tools. The hot spots and temperature gradient changes are identified from the diagram, and the heat exchange efficiency between the equipment is evaluated by comparing the temperature change trends of each device. The confirmation of the fluid flow direction is obtained through the ultrasonic flowmeter and differential pressure flowmeter installed at the connection points of the pipeline and the equipment. The differential pressure data is used to determine the pressure difference between the inlet and outlet of the equipment, and then the flow direction of the fluid is derived in combination with the flowmeter data. The numerical simulation tool based on finite element analysis (such as ANSYSFluent) is used to simulate the fluid flow, and the flow path and heat transfer path between the equipment are determined by analyzing the simulation results, and the flow and heat transfer path information is generated and archived.

[0073] S103: Based on the flow and heat transfer path information, by analyzing the temperature difference and pressure information of the device nodes, the heat exchange path between the nodes and the node connection matrix are constructed, and the heat flow relationship between the devices is structurally expressed in combination with the heat transfer path to generate the heat flow path structure matrix information;

[0074] The temperature difference and pressure difference of the equipment are analyzed through the sensor data, and the K-means clustering algorithm is used to perform cluster analysis on the temperature and pressure data, and the heat transfer areas between the equipment are divided. The heat exchange efficiency between the equipment is further evaluated through the heat flow analysis model, and the node connection matrix based on the physical model is used to construct the heat flow relationship between the equipment. Each node in the matrix represents a device, and the node value represents the heat exchange intensity. Finally, the heat flow path between the devices is displayed through the data visualization tool, and the structured heat flow path matrix information is generated and provided to the system for further analysis.

[0075] See also Figure 3 , according to the heat flow path structure matrix information, analyze the impact of boiler output steam on the turbine and heat exchanger, monitor the feedback data of condenser water flow, evaluate the response characteristics under various loads and working conditions, and generate thermal inertia feedback matrix information in the following specific steps:

[0076] S201: Based on the heat flow path structure matrix information, calculate the flow rate and pressure changes of the boiler output steam to the turbine and the heat exchanger, analyze the pressure loss of the steam in the flow, determine the steam loss by comparing the flow rate and pressure, and generate steam flow rate and pressure loss data;

[0077] To calculate the flow rate and pressure change of boiler output steam to the turbine and heat exchanger, the formula is:

[0078]

[0079] Where: ΔP represents pressure loss, in Pascals (Pa), which is the pressure difference measured by the pressure sensors at both ends of the pipeline. f is the friction coefficient, which is calculated by the Reynolds number Re or obtained by looking up the friction coefficient table. The friction coefficient of steam flowing in the pipeline in a thermal power plant depends on the turbulent state of the fluid. L is the pipeline length, in meters (m), which is obtained from the equipment design manual. In thermal power plants, the actual length of the equipment connecting pipeline is generally determined by measurement. D is the inner diameter of the pipeline, in meters (m), which is obtained from the equipment drawings. It represents the width of the steam flow channel and affects the steam flow rate and pressure loss. ρ is the steam density, in kilograms per cubic meter (kg / m3), which is obtained by looking up the table (steam table) or real-time calculation based on the steam temperature and pressure data. v is the steam flow rate, in meters per second (m / s), which is measured by an ultrasonic flowmeter or a turbine flowmeter and represents the flow rate of steam in the pipeline.

[0080] In a thermal power plant, when steam is transported from the boiler to the turbine or heat exchanger, the friction of the pipeline causes pressure loss. First, by measuring the steam flow rate v, the length L and diameter D of the pipeline, and the density ρ of the steam, the pressure loss is calculated using the above formula. The friction coefficient f is determined by the Reynolds number Re of the fluid. The Reynolds number formula is:

[0081]

[0082] Where μ is the dynamic viscosity of steam in Pascal seconds (Pa·s), which can be obtained by looking up the table. By calculating the Reynolds number, the turbulent or laminar state of the fluid can be determined, and the friction coefficient f can be determined by looking up the table. When the Reynolds number is greater than 4000, it means that the fluid is turbulent, and the friction coefficient in the pipeline needs to be found in the turbulent friction coefficient table.

[0083] If the length of the steam pipe from the boiler to the turbine in a thermal power plant is L = 100 meters, the pipe diameter is D = 0.1 meters, and the steam density is ρ = 0.6 kg / m 3 , steam velocity v = 10m / s, find the friction coefficient f = 0.02 (based on the friction coefficient table of turbulent state), substitute the value into the formula:

[0084]

[0085] By comparing with the historical operation data of the thermal power plant, if the historical data shows that the normal pressure loss of the boiler to turbine pipeline is about 500Pa, then the calculation result of 600Pa at this time indicates that there is additional friction loss in the current system, which means that the inner wall of the pipeline is fouled or the steam flow rate is too fast.

[0086] The pressure loss results calculated above can be combined with the actual monitored value of the steam flow rate to further evaluate the steam loss. If the output steam flow rate of the boiler in the system is 10m / s, but the steam flow rate at the turbine inlet slows down to 9m / s due to pressure loss, the amount of steam loss in the system can be inferred based on the correlation between pressure loss and flow rate change. The decrease in steam flow rate indicates that part of the energy is consumed during pipeline transmission. The comparison of flow rate and pressure confirms that steam loss is not only reflected in the decrease in flow rate, but may also cause heat loss through heat loss. This information indicates that the steam pipeline needs to be cleaned regularly or the steam output of the boiler needs to be adjusted to reduce friction losses in the pipeline and ensure that the turbine receives sufficient steam flow, thereby improving power generation efficiency and reducing steam waste.

[0087] S202: Based on the steam flow rate and pressure loss data, analyze the feedback data of the condenser water flow, combine the heat capacity and heat transfer coefficient between the equipment, evaluate the delay and response of the fluid flow, calibrate the equipment response time, and generate equipment heat transfer and flow feedback information;

[0088] First, the water flow velocity data is collected using an ultrasonic flow meter installed at the inlet and outlet of the condenser. The flow meter can provide real-time flow velocity information of the water flow in the pipeline, and the water temperature changes at the inlet and outlet of the condenser are monitored by a temperature sensor. The heat capacity data of the condenser in the equipment design manual is used in combination with the temperature and flow rate data collected by the sensor in real time to calculate the heat transfer performance of the equipment. For the evaluation of the heat transfer coefficient, the heat flux density and temperature difference are obtained by temperature sensors and heat flow meters installed on the surface and internal pipes of the condenser to determine the real-time heat transfer coefficient and evaluate the heat transfer efficiency of the condenser. The delayed response of the water flow is evaluated using the time series analysis method. The specific operations are as follows: the response characteristics of the water flow are judged using autocorrelation analysis, and the condenser response is modeled in combination with the data of heat capacity and heat transfer coefficient, the response delay in the heat transfer process between the water flow and steam is analyzed, and the feedback information is used for the operation optimization of the condenser in the thermal power plant.

[0089] S203: Based on the heat transfer and flow feedback information of the equipment, by analyzing the heat transfer delay data between the equipment nodes, analyzing the thermal inertia response caused by the load change, and generating thermal inertia feedback matrix information by accumulating the load and thermal inertia parameters for matrixing;

[0090] By monitoring the temperature changes between different nodes, the heat transfer delay between devices is determined. The specific operation process is: the node temperature data is processed through data analysis tools such as Matlab, and the missing values ​​are filled by interpolation. Then, the thermal response time difference between each node is analyzed through the heat transfer delay model, and the thermal inertia changes of each node load under different operating conditions are compared in combination with the benchmark load data. The load data is collected in real time by the equipment power meter, and the thermal inertia response is quantified by calculating the cumulative effect of load changes on the heat transfer response. Using the matrix operation method, the relationship between the load changes and thermal inertia between different nodes is accumulated to further optimize the load distribution strategy of the equipment and ensure that the equipment operates in a state of efficient heat transfer.

[0091] See also Figure 4 , according to the thermal inertia feedback matrix information, analyze the impact of transient changes in temperature and pressure on the heat exchange and flow pattern between the boiler, turbine and condenser, predict the temperature and pressure change trends, and generate the transient temperature and pressure change trend prediction results. The specific steps are as follows:

[0092] S301: Based on the thermal inertia feedback matrix information, referring to the temperature and pressure data between the current boiler, steam turbine, condenser, and heat exchanger, the transient change data is classified and marked, the transient response during load change and cooling failure is extracted, and the transient temperature and pressure change data is generated;

[0093] First, the real-time temperature and pressure data of equipment such as boilers, turbines, condensers and heat exchangers in thermal power plants are input into the data processing system. The data processing system compares and analyzes historical data with transient response models, and uses pattern recognition algorithms (such as support vector machines SVM) to classify and mark each operating condition. The refinement process is as follows: based on the thermal inertia feedback matrix information between equipment, the system classifies each transient change data and marks different operating conditions such as load changes and cooling failures. Under load change conditions, the temperature and pressure change rates of the equipment will show a relatively smooth transition, while when there is a cooling failure, the temperature rises rapidly and the pressure drops significantly. The system distinguishes these two situations through data difference analysis. Subsequently, the transient response data are grouped and stored using a data labeling method, and the transient temperature and pressure change characteristics under specific conditions are extracted according to different operating conditions. This process ensures that transient condition changes can be effectively identified in the complex operating environment of thermal power plants for subsequent analysis and control adjustments.

[0094] S302: Based on the transient temperature and pressure change data, analyze the impact of transient temperature and pressure changes on the heat exchange and flow pattern between the boiler, the turbine and the condenser, compare the change trend with the historical data, extract the influencing factors, and generate the heat exchange pattern change information;

[0095] Based on the transient temperature and pressure change data, the temperature and pressure changes of each equipment in the thermal power plant are compared with the historical data. The trend analysis model of temperature change rate and pressure change rate is used. In the specific implementation process, the sliding window technology is used to segment the real-time collected temperature and pressure data. The data in each time window is calculated by the linear regression method to calculate the temperature and pressure change trends, and these trends are compared with the change patterns under historical stable working conditions. The K-means clustering algorithm is used to classify the change patterns, and the heat exchange patterns of equipment such as boilers, turbines, and condensers are divided into different clusters according to specific conditions (such as load changes and cooling abnormalities). The clustering results are used to analyze which equipment's heat exchange patterns have changed significantly. Subsequently, based on the classified data, the main influencing factors that cause temperature and pressure changes are extracted, such as boiler combustion efficiency, cooling water flow rate of condensers, etc. The correlation between these influencing factors and temperature and pressure changes is calculated by correlation analysis methods, which are used to optimize the operation strategy of the thermal transfer system of thermal power plants.

[0096] S303: Based on the heat exchange mode change information, analyze the temperature and pressure change trends, calculate the predicted value under each working condition, and compare it with the current data to predict the future temperature and pressure change trends, and generate transient temperature and pressure change trend prediction results;

[0097] Analyze the temperature and pressure change trends through the formula:

[0098] Tpred =T0+k T ·Δt

[0099] P pred =P0+k P ·Δt

[0100] Calculate the predicted values ​​of temperature and pressure for each operating condition respectively.

[0101] Where: T pred It represents the predicted temperature in the future in degrees Celsius (℃), which is calculated through historical data. It is based on the current operating status of the equipment, measured in real time by the sensor and derived in combination with the historical change rate. T0 represents the current temperature in degrees Celsius (℃), which is the current actual value collected by the real-time temperature sensor. k T It represents the temperature change rate in degrees Celsius per second (℃ / s). It is calculated from the time series data of the temperature sensor, usually through historical temperature data and transient response characteristics analysis. Δt represents the predicted time interval in seconds (s), that is, the predicted time span, which is usually set according to the monitoring cycle of the operating conditions. pred It indicates the future predicted pressure in Pa, which is derived from historical data and current status. P0 indicates the current pressure in Pa, which is measured by the real-time pressure sensor. P It represents the rate of change of pressure in Pascals per second (Pa / s). It is calculated from the time series data of the pressure sensor and is usually derived by analyzing the trend of pressure changes over time.

[0102] If the current boiler temperature T0 = 350°C, the temperature change rate k T =0.5℃ / s, the current boiler pressure P0 = 2×10 6 Pa, pressure change rate k P =-1000Pa / s, the predicted temperature and pressure in the next 10 seconds are:

[0103] T pred =350+0.5·10=355℃

[0104] P pred =2×10 6 +(-1000)·10=1990000Pa

[0105] Through calculation, it is predicted that the temperature will be 355℃ and the pressure will be 1990000Pa in 10 seconds. This prediction result can be compared with the historical benchmark value or the historical normal range. For example, under historical operating conditions, the temperature and pressure of the boiler under similar load should remain stable, but the current prediction result shows that the pressure has dropped, which may indicate that there is an abnormality in the system or the equipment loss has increased, prompting the operator to make corresponding adjustments.

[0106] See also Figure 5 ,According to the prediction results of transient temperature and pressure change trend, a probability distribution model is established to identify the uncertainty degree of the equipment under each load state, and the specific steps of generating the working condition adaptability optimization parameter set are as follows:

[0107] S401: Based on the prediction results of transient temperature and pressure change trends, the temperature, pressure and flow data of the boiler, steam turbine, condenser and heat exchanger are screened and classified according to the working conditions, and key data points are extracted according to the corresponding working conditions. The key data points are the temperature change rate, pressure fluctuation amplitude and flow peak value, and the working condition data set is generated;

[0108] First, the mutual influence relationship between the data is analyzed through the covariance matrix method. The covariance matrix is ​​a matrix obtained by the covariance operation between every two variables in the data set. It reflects the coordinated change characteristics between different equipment under various working conditions. The size and sign of the covariance value determine the positive and negative correlation and correlation strength between the two variables. The temperature change rate, pressure fluctuation amplitude and flow peak are preliminarily screened through this matrix, and the data points with high correlation are retained, and other data are eliminated, providing accurate input data for subsequent working condition state modeling.

[0109] S402: Based on the working condition data set, a state model is established for each working condition, the input and output conditions of each working condition are set through the model structure, key data points are input, the entropy value of the equipment in the current state is analyzed, uncertainty information in the working condition fluctuation is extracted, and abnormal information of the load state is generated;

[0110] To analyze the entropy value of the device in its current state, the formula is used:

[0111]

[0112] Calculate the entropy value S of the current state of the device;

[0113] Among them, S is used to characterize the overall uncertainty of the equipment working condition. The larger the entropy value, the greater the state instability of the equipment under the current working condition. i is the probability distribution of the i-th characteristic data point, which can be obtained by normalizing the characteristic data under different working conditions. By statistically analyzing the historical data, the frequency of occurrence of each characteristic point is calculated to obtain its probability, Ti is the temperature change rate of the ith characteristic data point, in °C / s, which can be obtained by the temperature sensor in real-time operation. i is the pressure fluctuation amplitude of the ith characteristic data point, in Pa, which is monitored and obtained in real time by the pressure sensor during system operation. i is the peak flow rate of the ith characteristic data point in kg / s, which is collected by the flow meter during system operation. n is the total number of characteristic data points, which is usually determined based on the sampling frequency and duration of system monitoring. log represents the natural logarithm.

[0114] Under certain working conditions, a thermal power plant extracts 100 characteristic data points, with temperature change rates ranging from 10℃ / s to 50℃ / s, pressure fluctuations ranging from 100Pa to 500Pa, and flow peaks ranging from 200kg / s to 600kg / s. Through historical data analysis, if the probability distribution of a characteristic point is 0.1, the temperature change rate T1 = 20℃ / s, the pressure fluctuation range X1 = 200Pa, and the flow peak F1 = 400kg / s, the data of other characteristic points are similar.

[0115] Substituting into the formula:

[0116]

[0117] Assuming that the historical entropy data shows that the entropy value under the benchmark condition is usually around 1000, the calculated result of 1600.23 indicates that the current equipment operating condition uncertainty is high, significantly higher than the historical benchmark value. This result shows that the temperature, pressure and flow rate fluctuate greatly, and the equipment operating state is highly unstable, which may affect the safety and efficiency of the equipment. This calculation can provide a basis for operation adjustment, and it is recommended to optimize the temperature and pressure adjustment strategy of the equipment to reduce the uncertainty of the operating condition.

[0118] S403: Based on the abnormal information of the load state, analyze the influence of the temperature, pressure and flow parameters of the equipment under each working condition on the operating efficiency and stability of the equipment itself, extract the optimal operating parameters under the load and working condition, and generate the working condition adaptability optimization parameter set;

[0119] Firstly, a large amount of historical data is collected from the equipment operation records under different loads. The noise signal is filtered out by wavelet transform during data cleaning. This method can effectively separate the high-frequency noise components in the signal, and obtain the effective temperature, pressure and flow data after smoothing by keeping the low-frequency components of the signal. Then, the principal component analysis method is used to reduce the dimension of high-dimensional data. PCA reduces the dimension and retains the maximum variance by converting the original data into new unrelated principal components, and retains the most representative small amount of principal component data. Then, a linear regression model is used to establish a relationship model between load state and equipment parameters. The independent variables of this model are the cleaned temperature, pressure and flow data, and the dependent variable is the operating efficiency of the equipment. Finally, by fitting the model, the impact of load changes on the equipment operating efficiency is analyzed and the optimal operating parameters under working conditions are extracted. These parameters provide an optimization basis for the stable operation of the equipment under different working conditions.

[0120] See also Figure 6 According to the working condition adaptability optimization parameter set and the transient temperature and pressure change trend prediction results, the real-time data is compared with the change range of the transient trend prediction, and the adjustment instructions are generated according to the deviation. The specific steps of obtaining the dynamic control instruction set are as follows:

[0121] S501: Based on the operating condition adaptability optimization parameter set and the transient temperature and pressure change trend prediction results, read the real-time temperature, pressure and flow data of the boiler, steam turbine, condenser and heat exchanger, summarize them by time and equipment classification, and generate real-time equipment status data;

[0122] Read the real-time temperature, pressure and flow data of boilers, turbines, condensers and heat exchangers. The temperature sensors, pressure sensors and flow meters installed on the equipment send data regularly. These data are transmitted to the central controller via the MODBUS protocol, classified and summarized according to the device category and timestamp, and stored in the controller's built-in SQL database. The classified and summarized data are then processed through aggregation functions to extract the temperature, pressure and flow data of each device at different times. The processed data are then sorted in chronological order, and the status data are pushed to the operation interface in real time through the industrial communication protocol based on OPC-UA for operators to view.

[0123] S502: Based on the real-time equipment status data, the real-time temperature, pressure, and flow are compared with the transient temperature and pressure change trend prediction results, and the anomalies and deviations in the equipment operation are identified by calculating the deviation values ​​of temperature, pressure, and flow, and the equipment deviation information is generated;

[0124] To calculate the deviation of temperature, pressure and flow, and identify the abnormalities and deviations in equipment operation, follow the formula:

[0125] D T=T real -T pred

[0126] D X =X real -X pred

[0127] D F =F real -F pred

[0128] Calculate the deviation of the temperature, pressure and flow of the equipment respectively. T is the temperature deviation, D X is the pressure deviation value, D F is the flow deviation value, T real It is the real-time temperature of the device in degrees Celsius (℃). It is collected in real time by the temperature sensor installed on the device. The temperature sensor monitors the instantaneous temperature change of the device with high precision. pred is the predicted temperature of the equipment in degrees Celsius (℃), which is predicted by the transient temperature and pressure change trend prediction model. The model makes predictions based on the historical temperature data, load changes and environmental conditions of the equipment. real is the real-time pressure of the device, in Pascal (Pa). The pressure sensor is used to monitor the pressure changes of the device in real time. pred is the predicted pressure of the equipment, in Pascal (Pa), calculated by the transient temperature and pressure change trend prediction model, which predicts pressure based on historical data, equipment load and operating conditions. real It is the real-time flow rate of the equipment in kilograms per second (kg / s). The flow rate of the fluid in the equipment is measured in real time by the flow meter. pred It is the predicted flow rate of the equipment in kilograms per second (kg / s), obtained through a prediction model based on the historical flow data and operating conditions of the equipment.

[0129] If the real-time temperature of a device is T real =400℃, predicted temperature is T pred =395℃, real-time pressure is X real =120Pa, predicted pressure is X pred =115Pa, real-time flow rate is F real =

[0130] 500kg / s, predicted flow rate is F pred =490kg / s.

[0131] Substitute the formula to calculate the deviation value:

[0132] Temperature deviation:

[0133] D T =400-395=5℃

[0134] Pressure deviation:

[0135] D X =120-115=5Pa

[0136] Flow deviation value:

[0137] D F =500-490=10kg / s

[0138] Result analysis:

[0139] The calculated deviation values ​​are: temperature deviation of 5°C, pressure deviation of 5Pa, and flow deviation of 10kg / s. By calculating the deviation values ​​of temperature, pressure, and flow respectively, the abnormality of the equipment in these parameters can be identified. If the historical data shows that the deviation value range is: temperature deviation value does not exceed 2°C, pressure deviation value does not exceed 3Pa, and flow deviation value does not exceed 5kg / s. At this time, the deviation value is far beyond the reference range, indicating that the operating status of the equipment may be abnormal, and timely measures need to be taken to adjust the temperature, pressure, and flow to avoid equipment operation failure.

[0140] S503: Based on the equipment deviation information, analyze the degree of deviation of temperature, pressure and flow of each equipment, determine the upper and lower limits of the adjustment parameters according to the equipment performance standard, which is the safe temperature range of the equipment, the maximum and minimum pressure values ​​that the equipment can withstand, the minimum and maximum flow rates when the equipment is running, and the reaction speed of the equipment when adjusting the parameters, and generate a dynamic control instruction set;

[0141] First, the performance standards such as the safe temperature range, maximum and minimum pressure values, flow range and response speed of each device are extracted from the device historical performance database. The historical data are classified through cluster analysis methods (such as K-Means clustering), and the data are divided into different clusters according to the device category and operating environment. The most representative standard value in each cluster is extracted. Combined with the real-time status data of the current device, the gap between the current temperature, pressure and flow deviation of the device and the performance standard is compared to determine whether the current operation of the device exceeds the preset safety range. If the deviation of the device is too large, the system automatically generates an alarm message and adjusts the upper and lower limits of the parameters.

[0142] See also Figure 7 According to the dynamic control instruction set, the combustion rate of the boiler, the steam valve of the steam turbine, the water pump flow of the condenser and the fluid flow rate of the heat exchanger are linked to adjust the specific steps of obtaining the real-time control result of temperature and pressure linkage as follows:

[0143] S601: Based on the dynamic control instruction set, the boiler combustion rate, turbine steam valve, condenser water pump flow, and heat exchanger fluid flow rate are adjusted in real time to generate equipment linkage adjustment feedback results;

[0144] First, the control instructions of each device are decoded in real time through the PLC (logic controller) and sent to the corresponding actuator. The boiler combustion rate is adjusted by the fuel input of the burner, and the fuel supply rate of the burner is accurately controlled by the proportional valve. The steam valve adjustment of the steam turbine is controlled by the electric actuator to control the valve opening. The flow regulation of the condenser water pump is achieved by controlling the water pump speed through the frequency converter. The fluid flow rate of the heat exchanger is adjusted in real time by the flow control valve. Through the linkage adjustment between various devices, the system makes fine adjustments according to the operating status feedback from the real-time monitoring data.

[0145] S602: Based on the feedback results of the equipment linkage adjustment, the temperature and pressure changes are recorded in real time, the response speed and adjustment effectiveness of the equipment are detected, and the temperature and pressure adjustment response data are generated;

[0146] The temperature and pressure data of each device are sampled at high frequency through the data acquisition module, and the sampling frequency is set to 10 times per second. The real-time data of the temperature sensor and pressure sensor collected by the PLC is recorded in the historical database of the central control system. The response curve of the device is analyzed by the curve fitting method of the temperature and pressure change data (such as polynomial fitting). The response speed of the device is calculated by the rate of change of temperature and pressure. The effectiveness of the adjustment is evaluated by the error between the target value and the actual value. If the error is within the set deviation range, it means that the adjustment is effective. The system will automatically generate temperature and pressure adjustment response data and store it in the database for subsequent analysis.

[0147] S603: Based on the temperature and pressure adjustment response data, determine whether the temperature and pressure of the equipment have returned to the preset range, analyze the linkage control effect, perform secondary fine-tuning on the parameters that do not meet expectations, and generate real-time temperature and pressure linkage control results;

[0148] First, extract the preset range of temperature and pressure of the equipment from the equipment performance standard library. By comparing with the temperature and pressure adjustment response data, determine whether the changes in temperature and pressure meet the preset standards. Analyze the adjustment effect of the equipment through the adaptive adjustment algorithm (such as PID control). If some temperature or pressure parameters exceed the preset range, the adjustment system will perform secondary fine-tuning on the parameters with large deviations. The secondary fine-tuning compares the current actual value of temperature or pressure with the preset target value. If the actual value of temperature or pressure is higher than the preset value, the deviation is positive; if it is lower than the preset value, the deviation is negative. According to the positive or negative deviation, determine whether the corresponding control amount needs to be increased or decreased. For example, when the temperature is high, the combustion rate needs to be reduced or the cooling flow needs to be increased, and when the temperature is low, the combustion rate needs to be increased or the cooling flow needs to be reduced. According to the size of the deviation, determine the size of the adjustment range. Consider the response effect of the past adjustment and use a certain proportional principle for adjustment. The larger the deviation, the larger the adjustment range, but in order to avoid over-adjustment, a maximum and minimum adjustment step range will also be set to ensure that the amplitude of each adjustment is reasonable and stable. When determining the adjustment range, the response speed and inertia of the equipment should also be considered. For example, the combustion system needs to take into account the delayed effect of fuel combustion, and the condenser water pump needs to take into account the fluid inertia to avoid excessive adjustments that may cause system instability. The adjustment operation is automatically performed through proportional valves, actuators and other equipment. The system records the temperature and pressure response status again based on the fine-tuned data until the temperature and pressure return to the preset range.

[0149] See also Figure 8 , a temperature and pressure intelligent regulation system for a thermal power plant, the system comprising:

[0150] The heat flow path construction module is based on the heat transfer and flow channels between boilers, turbines, condensers, and heat exchangers in thermal power plants. It collects temperature, pressure, and flow data, builds a network structure that reflects the heat exchange and flow characteristics between devices, evaluates the heat exchange characteristics, and generates heat flow path structure matrix information in combination with fluid flow direction and heat transfer path.

[0151] The equipment response evaluation module analyzes the impact of boiler output steam on the turbine and heat exchanger based on the heat flow path structure matrix information, monitors the feedback data of the condenser water flow, combines the heat capacity, heat transfer coefficient and flow delay information between equipment, evaluates the equipment response characteristics under various loads and working conditions, and generates thermal inertia feedback matrix information;

[0152] The transient change analysis module monitors the temperature and pressure transient changes of boilers, turbines, condensers and heat exchangers in real time based on the thermal inertia feedback matrix information, analyzes the transient response during load fluctuations and cooling failures, predicts the temperature and pressure change trends, and generates transient temperature and pressure change trend prediction results;

[0153] Based on the prediction results of transient temperature and pressure change trends, the operating condition optimization module classifies the temperature, pressure and flow data of boilers, turbines, condensers and heat exchangers according to operating conditions, establishes a probability distribution model, identifies the operating uncertainty of equipment under various load conditions, and generates an operating condition adaptability optimization parameter set;

[0154] Based on the operating condition adaptability optimization parameter set and the transient temperature and pressure change trend prediction results, the linkage control module reads the real-time temperature, pressure and flow data, compares them with the prediction results, identifies the deviation of the current state of the equipment, and linkage-adjusts the boiler combustion rate, turbine steam valve, condenser water pump flow and heat exchanger fluid flow rate to obtain the real-time temperature and pressure linkage control results.

[0155] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A temperature and pressure intelligent regulation method for a thermal power plant, characterized in that: The following steps are involved: Based on the heat transfer and flow channels between boilers, turbines, condensers, and heat exchangers in thermal power plants, temperature, pressure, and flow data are collected to build a network structure representing the interaction between devices, evaluate the heat exchange characteristics of the nodes, and build the heat flow path structure matrix information; According to the heat flow path structure matrix information, the influence of the boiler output steam on the steam turbine and the heat exchanger is analyzed, and the feedback data of the condenser water flow is monitored, the response characteristics under various loads and working conditions are evaluated, and the thermal inertia feedback matrix information is generated; According to the thermal inertia feedback matrix information, the influence of transient changes in temperature and pressure on the heat exchange and flow pattern between the boiler, the turbine and the condenser is analyzed, the temperature and pressure change trends are predicted, and the transient temperature and pressure change trend prediction results are generated; According to the prediction results of the transient temperature and pressure change trend, a probability distribution model is established to identify the degree of uncertainty of the equipment under each load state and generate an optimized parameter set for working condition adaptability; According to the working condition adaptability optimization parameter set and the transient temperature and pressure change trend prediction results, the real-time data is compared with the change range of the transient trend prediction, and an adjustment instruction is generated according to the deviation to obtain a dynamic control instruction set; According to the dynamic control instruction set, the combustion rate of the boiler, the steam valve of the turbine, the water pump flow of the condenser and the fluid flow rate of the heat exchanger are linked and adjusted to obtain the real-time control result of temperature and pressure linkage.

2. The temperature and pressure intelligent adjustment method for a thermal power plant according to claim 1 is characterized in that: The heat flow path structure matrix information includes the connection relationship of the heat exchange paths between devices, the direction matrix of the fluid flow and the temperature difference data between the devices. The thermal inertia feedback matrix information includes the thermal delay time of the equipment, the change in heat capacity and the heat transfer efficiency coefficient. The transient temperature and pressure change trend prediction results include the temperature change rate, the amplitude of pressure increase or decrease, and the change in fluid flow pattern under transient response. The operating condition adaptability optimization parameter set includes the optimal combustion rate adjustment range of the boiler, the adjustment ratio of the turbine steam flow and the optimization coefficient of the condenser water flow. The dynamic control instruction set includes real-time adjustment of the boiler combustion rate, adjustment of the opening of the turbine steam valve and control of the flow of the condenser water pump. The temperature and pressure linkage real-time control results include the dynamic correction of the heat exchange rate between the synchronous adjustment boiler, the turbine, the condenser and the heat exchanger.

3. The temperature and pressure intelligent adjustment method for a thermal power plant according to claim 1 is characterized in that: Based on the heat transfer and flow channels between boilers, turbines, condensers, and heat exchangers in thermal power plants, temperature, pressure, and flow data are collected to build a network structure representing the interaction between devices, evaluate the heat exchange characteristics of the nodes, and build the heat flow path structure matrix information. The specific steps are as follows: Based on the heat transfer and flow channels between boilers, turbines, condensers and heat exchangers, collect temperature, pressure and flow data, classify and organize the data, generate a network connection structure according to the device nodes, mark the interactions between devices, and generate a device interaction network; Based on the equipment interaction network, according to the heat exchange characteristics of boiler pipes, turbine blades, and condenser inlet nodes, the flow direction and heat transfer path of the fluid are analyzed, the heat flow direction is marked and the path is confirmed, and the flow and heat transfer path information is generated; Based on the flow and heat transfer path information, by analyzing the temperature difference and pressure information of the device nodes, the heat exchange path between the nodes and the node connection matrix are constructed, and the heat flow relationship between the devices is structured in combination with the heat transfer path to generate the heat flow path structure matrix information.

4. The temperature and pressure intelligent adjustment method for a thermal power plant according to claim 1 is characterized in that: According to the heat flow path structure matrix information, the influence of boiler output steam on the steam turbine and heat exchanger is analyzed, and the feedback data of condenser water flow is monitored to evaluate the response characteristics under various loads and working conditions. The specific steps of generating thermal inertia feedback matrix information are as follows: Based on the heat flow path structure matrix information, the flow rate and pressure changes of the boiler output steam to the turbine and the heat exchanger are calculated, the pressure loss of the steam in the flow is analyzed, the steam loss is determined by comparing the flow rate and pressure, and the steam flow rate and pressure loss data are generated; Based on the steam flow rate and pressure loss data, the feedback data of the condenser water flow is analyzed, and the delay and response of the fluid flow are evaluated in combination with the heat capacity and heat transfer coefficient between the equipment, the equipment response time is calibrated, and the equipment heat transfer and flow feedback information is generated; Based on the heat transfer and flow feedback information of the equipment, the heat transfer delay data between equipment nodes is analyzed, the thermal inertia response caused by load changes is analyzed, and the load and thermal inertia parameters are accumulated and matrixed to generate thermal inertia feedback matrix information.

5. The temperature and pressure intelligent adjustment method for a thermal power plant according to claim 1 is characterized in that: According to the thermal inertia feedback matrix information, the influence of transient changes in temperature and pressure on the heat exchange and flow pattern between the boiler, the turbine and the condenser is analyzed, and the temperature and pressure change trends are predicted. The specific steps of generating the transient temperature and pressure change trend prediction results are as follows: Based on the thermal inertia feedback matrix information, with reference to the temperature and pressure data between the current boiler, steam turbine, condenser, and heat exchanger, the transient change data is classified and marked, the transient response during load change and cooling failure is extracted, and transient temperature and pressure change data is generated; Based on the transient temperature and pressure change data, analyze the impact of transient changes in temperature and pressure on heat exchange and flow patterns between the boiler, turbine and condenser, extract influencing factors by comparing the change trend with historical data, and generate heat exchange pattern change information; Based on the heat exchange mode change information, the temperature and pressure change trends are analyzed, the predicted values ​​under each working condition are calculated, and compared with the current data, the future temperature and pressure change trends are predicted, and the transient temperature and pressure change trend prediction results are generated.

6. The temperature and pressure intelligent adjustment method for a thermal power plant according to claim 1, characterized in that: According to the prediction results of transient temperature and pressure change trend, a probability distribution model is established to identify the uncertainty degree of the equipment under each load state, and the specific steps of generating the working condition adaptability optimization parameter set are as follows: Based on the transient temperature and pressure change trend prediction results, the temperature, pressure and flow data of the boiler, turbine, condenser and heat exchanger are screened and classified according to the operating conditions, and key data points are extracted according to the corresponding operating conditions. The key data points are the temperature change rate, pressure fluctuation amplitude and flow peak value, and the operating condition data set is generated; Based on the working condition data set, a state model is established for each working condition, input and output conditions of each working condition are set through the model structure, key data points are input, the entropy value of the equipment in the current state is analyzed, uncertainty information in working condition fluctuations is extracted, and abnormal information of the load state is generated; Based on the abnormal information of the load state, the influence of the temperature, pressure and flow parameters of the equipment under each working condition on the operating efficiency and stability of the equipment itself is analyzed, the optimal operating parameters under the load and working condition are extracted, and an optimized parameter set with working condition adaptability is generated.

7. The temperature and pressure intelligent adjustment method for a thermal power plant according to claim 6 is characterized in that: To analyze the entropy value of the device in its current state, the formula is used: Calculate the entropy value S of the current state of the device; Among them, q i is the probability distribution of the i-th feature data point, T i is the temperature change rate of the i-th characteristic data point, X i is the pressure fluctuation amplitude of the i-th characteristic data point, F i is the traffic peak value of the i-th feature data point, and n is the total number of feature data points.

8. The temperature and pressure intelligent adjustment method for a thermal power plant according to claim 1, characterized in that: According to the working condition adaptability optimization parameter set and the transient temperature and pressure change trend prediction results, the real-time data is compared with the change range of the transient trend prediction, and the adjustment instructions are generated according to the deviation. The specific steps of obtaining the dynamic control instruction set are as follows: Based on the operating condition adaptability optimization parameter set and the transient temperature and pressure change trend prediction results, read the real-time temperature, pressure and flow data of the boiler, steam turbine, condenser and heat exchanger, summarize them by time and equipment classification, and generate real-time equipment status data; Based on the real-time equipment status data, the real-time temperature, pressure, and flow are compared with the transient temperature and pressure change trend prediction results, and the anomalies and deviations in equipment operation are identified by calculating the deviation values ​​of temperature, pressure, and flow, and the equipment deviation information is generated; Based on the equipment deviation information, the degree of deviation of temperature, pressure and flow of each device is analyzed. According to the equipment performance standards, which are the safe temperature range of the equipment, the maximum and minimum pressure values ​​that the equipment can withstand, the minimum and maximum flow rates when the equipment is running, and the reaction speed of the equipment when adjusting parameters, the upper and lower limits of the adjustment parameters are determined, and a dynamic control instruction set is generated.

9. The temperature and pressure intelligent adjustment method for a thermal power plant according to claim 1, characterized in that: According to the dynamic control instruction set, the specific steps of adjusting the combustion rate of the boiler, the steam valve of the steam turbine, the water pump flow rate of the condenser and the fluid flow rate of the heat exchanger in a linked manner to obtain the temperature and pressure linkage real-time control result are as follows: Based on the dynamic control instruction set, the boiler combustion rate, turbine steam valve, condenser water pump flow, and heat exchanger fluid flow rate are adjusted in real time to generate equipment linkage adjustment feedback results; Based on the feedback results of the linkage adjustment of the equipment, the temperature and pressure changes are recorded in real time, the response speed and adjustment effectiveness of the equipment are detected, and the temperature and pressure adjustment response data are generated; Based on the temperature and pressure adjustment response data, determine whether the temperature and pressure of the equipment have returned to the preset range, analyze the linkage control effect, perform secondary fine-tuning on the parameters that do not meet expectations, and generate real-time temperature and pressure linkage control results.

10. A temperature and pressure intelligent regulation system for a thermal power plant, characterized in that: According to any one of claims 1 to 9, the temperature and pressure intelligent regulation method for a thermal power plant is implemented, and the system comprises: The heat flow path construction module is based on the heat transfer and flow channels between boilers, turbines, condensers, and heat exchangers in thermal power plants. It collects temperature, pressure, and flow data, builds a network structure that reflects the heat exchange and flow characteristics between devices, evaluates the heat exchange characteristics, and generates heat flow path structure matrix information in combination with fluid flow direction and heat transfer path. The equipment response evaluation module analyzes the influence of boiler output steam on the steam turbine and the heat exchanger based on the heat flow path structure matrix information, monitors the feedback data of the condenser water flow, combines the heat capacity, heat transfer coefficient and flow delay information between the equipment, evaluates the equipment response characteristics under various loads and working conditions, and generates thermal inertia feedback matrix information; The transient change analysis module monitors the temperature and pressure transient changes of the boiler, steam turbine, condenser and heat exchanger in real time based on the thermal inertia feedback matrix information, analyzes the transient response during load fluctuation and cooling failure, predicts the temperature and pressure change trends, and generates transient temperature and pressure change trend prediction results; Based on the prediction results of the transient temperature and pressure change trend, the operating condition optimization module classifies the temperature, pressure and flow data of the boiler, steam turbine, condenser and heat exchanger according to the operating conditions, establishes a probability distribution model, identifies the operating uncertainty of the equipment under various load conditions, and generates an operating condition adaptability optimization parameter set; Based on the operating condition adaptability optimization parameter set and the transient temperature and pressure change trend prediction results, the linkage control module reads the real-time temperature, pressure and flow data, compares them with the prediction results, identifies the deviation of the current state of the equipment, and linkage-adjusts the boiler combustion rate, turbine steam valve, condenser water pump flow and heat exchanger fluid flow rate to obtain the temperature and pressure linkage real-time control results.

Images