Thermal power plant operation management intelligent platform and system

Abstract

The invention discloses a thermal power plant operation management intelligent platform and system, and relates to the technical field of thermal power plant management, the platform comprises an acquisition unit used for acquiring real-time operation data of a thermal power plant, the real-time operation data comprising environmental parameters, equipment state parameters, fuel inventory parameters and power market fluctuation parameters; the generation unit is used for generating dynamic optimization parameters through a multi-target dynamic optimization model based on the real-time operation data, and the dynamic optimization parameters comprise a fuel consumption priority, a power generation efficiency weight and an environmental protection deviation threshold value; and the adjusting unit is used for dynamically adjusting the operation management parameters of the thermal power plant according to the dynamic optimization parameters. According to the invention, environmental protection constraints, equipment health degree and market demands are integrated, a fuel scheduling strategy and unit load distribution are optimized in real time, the power generation efficiency and the fuel utilization rate are improved, and technical support is provided for intelligent management of a thermal power plant.

Description

Technical Field

[0001] This application relates to the technical field of thermal power plant management, and particularly to an intelligent platform and system for the operation and management of thermal power plants. Background Art

[0002] As a core facility for traditional energy supply, the operation and management of thermal power plants need to balance multiple objectives such as environmental protection compliance, power generation efficiency, and economic benefits. However, the existing management models generally have problems such as insufficient data integration ability and lagging response, and it is difficult to adapt to the real-time changing operating environment and market conditions. Traditional methods mostly rely on manual experience or single-dimensional static rules, which are prone to unreasonable resource allocation, excessive emissions, or revenue losses, restricting the overall operating efficiency of thermal power plants. Therefore, there is an urgent need for an intelligent platform and system for the operation and management of thermal power plants to solve the above-mentioned technical problems. Summary of the Invention

[0003] A series of simplified concepts are introduced in the Summary of the Invention section, which will be further elaborated in the Detailed Description section. The Summary of the Invention section of this application does not mean to attempt to define the key features and essential technical features of the claimed technical solution, nor does it mean to attempt to determine the protection scope of the claimed technical solution.

[0004] In a first aspect, this application provides an intelligent platform for the operation and management of thermal power plants, the platform comprising:

[0005] An acquisition unit, configured to acquire real-time operation data of the thermal power plant, wherein the real-time operation data includes environmental parameters, equipment status parameters, fuel inventory parameters, and power market fluctuation parameters;

[0006] A generation unit, configured to generate dynamic optimization parameters through a multi-objective dynamic optimization model based on the real-time operation data, wherein the dynamic optimization parameters include fuel consumption priority, power generation efficiency weight, and environmental protection deviation threshold;

[0007] An adjustment unit, configured to dynamically adjust the operation and management parameters of the thermal power plant according to the dynamic optimization parameters.

[0008] In some embodiments, the specific steps of acquiring the real-time operation data of the thermal power plant include:

[0009] Collecting environmental parameters through a distributed sensor network, wherein the environmental parameters include plant area temperature gradient, flue gas particulate matter concentration, and cooling water flow rate;

[0010] Obtaining the vibration spectrum data of the generator set bearings, and extracting the temperature deviation degree on the surface of the turbine blades through a thermal imaging module, and integrating the vibration spectrum data and the temperature deviation degree into equipment status parameters;

[0011] Generate fuel inventory parameters based on historical fuel inventory consumption data;

[0012] Generate power market volatility parameters based on a power prediction model, where the power market volatility parameters include real-time electricity price volatility and regional electricity demand forecast values.

[0013] In some embodiments, the specific steps of generating dynamic optimization parameters through a multi-objective dynamic optimization model based on real-time operation data include:

[0014] Input the flue gas particulate matter concentration into a preset environmental protection constraint model to calculate the real-time deviation between the current flue gas particulate matter concentration and the preset emission standard;

[0015] Dynamically compensate the real-time deviation based on the coupling relationship between the cooling water flow rate and the plant area temperature gradient to generate an environmental protection deviation threshold;

[0016] Calculate the generator set efficiency decay coefficient according to the vibration spectrum data and temperature deviation;

[0017] Construct a power generation efficiency revenue function based on the generator set efficiency decay coefficient and real-time electricity price volatility to determine the power generation efficiency weight;

[0018] Generate fuel consumption priorities through a fuel scheduling optimization algorithm based on the fuel inventory parameters and regional electricity demand forecast values.

[0019] In some embodiments, the specific steps of dynamically adjusting the operation management parameters of a thermal power plant according to the dynamic optimization parameters include:

[0020] Dynamically allocate the real-time consumption rates of multiple fuel bins based on the fuel consumption priorities and generate an adjustment instruction for the fuel procurement plan;

[0021] Optimize the generator set load distribution strategy according to the power generation efficiency weight so that the high-weight generator sets can respond to the power demand corresponding to the real-time electricity price volatility first;

[0022] When the environmental protection deviation threshold exceeds the preset threshold, trigger an equipment maintenance cycle instruction;

[0023] Generate a cleaning priority list for turbine blades based on the equipment maintenance cycle instruction;

[0024] Integrate the adjustment instruction for the fuel procurement plan, the generator set load distribution strategy, and the cleaning priority list into the dynamic adjustment result of the operation management parameters.

[0025] In some embodiments, the above platform further includes:

[0026] A correction unit for iteratively correcting the above dynamic optimization parameters based on a preset feedback mechanism.

[0027] In some embodiments, the above platform further includes:

[0028] A first construction unit, configured to construct a first anomaly detection model based on the physical correlation between the plant area temperature gradient and the cooling water flow rate among the above environmental parameters;

[0029] A second construction unit, configured to construct a second anomaly detection model according to the time-domain correlation between the vibration spectrum data and the temperature deviation degree among the above equipment status parameters;

[0030] A calibration unit, configured to trigger a data source location and sensor calibration instruction when the above first anomaly detection model or the above second anomaly detection model outputs an anomaly flag, and re-input the calibrated data into the above multi-objective dynamic optimization model.

[0031] In some embodiments, the above platform further includes:

[0032] A judgment unit, configured to determine that the cooling system fails when it is detected that the above plant area temperature gradient is abnormal and the above temperature deviation degree is greater than the critical value;

[0033] A failure handling unit, configured to trigger a pre-start instruction for a standby cooling device in the case of the failure of the above cooling system;

[0034] An allocation unit, configured to re-allocate the consumption ratio of low-calorific value fuel based on the above pre-start instruction and the above fuel consumption priority to reduce the load of the generator set.

[0035] In a second aspect, the present application proposes a smart operation and management system for a thermal power plant, including the smart operation and management platform for a thermal power plant according to any one of the first aspect.

[0036] In summary, the present application effectively solves the problems of data isolation, response lag, and multi-objective conflict in traditional methods by obtaining environmental parameters, equipment status parameters, fuel inventory parameters, and power market fluctuation parameters in real time, constructing a multi-objective dynamic optimization model to generate fuel consumption priority, power generation efficiency weight, and environmental protection deviation threshold, and adjusting the operation and management strategy based on the dynamic optimization parameters. The present application realizes the dynamic balance between environmental protection indicators and power generation efficiency, reduces the operation cost through the fuel dispatch optimization algorithm, and at the same time adaptively adjusts the maintenance cycle in combination with the equipment health status, improving the intelligent level and economic benefits of the thermal power plant operation, and ensuring environmental protection compliance and equipment operation reliability.

[0037] For the smart operation and management platform for a thermal power plant proposed by the present disclosure, other advantages, objectives, and features of the present disclosure will be partially reflected by the following description, and partially will be understood by those skilled in the art through the research and practice of the present disclosure. Description of the Drawings

[0038] Various other advantages and benefits will become clear to those of ordinary skill in the art by reading the following detailed description of the preferred embodiments. The drawings are only for the purpose of illustrating the preferred embodiments and are not considered to be a limitation of this specification. Also, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0039] Figure 1 A structural schematic diagram of an intelligent platform for thermal power plant operation and management provided by an embodiment of the present application;

[0040] Figure 2 A structural schematic diagram of an intelligent operation and management system for a thermal power plant provided by an embodiment of the present application. Detailed implementation manners

[0041] The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and above-mentioned drawings of the present application are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments.

[0042] Please refer to Figure 1 , a structural schematic diagram of an intelligent platform 10 for thermal power plant operation and management provided by an embodiment of the present application, which may specifically include:

[0043] An acquisition unit 101, configured to acquire real-time operation data of the thermal power plant, where the real-time operation data includes environmental parameters, equipment status parameters, fuel inventory parameters, and power market fluctuation parameters;

[0044] Exemplarily, by collecting multi-dimensional operation data of the thermal power plant in real time, it provides a basic support for subsequent dynamic optimization. This step covers environmental parameters, equipment status parameters, fuel inventory parameters, and power market fluctuation parameters, and constructs a comprehensive data system covering environmental protection, equipment health, resource scheduling, and market response. Through multi-source data integration, it realizes the global perception of the operation status of the thermal power plant and lays a data foundation for dynamic decision-making.

[0045] The acquisition mechanism of real-time operation data is designed based on the interaction characteristics between the physical system of the thermal power plant and the external environment. Environmental parameters reflect the impact of the plant operation environment on equipment efficiency and emissions. Equipment status parameters capture the real-time health status of key components. Fuel inventory parameters and power market fluctuation parameters provide dynamic inputs from the dimensions of resource reserve and economic benefits respectively. The collaborative collection of these data ensures that the subsequent optimization model can comprehensively balance multiple objectives such as environmental compliance, equipment stability, and economic benefits.

[0046] A generation unit 102 is used to generate dynamic optimization parameters through a multi-objective dynamic optimization model based on real-time operation data. The dynamic optimization parameters include fuel consumption priority, power generation efficiency weight, and environmental protection deviation threshold.

[0047] Exemplarily, through the multi-objective dynamic optimization model, the real-time operation data is converted into executable dynamic optimization parameters. This model takes environmental compliance, power generation efficiency, and fuel cost control as core objectives. By integrating environmental parameters, equipment status, fuel inventory, and market fluctuation data, it dynamically coordinates the conflicts among environmental protection constraints, power generation efficiency, and economic benefits, and generates three key parameters: fuel consumption priority, power generation efficiency weight, and environmental protection deviation threshold. Among them, the fuel consumption priority is used to optimize the fuel bin scheduling strategy, the power generation efficiency weight guides the unit load distribution, and the environmental protection deviation threshold dynamically restricts emission control. The three together form a multi-dimensional decision-making basis for the operation management of the thermal power plant.

[0048] The synergistic effect of the dynamic parameters is the core principle of this step. The fuel consumption priority guides the differential consumption strategy of the fuel bin. The power generation efficiency weight drives the load of high-yield units to respond preferentially. The environmental protection deviation threshold triggers equipment maintenance or emission compensation actions. The three achieve dynamic linkage through the model weight distribution and real-time feedback mechanism, ensuring that the thermal power plant simultaneously meets the multi-objective balance of environmental compliance, equipment health, and market benefits in complex operation scenarios, and providing a globally optimized parameter basis for subsequent operation adjustments.

[0049] An adjustment unit 103 is used to dynamically adjust the operation management parameters of the thermal power plant according to the dynamic optimization parameters.

[0050] Exemplarily, in this step, the dynamic optimization parameters are converted into executable operation management strategies to achieve real-time adaptive adjustment of the operation parameters of the thermal power plant. Based on the fuel consumption priority, the system dynamically allocates the consumption rates of multiple fuel bins and generates purchase plan adjustment instructions to ensure the precise matching of fuel scheduling with inventory turnover and market demand. The power generation efficiency weight drives the differential distribution of the load of the generator sets, preferentially increasing the output of high-efficiency units to respond to electricity price fluctuations and maximizing power generation benefits. The environmental protection deviation threshold triggers equipment maintenance instructions or cleaning priority lists through real-time monitoring and comparison with the threshold to ensure the dynamic balance of emission compliance and equipment health status.

[0051] The global coordination of the adjustment mechanism is the core principle of this step. Through the linkage effect of dynamically optimizing parameters, the system realizes multi-objective collaborative optimization in key links such as fuel scheduling, load distribution, and equipment maintenance. For example, when the environmental protection deviation exceeds the standard, the maintenance and cleaning of high-priority units are preferentially started, and at the same time, the consumption ratio of low-calorific-value fuel is adjusted to reduce the load pressure, forming a closed-loop control of environmental protection, efficiency, and safety. Finally, the adaptive optimization of the operation management parameters of the thermal power plant and the efficient integration of multi-dimensional resources are realized.

[0052] In summary, this application collects environmental parameters such as the temperature gradient in the plant area, the concentration of flue gas particulate matter, and the cooling water flow through a distributed sensor network, enabling real-time monitoring of the external environment during the operation of the thermal power plant, providing a basis for energy conservation, emission reduction, and stable equipment operation; obtaining the bearing vibration spectrum data of the generator set and the temperature deviation degree on the surface of the turbine blade as equipment status parameters helps to timely detect potential equipment failure hazards and ensure the safe and reliable operation of the equipment. Based on the historical consumption data of fuel inventory, fuel inventory parameters are generated. Combining with the predicted value of regional electricity demand, the fuel consumption priority is determined through the fuel scheduling optimization algorithm to realize the scientific allocation of fuel, avoid overstocking or shortage, and reduce fuel costs. Using the power prediction model to generate the real-time electricity price volatility, constructing a power generation efficiency revenue function to determine the power generation efficiency weight, and optimizing the load distribution strategy of the generator set, so that the high-weight units can respond to the power demand first, improving the power generation efficiency and economic benefits. According to the real-time deviation between the concentration of flue gas particulate matter and the preset emission standard, combined with the coupling relationship between the cooling water flow and the temperature gradient in the plant area, an environmental protection deviation threshold is generated. When the preset threshold is exceeded, a device maintenance cycle instruction is triggered to ensure the environmental protection compliance operation of the thermal power plant. By iteratively correcting and dynamically optimizing parameters, the operation management level of the thermal power plant is continuously improved, realizing the dynamic balance of environmental protection, efficiency, and economic benefits, and promoting the thermal power plant to develop towards the direction of intelligence and high efficiency.

[0053] In some instances, the specific steps for obtaining the real-time operation data of the thermal power plant include:

[0054] Collecting environmental parameters through a distributed sensor network, where the environmental parameters include the temperature gradient in the plant area, the concentration of flue gas particulate matter, and the cooling water flow;

[0055] Obtaining the vibration spectrum data of the bearings of the generator set and extracting the temperature deviation degree on the surface of the turbine blade through a thermal imaging module, and integrating the vibration spectrum data and the temperature deviation degree into equipment status parameters;

[0056] Generating fuel inventory parameters based on the historical consumption data of fuel inventory;

[0057] Generating power market fluctuation parameters based on a power prediction model, where the power market fluctuation parameters include the real-time electricity price volatility and the predicted value of regional electricity demand.

[0058] Exemplarily, environmental parameters of a thermal power plant are collected in real time through a distributed sensor network. The sensor network covers key areas of the plant (such as the boiler area, cooling tower, flue gas treatment device, etc.), and continuously obtains temperature gradient, flue gas particulate matter concentration, and cooling water flow data through spatially distributed monitoring nodes. Specifically, the temperature gradient measures the temperature distribution differences in different areas through a multi-point temperature sensor array, reflecting the operating balance of the thermal system; the flue gas particulate matter concentration monitors the pollutant content in the discharged flue gas in real time through a laser scattering sensor or an electrochemical sensor; the cooling water flow is collected through an electromagnetic flowmeter or an ultrasonic flowmeter to obtain the instantaneous flow rate of the cooling water circulation system, which is used to evaluate the cooling efficiency and heat exchange state. The collaborative collection of the above environmental parameters provides basic data support for subsequent environmental protection index analysis and equipment operation optimization.

[0059] Equipment status parameters are obtained through multi-modal sensing technology. First, vibration acceleration sensors are deployed at the bearings of the generator set to collect vibration spectrum data. The spectrum data contains amplitude characteristics in different frequency bands, which are used to identify mechanical faults such as bearing wear and shafting imbalance. Secondly, a non-contact temperature scan is performed on the surface of the turbine blade through a thermal imaging module to generate a temperature distribution map and extract the temperature deviation, that is, the difference between the actual temperature and the theoretical design temperature, which characterizes the thermal stress state and cooling effect of the blade. Synchronizing the vibration spectrum data and the temperature deviation in time and fusing the data form comprehensive equipment status parameters, which can comprehensively reflect the mechanical health status and thermodynamic performance of the generator set and provide key basis for equipment maintenance decisions.

[0060] In the intelligent operation and management of a thermal power plant, the dynamic generation of fuel inventory parameters is achieved through the following steps:

[0061] First, conduct in-depth analysis of historical consumption data, and perform statistical modeling on the consumption rates and periodic patterns of different fuel types. By analyzing the consumption patterns in historical data, identify the consumption trends of different fuels under different seasons and different production loads, and establish an inventory consumption prediction model. This model can predict the consumption demand of each fuel within a certain future period, providing a benchmark reference for inventory management. For example, during the peak electricity consumption period in winter, the coal consumption rate may increase, and the model will adjust the prediction value according to historical data of the same period to ensure the timeliness of inventory replenishment.

[0062] Secondly, the inventory levels of each fuel tank are monitored in real time through weight sensors or level gauges deployed in the fuel tanks. Combining the real-time inventory data with the historical consumption model, the turnover period of the current inventory is calculated. The turnover period reflects the length of time that the inventory fuel can be maintained at the current consumption rate. For example, if the inventory of a certain fuel tank is 1000 tons and the historical daily average consumption rate is 50 tons, the turnover period is 20 days. The system dynamically updates this period value and takes into account changes in the real-time consumption rate to ensure that the calculation of the turnover period is consistent with the actual operating status.

[0063] Finally, fuel inventory parameters are generated by integrating the inventory level, consumption rate, and turnover period. This parameter contains multi-dimensional information, such as low inventory warning flags, high calorific value fuel reserve priorities, etc. When the inventory level approaches the safety threshold and the turnover period is below the preset lower limit, the system automatically marks this fuel type as an urgent procurement target and triggers a procurement plan adjustment instruction. At the same time, based on the calorific value characteristics of the fuel and the inventory status, the reserve strategy for high calorific value fuel is optimized. For example, during peak electricity price periods, high calorific value fuel is preferentially consumed to improve power generation efficiency, while inventory is replenished during low demand periods. In addition, the system dynamically adjusts the fuel procurement frequency and batch according to the turnover period to avoid inventory backlogs or shortages, ensuring the economy and stability of fuel supply. Through the above, the fuel inventory parameters can reflect the inventory status and demand changes in real time, providing an accurate basis for fuel scheduling priority decisions and realizing the dynamic optimization of inventory management and cost control.

[0064] In the process of predicting and generating power market fluctuation parameters, real-time electricity price volatility and regional electricity demand forecast values are dynamically generated by integrating multi-source data and applying prediction models. First, the calculation of real-time electricity price volatility depends on the real-time electricity price data of the power trading platform, supply-demand relationship indicators, and weather impact factors. The system collects historical electricity price data, analyzes its trends and periodic characteristics over time, and combines the current supply-demand balance state (such as generator output, user load demand) and weather conditions (such as the impact of extreme temperatures on electricity demand) to construct a time series prediction model. This model predicts the future short-term electricity price fluctuation trend by identifying patterns in historical data. For example, during high-temperature weather, the increase in air conditioner usage may lead to a surge in electricity demand. The model will combine the historical electricity price fluctuation patterns during high-temperature periods to predict the upward risk of the current electricity price, thereby generating a dynamic electricity price volatility parameter.

[0065] Secondly, the generation of the regional electricity demand forecast value is based on historical electricity consumption data, industrial activity indices, and meteorological forecast information. The system first analyzes historical electricity consumption records to identify the impact patterns of different seasons, weekdays and holidays, and changes in industrial activity intensity on electricity loads. At the same time, industrial activity indices (such as manufacturing production indices, commercial electricity consumption) are introduced as demand driving factors, and combined with meteorological data (such as temperature and humidity forecasts for the next week) to construct a multi-dimensional electricity demand forecasting model. For example, during a cold wave warning, the model will refer to the electricity consumption growth trend during low-temperature weather in the same period of history, superimpose the current industrial activity intensity, predict the peak electricity load in the next few days, and generate corresponding demand forecast values.

[0066] In the parameter output stage, the system integrates the real-time electricity price volatility and the regional electricity demand forecast value into power market volatility parameters. This integration process is achieved through dynamic weight allocation. For example, during periods of high electricity price volatility and high demand forecasts, the system will assign a higher decision weight to the electricity price volatility to prioritize the goal of maximizing market returns. Conversely, during periods of stable demand and low electricity price volatility, it focuses on the precise matching of demand forecasts. The integrated parameters are input into a multi-objective optimization model to drive the dynamic adjustment of the generator output strategy. For example, when it is predicted that the electricity price is about to rise and the electricity demand surges, the optimization model will give priority to dispatching efficient units to increase output, and at the same time adjust the fuel consumption priority to match the power supply during peak hours, achieving the coordinated optimization of revenue and demand response. Through the above content, the power market volatility parameters can reflect market dynamics and demand changes in real time, providing a key basis for the intelligent adjustment of the thermal power plant's power generation strategy, and ensuring the dual improvement of economic benefits and operational stability in a complex market environment.

[0067] In some instances, the specific steps for generating dynamic optimization parameters through a multi-objective dynamic optimization model based on real-time operation data include:

[0068] Input the flue gas particulate matter concentration into a preset environmental protection constraint model to calculate the real-time deviation between the current flue gas particulate matter concentration and the preset emission standard;

[0069] Dynamically compensate the real-time deviation based on the coupling relationship between the cooling water flow rate and the plant area temperature gradient to generate an environmental protection deviation threshold;

[0070] Calculate the generator set efficiency decay coefficient based on the vibration spectrum data and the temperature deviation;

[0071] Based on the generator set efficiency decay coefficient and the real-time electricity price volatility, construct a power generation efficiency revenue function to determine the power generation efficiency weight;

[0072] Based on the fuel inventory parameters and the regional electricity demand forecast value, generate the fuel consumption priority through a fuel dispatch optimization algorithm.

[0073] Exemplarily, the core of the environmental protection constraint model lies in the setting and adaptive calibration of the dynamic limit curve. The dynamic limit curve is designed based on time-period requirements. For example, the emission limit allowed during the peak daytime power consumption period is slightly higher than that during the low-load period at night to balance environmental protection requirements and power generation demands. The model matches the corresponding threshold range of the current time in real time through the built-in time - emission standard mapping table. At the same time, the model conducts adaptive calibration in combination with the actual operating conditions of the thermal power plant (such as the current fuel type, unit load rate, and equipment operating status). For example, when it is detected that high-sulfur fuel is used, the model automatically reduces the emission limit threshold to offset the impact of fuel characteristics on pollutant generation; under the high-load operating state of the unit, the limit is appropriately relaxed to ensure power generation stability, but it is necessary to ensure compliance with regulatory requirements at all times.

[0074] The calculation of the real-time deviation amount is achieved by comparing the current flue gas particulate matter concentration with the threshold range of the dynamic limit curve. If the current concentration value is within the limit range, the deviation amount is zero; if it exceeds the limit, the deviation amount is calculated proportionally according to the exceeding amplitude. For example, when the concentration exceeds the limit by 10%, the deviation amount is marked as a mild over-standard; when it exceeds by 30%, it is a severe over-standard. The sliding window analysis of historical emission data is introduced. For example, based on the concentration fluctuation trend in the past hour, the potential over-standard risk in the short term in the future is predicted, and the calculation weight of the deviation amount is adjusted in advance to enhance the early warning ability of the model.

[0075] The dynamic compensation mechanism is designed based on the coupling relationship between the cooling water flow rate and the plant area temperature gradient. The cooling water flow rate is monitored in real time by an electromagnetic flowmeter. When the flow rate is lower than the preset safety threshold, the system determines that the cooling efficiency is insufficient. At this time, the plant area temperature gradient will abnormally increase due to the inability to dissipate heat in time, specifically manifested as an increase in the temperature difference between the boiler area and the cooling tower outlet. The model collects multi-region temperature data through an array of temperature sensors, calculates the gradient change rate, and combines the flow rate data to judge the operating state of the cooling system. When it is detected that the flow rate is insufficient and the temperature gradient exceeds the critical value, the model automatically triggers the compensation mechanism and increases the emission control weight. For example, multiply the original deviation amount by a compensation coefficient to generate a more stringent environmental protection deviation threshold. This threshold will directly act on the emission control strategy, such as forcing the reduction of the consumption ratio of high-pollution fuels or starting standby purification equipment to ensure that the emission concentration returns within the limit range.

[0076] The finally generated environmental protection deviation threshold not only reflects the compliance of the current emission status but also dynamically integrates the indirect impact of environmental parameters on emission control. For example, in a high-temperature environment in summer, the accelerated evaporation rate of cooling water may lead to a decrease in the flow rate. At this time, the model tightens the threshold in advance through the dynamic compensation mechanism to avoid a chain of emission over-standard caused by reduced cooling efficiency. This mechanism improves the adaptability of the model to complex operating conditions and ensures the scientific nature and real-time nature of the environmental protection control strategy.

[0077] The calculation of the generator set efficiency decay coefficient is based on the comprehensive analysis of vibration spectrum data and temperature deviation. The vibration spectrum data is collected by sensors installed at the bearings of the generator set, and its spectrum characteristics reflect the health status of mechanical components. For example, an abnormal increase in the amplitude in the high-frequency band usually indicates bearing wear or lubrication failure, while periodic vibration in the low-frequency band may be caused by shafting imbalance. The system identifies these abnormal characteristics through frequency-domain analysis techniques, quantifies their severity, and generates a vibration anomaly index. At the same time, the thermal imaging module continuously monitors the temperature distribution on the surface of the turbine blades and calculates the deviation between the actual temperature and the designed temperature. This deviation is directly related to the thermal stress state and cooling efficiency of the blades. The greater the deviation, the more significant the deterioration of the thermodynamic performance. The system fuses the vibration anomaly index and the temperature deviation according to preset weights. For example, the vibration anomaly index accounts for 60% and the temperature deviation accounts for 40%, and finally generates a comprehensive efficiency decay coefficient. This coefficient characterizes the decay degree of the current efficiency of the generator set relative to the theoretical maximum value in percentage form, providing a quantitative basis for subsequent economic decision-making.

[0078] The construction of the power generation efficiency benefit function takes maximizing economic benefits as the core goal, while taking into account the health status of the equipment. The function is optimized by dynamically balancing the increase in costs caused by efficiency decay and the change in benefits brought about by electricity price fluctuations. Specifically, when the real-time electricity price is at a peak, the benefits brought by the high electricity price may cover the increased operating costs due to efficiency decay. At this time, the system will increase the power generation efficiency weight of this unit. Even if its efficiency decay coefficient is high, it will still be preferentially dispatched to maximize benefits; on the contrary, during the low electricity price period, the system reduces the weight of the unit with a high decay coefficient, reduces its operating time to reduce losses, and at the same time increases the load share of the unit with a low decay. In addition, the function introduces a non-linear influence mechanism of the decay coefficient: when the efficiency decay coefficient exceeds the critical threshold, the corresponding cost growth rate increases. At this time, even if the electricity price is high, the system will limit the dispatching priority of this unit to avoid excessive deterioration of the equipment.

[0079] The multi-objective optimization process determines the power generation efficiency weights of each unit through iterative calculations. The optimization algorithm takes real-time electricity price data, efficiency decay coefficients, and grid load demand as inputs, and finds the balance point between maximizing benefits and minimizing equipment losses under the constraint of ensuring power supply stability. For example, when the electricity demand surges, the algorithm preferentially allocates the power generation tasks during high electricity price periods to units with moderate efficiency decay coefficients and higher benefit weights; during the period of gentle demand, it focuses on dispatching units with low decay to extend the equipment life. The optimization result generates the weight values of each unit in real time. The units with higher weights will bear a larger proportion of the load, and at the same time, the system continuously monitors the operating data and dynamically adjusts the weight allocation strategy.

[0080] The above mechanism achieves a high degree of coordination between economy and equipment health. By deeply coupling the efficiency decay coefficient with the depth of electricity price fluctuations, the system can not only respond to market changes to capture revenue opportunities but also avoid irreversible damage to key equipment through weight regulation. For example, for a certain unit with an efficiency decay coefficient of 15%, the weight is increased to 0.8 during the electricity price peak to bear the main load; when the electricity price drops to the flat section, the weight is reduced to 0.4, and the load is transferred to a standby unit with an 8% decay coefficient. This dynamic strategy not only ensures short-term benefits but also extends the overall life by balancing equipment usage, reflecting the core advantages of intelligent management.

[0081] The fuel scheduling optimization algorithm dynamically generates the fuel consumption priority by comprehensively considering the fuel inventory parameters and the predicted regional electricity demand values, aiming to achieve the dual goals of minimizing inventory costs and maximizing power supply stability. The core of the algorithm lies in real-time matching of fuel characteristics with the electricity market demand and adaptively adjusting the fuel bin activation strategy according to the inventory status and market fluctuations.

[0082] The algorithm first constructs a multi-dimensional evaluation matrix based on the inventory quantity, calorific value, and procurement cost in the fuel inventory parameters. The inventory quantity reflects the real-time available resources in each fuel bin, the calorific value determines the power generation efficiency per unit of fuel, and the procurement cost is related to the economic index. For example, although high-calorific-value fuel has a higher procurement cost, its power generation per unit is higher, which is suitable for periods of surging electricity demand to quickly improve power supply capacity; low-calorific-value fuel has a lower cost but limited power generation efficiency and is suitable for periods of flat demand to reduce operating costs. The algorithm calculates the economic index of each fuel bin through the ratio of calorific value to cost and determines the initial priority in combination with the inventory quantity.

[0083] The predicted regional electricity demand value provides the basis for dynamic scheduling of the algorithm. When it is predicted that the electricity demand is about to enter the peak period, the algorithm preferentially activates the high-calorific-value fuel bin to maximize power generation efficiency and ensure power supply stability. At the same time, the algorithm monitors the change trend of the inventory quantity in real time. When the inventory quantity of a certain fuel bin is lower than the preset safety threshold (such as the critical value to meet the demand for the next 12 hours), the inventory warning mechanism is immediately triggered. At this time, the algorithm generates an emergency procurement order in combination with the procurement cost data and dynamically adjusts the consumption ratio of low-calorific-value fuel. For example, the priority of low-calorific-value fuel is increased to a medium level to extend the inventory cycle of high-calorific-value fuel and avoid the risk of power supply interruption caused by inventory depletion.

[0084] The fuel scheduling optimization algorithm further incorporates power supply stability constraints. When the power market fluctuates violently or there is a large uncertainty in the predicted regional electricity demand, the algorithm conducts multi-scenario simulation analysis to preset fuel scheduling plans under different demand fluctuation ranges. For example, when the predicted demand deviation exceeds 10%, the algorithm automatically activates the standby fuel storage and quickly matches the demand gap based on the calorific value distribution to ensure power supply continuity. In addition, the algorithm tracks the price fluctuations in the fuel procurement market in real time. When it detects that the price of a certain fuel type is about to rise, it increases the procurement volume in advance to lock in costs, and at the same time adjusts the consumption priority to optimize the inventory structure.

[0085] The adaptive ability of the algorithm is reflected in the dynamic feedback mechanism. After each fuel scheduling decision is executed, the system collects actual power generation efficiency, inventory consumption rate, and market response data, and conducts a comparative analysis with the predicted values. If it is found that the deviation continuously exceeds the fault tolerance range, the parameters of the demand prediction model are automatically corrected, and the fuel priority is recalculated. For example, when the actual electricity demand is higher than the predicted value, the algorithm increases the activation ratio of high-calorific value fuels in the next scheduling cycle and shortens the procurement interval of low-calorific value fuels to quickly respond to supply and demand changes. Through continuous iterative optimization, the algorithm gradually approaches the global optimal balance point between inventory cost and power supply stability, achieving efficient resource allocation and risk control.

[0086] The above design makes the fuel scheduling strategy both economical and robust. For example, during the peak summer electricity consumption period, the algorithm preferentially schedules the high-calorific value coal storage to meet the surging demand, and at the same time automatically triggers the emergency procurement of imported liquefied natural gas according to the inventory to supplement the reserves; while during the low valley period at night, it switches to low-calorific value local lignite to reduce operating costs. This dynamic strategy not only ensures power supply stability but also significantly reduces the comprehensive fuel cost through precise inventory management and market response, reflecting the core value of intelligent scheduling.

[0087] In some instances, according to the dynamic optimization parameters, the specific steps for dynamically adjusting the operation management parameters of thermal power plants include:

[0088] Based on the fuel consumption priority, dynamically allocate the real-time consumption rate of multiple fuel storage, and generate adjustment instructions for the fuel procurement plan;

[0089] According to the power generation efficiency weight, optimize the load distribution strategy of the generator sets so that the high-weight units give priority to responding to the electricity demand corresponding to the real-time electricity price volatility;

[0090] When the environmental protection deviation threshold exceeds the preset threshold, trigger the equipment maintenance cycle instruction;

[0091] Based on the equipment maintenance cycle instruction, generate a cleaning priority list for turbine blades;

[0092] Integrate the adjustment instructions for the fuel procurement plan, the load distribution strategy of the generator sets, and the cleaning priority list into the dynamic adjustment results of the operation management parameters.

[0093] Exemplarily, based on the fuel consumption priority, the system dynamically allocates the real-time consumption rates of multiple fuel bins. The priority is generated by a fuel scheduling optimization algorithm, comprehensively considering fuel calorific value, inventory level, and procurement cost. For example, during peak electricity demand periods, high-calorific-value fuel bins are preferentially enabled to improve power generation efficiency, while monitoring the inventory consumption rates of each bin; when the inventory level of a certain fuel bin is lower than the safety threshold, its consumption rate is automatically reduced and an emergency procurement instruction is generated. The procurement instruction includes the fuel type, procurement quantity, and arrival time window, and is sent to the supplier in real time through the supply chain management system to ensure that inventory replenishment synchronizes with demand fluctuations. In addition, the system dynamically adjusts the time span of the procurement plan according to short-term changes in the regional electricity demand forecast value. For example, when demand fluctuates violently, the procurement cycle is adjusted from daily to every six hours to enhance response flexibility.

[0094] Optimize the load distribution strategy of the generator sets according to the power generation efficiency weight, which is dynamically determined by the power generation efficiency benefit function. High-weight generator sets (i.e., those with a low efficiency decay coefficient and a high real-time electricity price benefit) preferentially undertake the load during periods with a higher electricity price volatility. For example, during the peak period of real-time electricity price, the system allocates 70% of the load to the top three generator sets in terms of weight to maximize the benefit; while during the trough period of electricity price, the load ratio of generator sets with a high decay coefficient is reduced to 30% to reduce equipment wear. The load distribution strategy is sent to each generator set controller in real time through the plant-level monitoring system to dynamically adjust the steam turbine inlet valve opening and boiler combustion parameters to ensure that the output power precisely matches the target load. At the same time, the system introduces a load mutation constraint to limit the load change amplitude of a single generator set within a unit time to avoid mechanical stress fatigue caused by frequent peak shaving of the equipment.

[0095] When the environmental protection deviation threshold exceeds the preset limit, the system triggers an equipment maintenance cycle instruction. For example, if the flue gas particulate matter concentration exceeds the standard for three consecutive hours, it is determined that the dust removal equipment efficiency has declined, and an instruction for filter bag replacement or spray system maintenance is automatically generated. The maintenance instruction includes the maintenance type, execution time, and priority, and is associated with the equipment health status database to preferentially process the equipment that has the greatest impact on environmental protection indicators.

[0096] For turbine blade maintenance, the system generates a cleaning priority list based on historical temperature deviation data and vibration spectrum anomaly indices. For example, blades with a temperature deviation exceeding 5% and accompanied by high-frequency vibration are marked as first-level cleaning priority. The abnormal conditions of such blades have a greater impact on equipment performance and environmental protection indicators, and high-pressure water gun cleaning needs to be completed within 24 hours to quickly restore the normal operation state of the equipment; when the temperature deviation is between 3% - 5%, or although the temperature deviation is below 3% but the vibration spectrum anomaly index reaches a certain level, the blades are marked as second-level cleaning priority. The abnormal conditions of such blades are of medium severity, and professional chemical cleaning is required to be arranged within 48 hours to ensure the continuous and stable operation of the equipment; while blades with a deviation below 3% are marked as third-level priority and incorporated into the regular maintenance plan for processing according to the established maintenance cycle.

[0097] Maintenance instructions are automatically dispatched to the operation and maintenance team through the work order management system, and the execution progress is monitored in real time. Such a priority division and processing mechanism can reasonably arrange maintenance work according to the actual situation of the equipment, ensuring the efficient and stable operation of the thermal power plant under the premise of environmental protection compliance.

[0098] Integrate the fuel procurement plan adjustment instruction, the generator set load distribution strategy, and the equipment cleaning priority list into a unified set of operation management parameters. Send each parameter to the fuel dispatching system, the unit control system, and the maintenance management system through the data bus to ensure the coordinated execution of multiple systems. For example, when starting the high-calorific value fuel bin, synchronously adjust the load distribution weight of the corresponding unit, and associate the improvement of the maintenance priority of the dust removal equipment for that fuel bin. During the execution process, collect data on fuel consumption rate, unit output power, and environmental protection indicators in real time, and compare and analyze them with the expected goals. If the deviation exceeds the tolerance threshold (such as the load distribution error exceeds 5%), then trigger the parameter fine-tuning mechanism, such as dynamically increasing the load of the standby unit or temporarily adjusting the order of fuel bin activation. Finally, all adjustment results form a closed-loop feedback and are input into the multi-objective dynamic optimization model to provide an iterative basis for the next round of decision-making, realizing the full-cycle intelligent management of the thermal power plant operation.

[0099] In some instances, the above platform further includes:

[0100] A correction unit for iteratively correcting the above dynamic optimization parameters based on a preset feedback mechanism.

[0101] Exemplarily, the feedback mechanism first collects the actual operation data after the adjustment of the operation management parameters of the thermal power plant in real time through a distributed sensor network, a device monitoring system, and a market data interface. Specifically, it includes data such as the actual fuel consumption rate, the output power of the generator set, the concentration of flue gas particulate matter, and the equipment maintenance execution status. Denoise the original data. For example, use the moving window average method to eliminate the instantaneous fluctuation noise of the sensor, and ensure the temporal consistency of multi-source data through timestamp synchronization. The preprocessed data forms a standardized data set, providing a reliable input for subsequent deviation analysis.

[0102] Based on the preprocessed data, calculate the deviation between the actual value and the model prediction value of each dynamic optimization parameter. For example, compare the difference between the actual fuel consumption rate and the predicted value of the scheduling algorithm to calculate the inventory consumption deviation; analyze the matching error between the actual output power of the generator set and the load distribution strategy to generate the efficiency deviation; monitor the continuous deviation amount between the actual value of the environmental protection index and the environmental protection deviation threshold to quantify the emission control deviation. Further, evaluate the influence weight of the deviation on the operation target: too high inventory consumption deviation may lead to a sharp increase in procurement costs, and a continuous positive emission control deviation increases the risk of environmental protection penalties. By constructing a deviation-influence weight matrix, identify the key parameters that need to be corrected first.

[0103] According to the deviation evaluation results, the system adaptively corrects the core parameters of the multi-objective dynamic optimization model. For example, when the inventory consumption deviation of the fuel indicates that the prediction model underestimates the demand, automatically increase the safety inventory coefficient in the fuel scheduling algorithm and shorten the procurement cycle; if the power generation efficiency deviation shows that the actual loss of the unit is higher than the predicted value, adjust the temperature deviation weight in the calculation of the efficiency decay coefficient to strengthen the influence of the equipment health status on the weight. For the correction of the environmental protection deviation threshold, the system dynamically adjusts the coupling compensation coefficient of the cooling water flow and the temperature gradient in combination with the historical over-standard frequency and compensation effect, making the threshold setting closer to the actual working conditions. The corrected parameters take effect immediately and are marked with a version number and stored in the model parameter database.

[0104] After the parameter correction, the system starts a new round of multi-objective dynamic optimization, generates updated operation management parameters and executes the adjustment. At the same time, establish a verification cycle, collect the actual operation data under the new parameters, and compare the deviation change trend. If the deviation is reduced to the fault tolerance range after the parameter correction, it is determined that the correction is effective, and the parameter version is marked as a stable state; if the deviation is not improved or deteriorates, trigger a secondary correction process, such as introducing manual intervention rules or expanding the historical data training set to retrain the model. All correction records and verification results form a closed-loop knowledge base, providing an experience reference for subsequent iterations to ensure that the optimization model continuously approaches the global optimal solution.

[0105] In some instances, the above platform further includes:

[0106] The first construction unit is used to construct a first anomaly detection model based on the physical correlation between the plant temperature gradient and the cooling water flow rate among the above environmental parameters;

[0107] The second construction unit is used to construct a second anomaly detection model according to the time-domain correlation between the vibration spectrum data and the temperature deviation degree among the above equipment state parameters;

[0108] The calibration unit is used to trigger a data source location and sensor calibration instruction when the above first anomaly detection model or the above second anomaly detection model outputs an anomaly flag, and re-enter the calibrated data into the above multi-objective dynamic optimization model.

[0109] Exemplarily, a first anomaly detection model is constructed based on the physical correlation between the plant temperature gradient and the cooling water flow rate among the environmental parameters. The principle of the model is as follows: The cooling water flow rate directly affects the heat exchange efficiency of the plant. Insufficient flow rate will cause heat to not dissipate in time, thereby triggering an abnormal temperature gradient. Specifically, the model establishes a normal correlation curve between the temperature gradient and the cooling water flow rate through historical operation data. For example, at the rated flow rate, the temperature difference between the boiler area and the outlet of the cooling tower should be maintained within a preset range. During real-time monitoring, the system calculates the ratio of the current temperature gradient value (such as the difference between the temperature in the boiler area and the temperature at the outlet of the cooling tower) to the cooling water flow rate. If this ratio continuously exceeds the historical normal fluctuation range (for example, exceeding the threshold by 10% for three consecutive minutes), it is determined that the physical correlation is abnormal. At this time, the model outputs an anomaly flag and records the data characteristics during the abnormal period (such as a sudden drop in flow rate accompanied by a sharp rise in gradient), providing a basis for subsequent fault diagnosis.

[0110] A second anomaly detection model is constructed according to the time-domain correlation between the vibration spectrum data and the temperature deviation degree among the equipment state parameters. The model identifies the hidden deterioration of the equipment health state by analyzing the time-series correlation characteristics of the vibration signal and the temperature data. For example, when the turbine blade is fouled and the heat dissipation efficiency decreases, the amplitude of a specific frequency band in the vibration spectrum will increase periodically, and at the same time, the temperature deviation degree on the blade surface gradually rises. The model extracts features such as the root mean square value and peak factor of the vibration spectrum through a sliding time window and performs a correlation analysis with the temperature deviation degree in the same time period. If the correlation coefficient between the vibration characteristics and the temperature deviation degree is lower than the preset correlation threshold, it is determined that the time-domain correlation is abnormal and marked as a potential equipment fault.

[0111] When the first or second anomaly detection model outputs an anomaly flag, the system starts the data source localization process. For the anomalies of the first model, the system first verifies the real-time data consistency of the cooling water flow sensor and the temperature sensor: if the flow sensor shows normal while the temperature gradient is abnormal, a temperature sensor calibration instruction is triggered; if the flow data is abnormal while the temperature gradient meets the expectation, it is determined that the flowmeter is faulty, and a zero calibration or probe cleaning instruction for the electromagnetic flowmeter is triggered. For the anomalies of the second model, the system compares the vibration sensor data at different positions of the same device: if only the data of a single sensor is abnormal, the sensor is marked as the fault source, and a sensitivity calibration of the vibration accelerometer is triggered; if the data of multiple sensors is synchronously abnormal and the temperature deviation correlation is lost, it is determined that there is a mechanical fault in the device, and a focal length calibration of the thermal imaging module and an installation status check of the vibration sensor are triggered. The calibration instructions are automatically issued, and the operation and maintenance personnel are required to complete the operation within a limited time.

[0112] After calibration, the system re-collects the sensor data and verifies the data validity through a verification module. For example, after the calibration of the cooling water flow, it is required to satisfy that the ratio of the flow rate - temperature gradient returns to the normal historical range; after the calibration of the vibration sensor, it is necessary to ensure that the correlation coefficient between the spectral characteristics and the temperature deviation degree resumes to above the preset correlation threshold. After passing the verification, the system re-enters the calibrated data into the multi-objective dynamic optimization model to replace the data records during the abnormal period. At the same time, the model automatically updates the anomaly detection threshold according to the calibration results: if the current anomaly is caused by sensor drift, the fault tolerance range of the sensor is tightened; if it is caused by equipment deterioration, the weight coefficient of the correlation analysis is adjusted. All calibration records and model parameter update information are stored in the knowledge base to optimize the accuracy and response speed of subsequent anomaly detection, forming a closed-loop management of detection - calibration - optimization.

[0113] In some instances, the above platform further includes:

[0114] A judgment unit, configured to determine that the cooling system fails when it is detected that the temperature gradient in the above factory area is abnormal and the above temperature deviation degree is greater than the critical value;

[0115] A failure handling unit, configured to trigger a pre-start instruction for the standby cooling equipment in the case of the failure of the above cooling system;

[0116] An allocation unit, configured to re-allocate the consumption ratio of the low-calorific-value fuel based on the above pre-start instruction and the above fuel consumption priority to reduce the load of the generator set.

[0117] Exemplarily, when the temperature gradient in the plant area is abnormal and the temperature deviation of the turbine blade exceeds the critical value, the system determines that the cooling system has failed. Specifically, the abnormal temperature gradient in the plant area is detected by a distributed temperature sensor array: under normal operating conditions, the temperature difference between the boiler area and the outlet of the cooling tower should be maintained within a preset range. If the temperature difference shown by three consecutive groups of sensor data (such as the boiler area, the turbine unit area, and the inlet of the cooling tower) exceeds the threshold, a temperature gradient anomaly flag is triggered. At the same time, the thermal imaging module monitors the surface temperature of the turbine blade in real time. When it is detected that the temperature deviation of a single or multiple blades exceeds the critical value, and the amplitude of the low-frequency band in the vibration spectrum abnormally increases, the system determines that the heat dissipation efficiency of the cooling system has seriously decreased, and triggers a failure state alarm.

[0118] After the failure of the cooling system is determined, the system immediately triggers a pre-start command for the standby cooling equipment. The standby equipment includes an auxiliary cooling water pump, an emergency cooling tower, and a plate heat exchanger. The pre-start command is executed through the following steps: First, start the auxiliary cooling water pump to increase the cooling water circulation flow rate to make up for the insufficient flow rate of the main pump; Second, activate the fan system of the emergency cooling tower to enhance the heat dissipation capacity; Finally, switch part of the heat exchange load to the plate heat exchanger to share the pressure of the original cooling tower. The status of all standby equipment is monitored in real time by the PLC controller to ensure seamless connection of the start-up timing with the main system. For example, the auxiliary pump reaches the rated flow rate within 5 seconds, and the emergency fan runs at full speed within 10 seconds to avoid further deterioration of the temperature gradient.

[0119] Based on the pre-start command and the fuel consumption priority, the system dynamically adjusts the usage ratio of fuel types to reduce the load of the generator set. The fuel consumption priority is generated by the fuel scheduling optimization algorithm. Low calorific value fuels (such as lignite) are usually marked as low-cost and low-priority standby options. When the cooling system fails, the system performs the following operations: First, reduce the consumption rate of the high calorific value fuel bin (such as bituminous coal) to a safe level to reduce the heat generation per unit time; Second, increase the consumption priority of the low calorific value fuel bin, and increase its load ratio from 20% to 60%. Maintain the basic power supply by increasing the combustion amount of low calorific value fuel, and at the same time reduce the overall heat load; Finally, associate with the procurement plan adjustment module to generate an emergency replenishment order for low calorific value fuel to ensure that the inventory can continuously support the adjusted consumption strategy.

[0120] After fuel reallocation and the startup of the standby cooling equipment, the system coordinates the load of the generator sets in real time through the plant-level monitoring platform. Specifically, it includes: reducing the output of high-weight units to 70% of the rated power to reduce their cooling requirements; transferring part of the load to standby units with lower efficiency but lower cooling pressure; at the same time, adjusting the boiler combustion parameters (such as air-fuel ratio, air intake volume) to optimize the combustion efficiency of low-calorific-value fuels. During this period, the environmental protection constraint model continuously monitors the flue gas emission indicators. If the particulate matter concentration approaches the limit value due to fuel switching, the operating power of the dust removal equipment is synchronously increased to ensure environmental protection compliance. All adjustment instructions are sent in real time through the data bus to form a multi-dimensional collaborative control of cooling, fuel, load, and environmental protection until the cooling system is repaired and the temperature gradient returns to the normal range.

[0121] Please refer to Figure 2 , which is a schematic structural diagram of a smart operation and management system 100 for a thermal power plant provided by an embodiment of the present application, including the smart operation and management platform 10 of the thermal power plant as described in the first aspect.

[0122] Those skilled in the art should understand that the embodiments of the present application can provide methods, systems, or computer program products. Therefore, the present application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-readable storage media containing computer-readable program code.

[0123] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0124] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured product including an instruction device, and the instruction device implements the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0125] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 steps of the functions specified in one block or multiple blocks.

[0126] The embodiment of the present application also provides a computer program product, which includes computer software instructions. When the computer software instructions run on a processing device, the processing device is caused to execute Figure 1 the process of an intelligent platform for the operation and management of a thermal power plant in the corresponding embodiment.

[0127] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless manner. The computer-readable storage medium can be any available medium that the computer can store or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium, an optical medium, or a semiconductor medium, etc.

[0128] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0129] In several embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be in an electrical, mechanical, or other form.

[0130] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or distributed across multiple network units. Some or all of these units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0131] In addition, each functional unit in various embodiments of this application can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware and / or software functional units.

[0132] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device to execute all or part of the steps of the methods in various embodiments of this application.

[0133] The above embodiments are only used to illustrate the technical solutions of this application, rather than to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of various embodiments of this application.

[0134] Although the preferred embodiments of this specification have been described, those skilled in the art can make additional changes and modifications once they know the basic creative concept. Therefore, the appended claims are intended to be interpreted to include the preferred embodiments and all changes and modifications falling within the scope of this specification.

[0135] Obviously, those skilled in the art can make various changes and deformations to this specification without departing from the spirit and scope of this specification. Thus, if these modifications and deformations of this specification fall within the scope of the claims of this specification and their equivalent technologies, this specification is also intended to include these changes and deformations.

Claims

1. A smart platform for the operation and management of a thermal power plant, characterized in that, The platform includes: An acquisition unit for acquiring real-time operation data of a thermal power plant, where the real-time operation data includes environmental parameters, equipment status parameters, fuel inventory parameters, and power market fluctuation parameters; A generation unit for generating dynamic optimization parameters through a multi-objective dynamic optimization model based on the real-time operation data, where the dynamic optimization parameters include fuel consumption priority, power generation efficiency weight, and environmental protection deviation threshold; An adjustment unit for dynamically adjusting the operation management parameters of the thermal power plant according to the dynamic optimization parameters.

2. The platform according to claim 1, wherein The specific steps for acquiring the real-time operation data of the thermal power plant include: Collecting environmental parameters through a distributed sensor network, where the environmental parameters include plant area temperature gradient, flue gas particulate matter concentration, and cooling water flow rate; Acquiring vibration spectrum data of the generator set bearings and extracting the temperature deviation degree on the surface of the turbine blades through a thermal imaging module, and integrating the vibration spectrum data and the temperature deviation degree into equipment status parameters; Generating fuel inventory parameters based on historical fuel inventory consumption data; Generating power market fluctuation parameters based on a power prediction model, where the power market fluctuation parameters include real-time electricity price volatility and regional electricity demand forecast values.

3. The platform according to claim 2, wherein The specific steps for generating dynamic optimization parameters through a multi-objective dynamic optimization model based on the real-time operation data include: Inputting the flue gas particulate matter concentration into a preset environmental protection constraint model to calculate the real-time deviation amount between the current flue gas particulate matter concentration and the preset emission standard; Dynamically compensating the real-time deviation amount based on the coupling relationship between the cooling water flow rate and the plant area temperature gradient to generate an environmental protection deviation threshold; Calculating the efficiency decay coefficient of the generator set according to the vibration spectrum data and the temperature deviation degree; Constructing a power generation efficiency revenue function based on the generator set efficiency decay coefficient and the real-time electricity price volatility to determine the power generation efficiency weight; Generating a fuel consumption priority through a fuel scheduling optimization algorithm based on the fuel inventory parameters and the regional electricity demand forecast values.

4. The platform according to claim 1, characterized in that, The specific steps for dynamically adjusting the operation management parameters of the thermal power plant according to the dynamic optimization parameters include: Dynamically allocating the real-time consumption rates of multiple fuel bins based on the fuel consumption priority and generating an adjustment instruction for the fuel procurement plan; Optimizing the load distribution strategy of the generator sets according to the power generation efficiency weight so that the high-weight generator sets respond to the power demand corresponding to the real-time electricity price volatility first; When the environmental protection deviation threshold exceeds the preset threshold, triggering an equipment maintenance cycle instruction; Generating a cleaning priority list for the turbine blades based on the equipment maintenance cycle instruction; Integrating the adjustment instruction for the fuel procurement plan, the load distribution strategy of the generator sets, and the cleaning priority list into the dynamic adjustment result of the operation management parameters.

5. The platform according to claim 1, characterized in that, The platform further includes: A correction unit for iteratively correcting the dynamic optimization parameters based on a preset feedback mechanism.

6. The method according to claim 2, wherein The platform further includes: A first construction unit for constructing a first anomaly detection model based on the physical correlation between the plant area temperature gradient and the cooling water flow rate in the environmental parameters; A second construction unit, configured to construct a second anomaly detection model according to the time-domain correlation between the vibration spectrum data and the temperature deviation degree in the device state parameters; A calibration unit, configured to trigger a data source location and sensor calibration instruction when the first anomaly detection model or the second anomaly detection model outputs an anomaly flag, and re-input the calibrated data into the multi-objective dynamic optimization model.

7. The platform according to claim 3, characterized in that, The platform further includes: A judgment unit, configured to determine that the cooling system fails when it is detected that the plant temperature gradient is abnormal and the temperature deviation degree is greater than a critical value; A failure handling unit, configured to trigger a pre-start instruction for a standby cooling device in the case of the failure of the cooling system; An allocation unit, configured to re-allocate the consumption ratio of low calorific value fuel based on the pre-start instruction and the fuel consumption priority to reduce the load of the generator set.

8. A smart operation and management system for a thermal power plant, characterized in that, It includes a smart platform for the operation and management of a thermal power plant according to any one of claims 1-7.

Images