Intelligent operation management system for thermal power plant

Abstract

The invention discloses a thermal power plant intelligent operation management system. Comprising a data acquisition module used for acquiring cost data, a data processing module used for processing the acquired data, a data analysis module used for analyzing the obtained data, a cost calculation module used for calculating real-time cost, a cost analysis module used for analyzing the cost, and a prediction module used for predicting the purchase quantity. The resource configuration module is used for obtaining a resource configuration optimization scheme according to a cost analysis result; and the data acquisition module, the data processing module, the data analysis module, the cost calculation module, the cost analysis module, the resource configuration module and the prediction module are respectively connected with a central control system. According to the thermal power plant intelligent operation management system provided by the invention, the cost data can be deeply analyzed in combination with the actual situation, a corresponding optimization scheme is provided, and intelligent operation management in the cost aspect is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent management, and in particular relates to an intelligent operation and management system for a thermal power plant. Background Art

[0002] A thermal power plant, referred to as a thermal power plant, is a factory that uses coal, oil, and natural gas as fuel to produce electricity. The power industry is the basic industry of the national economy, driving the continuous development of the social economy. Electricity safety production is a process-based and continuous production process, so it is extremely important to ensure the stable operation of the power plant. At present, power companies are facing great cost pressure. In order to effectively improve the management level of power generation companies, save energy, and improve the competitiveness of companies, it is necessary to analyze the real-time cost of thermal power plants.

[0003] The real-time cost of a power plant includes real-time fuel cost, real-time auxiliary power consumption cost, environmental protection cost, sewage cost, maintenance cost and fixed cost per kilowatt-hour, of which fuel cost accounts for as much as 70% to 80%. Reducing coal-fired costs is an important task for thermal power plants. Real-time cost analysis of thermal power plants can provide effective data support for enterprises, and can find out which link has excessive costs, and then optimize resource allocation, thereby reducing costs and improving corporate competitiveness. On the other hand, the resources of enterprises are limited, whether human or material resources, so the best resource allocation is required to face various conditions in the operation of the unit. In summary, in the operation and management process of thermal power plants, cost analysis can effectively find out the unreasonable cost expenditure of enterprises, thereby realizing resource allocation optimization. Therefore, there is a need for an intelligent business management system with automatic cost analysis, and the present invention solves this technical problem. Summary of the invention

[0004] The present invention provides an intelligent operation and management system for a thermal power plant, which can conduct in-depth analysis of cost data in combination with actual conditions, and provide corresponding optimization solutions, thereby realizing intelligent operation and management of costs.

[0005] A smart operation and management system for a thermal power plant, comprising a data acquisition module for acquiring cost data, a data processing module for processing the acquired data, a data analysis module for analyzing the acquired data, a cost calculation module for calculating real-time costs, a cost analysis module for analyzing costs, a prediction module for predicting purchase quantities, and a resource allocation module for deriving a resource allocation optimization plan based on cost analysis results. The data acquisition module, the data processing module, the data analysis module, the cost calculation module, the cost analysis module, the resource allocation module, and the prediction module are respectively connected to a central control system, the central control system is connected to a display module and a decision module, the decision module is used to calculate the cost required for procurement, and the data analysis module is used to analyze the remaining quantity of fuel on a certain day based on the acquired data.

[0006] Furthermore, the data collection module is used to collect data on fuel inventory and procurement, as well as data related to electricity costs, real-time costs, and coal yard operations;

[0007] The data processing module is used to integrate and process the collected data to facilitate subsequent data analysis;

[0008] The cost calculation module calculates the real-time cost, which includes variable cost and fixed cost. The variable cost includes fuel cost, sewage cost, maintenance cost, auxiliary power consumption cost and environmental protection cost. The fixed cost includes the annual average electricity cost.

[0009] The cost analysis module analyzes the proportion of various costs and provides comparative analysis results of various costs with historical cost data;

[0010] The resource allocation module will derive a corresponding optimization plan based on the results of the cost analysis to guide operators to perform optimization operations;

[0011] The data analysis module analyzes the data, calculates the average calorific value of the inventory fuel, and calculates the remaining amount of fuel on a certain day based on the average calorific value, and calculates the cost required for procurement through the decision module based on the prediction results of the prediction module.

[0012] Furthermore, the data acquisition module collects historical fuel purchase information, including purchase records, prices, purchase quantities and purchase times, and collects fuel consumption data, including fuel consumption and inventory, and collects supply chain information, including supplier information records, fuel quality and fulfillment rates, as well as real-time cost data as well as coal yard operation data and unit operation data.

[0013] Furthermore, the data processing module can merge data from different sources to create a unified view, specifically by combining different data sets D1, D2, ..., D n Merge to achieve data integration:

[0014]

[0015] Among them, D i represents all data sets, f(D i ) represents the merging operation of the data sets, and then extracting the data from the original data source:

[0016]

[0017] Among them, E represents the operation extracted from the data source, and D raw represents the original data after extraction, D source Represents a data source;

[0018] Then perform the conversion on the obtained data:

[0019] D transfromed =T(D raw )={t(d)|d∈D raw}

[0020] Where T represents the conversion operation, D transfromed Represents the transformed data;

[0021] Then load the transformed data into the database:

[0022] D final =L(D transfromed )

[0023] Among them, L represents the load operation, D final Represents the data loaded into the database.

[0024] Furthermore, the calculation of the calorific value by the data analysis module includes:

[0025] The time period from the day after the last fuel delivery to the day of the next fuel delivery is denoted as k, and the remaining fuel inventory in the previous stage is denoted as X k-1 The average calorific value of the remaining fuel is expressed as Q k-1 ;

[0026] The average calorific value Q of the total amount of fuel in stage k k It is expressed as:

[0027]

[0028] in, represents the sum of the calorific values ​​of the different fuels purchased in stage k, P cfr represents the fuel redemption rate, x i，k represents the fuel purchase quantity in stage k, Q i Indicates the calorific value of the fuel at this stage, X k，0 It indicates the sum of the remaining quantity in the previous stage and the fuel quantity in this stage.

[0029] Furthermore, the process of the data analysis module calculating the remaining amount of fuel on a certain day according to the average calorific value includes:

[0030] X a It is expressed as the inventory on day a in stage k, X a-1 represents the inventory volume on the day before day a, then X a The calorific value can be expressed as the total calorific value Q of the previous day k X a-1 , minus the calorific value NE consumed by power generation on that day a *z, and then divided by the average calorific value of the stored fuel:

[0031]

[0032] Where N represents the fuel consumption rate per kilowatt-hour, E a It represents the electricity generation on that day, and z represents the calorific value per kilogram of fuel.

[0033] Furthermore, the prediction process of the prediction module is as follows:

[0034] Represent fuel consumption data through time series analysis:

[0035] C(t)=a*C(t-1)+∈(t)

[0036] Among them, C(t) is the fuel consumption at time t, is the autoregressive coefficient, and ∈(t) is the error term;

[0037] Establish a prediction model and use the autoregressive integrated moving average model to express it:

[0038]

[0039] in, θ1, θ q are model parameters, e(t) represents the white noise error term;

[0040] To take seasonality into account, the seasonally decomposed time series is used to adjust the trend:

[0041] C(t)=T(t)+S(t)+R(t)

[0042] Among them, T(t) is the trend component, S(t) is the seasonal component, and R(t) is the residual.

[0043] Furthermore, the decision-making process of the decision-making module includes:

[0044] Obtain the required fuel consumption C(t) and use it as the amount of fuel to be purchased in the next stage; multiply the fuel amount by the unit fuel cost x to obtain the purchase cost:

[0045] C(t)=C(t)*x

[0046] Among them, C(x) represents the purchase cost.

[0047] Furthermore, the analysis process of the cost analysis module includes: obtaining the cost composition ratio of each aspect according to the results calculated by the cost calculation module; comparing the current ratio with the historical ratio to obtain a comparison result; when the proportion of a certain cost component is higher than the historical statistical level by a certain degree, it is considered that this cost composition is unreasonable and resource optimization allocation is required.

[0048] Furthermore, the configuration method of the resource configuration module includes:

[0049] When fuel costs are too high, a strategy of burning low-priced coal is proposed while ensuring safe operation, and a plan for purchasing low-priced coal is proposed to reduce fuel costs and meet the power plant's inventory requirements;

[0050] When the power consumption cost of the auxiliary machine is too high, the main part of the power consumption is found through the comparison of the historical power consumption of each auxiliary machine, and the following solutions are proposed: energy-saving optimization is carried out for this part to reduce the power consumption cost;

[0051] When the environmental protection cost is too high, the following solution is proposed: on the basis of ensuring that the environmental protection does not exceed the standard, by appropriately increasing the emission concentration of NOx, SO2 and dust, reducing the use of ammonia and limestone slurry, and thus reducing the cost of ammonia and limestone slurry;

[0052] When the pollution discharge cost is too high, the following solutions are proposed: take environmental protection emission reduction measures to reduce the emission level of pollutants, reduce the assessment of the unit, and reduce the load operation when necessary;

[0053] When maintenance costs are too high, the following solution is proposed: reduce equipment loss and maintenance costs by strengthening equipment optimization and inspection measures.

[0054] The technical effects of the present invention are as follows:

[0055] (1) This solution uses the data collection module to collect data related to electricity costs, real-time costs, and coal yard operations, which are then processed by the data processing module. The cost calculation module then calculates the costs of each aspect. The cost analysis module analyzes the cost composition ratio of each aspect based on the calculation results. The resource allocation module provides a resource allocation optimization solution based on the aspects corresponding to the higher proportion of the cost composition ratio, thereby achieving cost control and realizing smart business management.

[0056] (2) When the fuel cost is too high, the resource allocation optimization module will provide a low-cost procurement plan. The specific process is as follows: the data acquisition module collects historical procurement information, fuel consumption, inventory and other information to provide data support for subsequent data analysis. The data processed by the data processing module will be transmitted from the central control system to the data analysis module and the prediction module. The data analysis module is used to query the inventory quantity on a certain day. The prediction module can predict the fuel consumption within a period of time based on historical data, and the decision module can calculate the procurement cost based on the fuel consumption, thereby realizing intelligent management of fuel procurement quantity and cost.

[0057] (3) This solution can calculate the inventory quantity of a certain day based on the calorific value of the fuel. When the recorded inventory quantity is wrong, this method can be used for calculation, and the staff does not need to count and record the remaining fuel quantity in the inventory every day, making it easier to obtain the remaining fuel quantity;

[0058] (4) The prediction module can be used to predict fuel demand. Compared with traditional manual experience, it improves the accuracy of prediction and reduces labor costs, thereby improving operational efficiency, facilitating more efficient inventory management, and facilitating the intelligent operation of thermal power plants. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a connection block diagram of the present invention.

[0060] Figure 2 It is a flowchart of the workflow of the present invention. DETAILED DESCRIPTION

[0061] The technical solution of the present invention will be clearly and completely described below in conjunction with specific embodiments and drawings.

[0062] See also Figure 1 , Figure 2A smart management system for a thermal power plant includes a data acquisition module for collecting cost data, a data processing module for processing the collected data, a data analysis module for analyzing the obtained data, a cost calculation module for calculating real-time costs, a cost analysis module for analyzing costs, a prediction module for predicting the purchase quantity, and a resource allocation module for deriving a resource allocation optimization plan based on the cost analysis results. The data acquisition module, the data processing module, the data analysis module, the cost calculation module, the cost analysis module, the resource allocation module, and the prediction module are respectively connected to the central control system, and the central control system is connected to the display module and the decision module. The decision module is used to calculate the cost required for procurement, and the data analysis module is used to analyze the remaining amount of fuel on a certain day based on the obtained data. The display module can display the corresponding data.

[0063] Furthermore, the data collection module is used to collect data on fuel inventory and procurement, as well as data related to electricity costs, real-time costs, and coal yard operations;

[0064] The data processing module is used to integrate and process the collected data to facilitate subsequent data analysis;

[0065] The cost calculation module calculates the real-time cost, which includes variable cost and fixed cost. Variable cost includes fuel cost, sewage cost, maintenance cost, auxiliary power consumption cost and environmental protection cost. Fixed cost includes annual average electricity cost.

[0066] The cost analysis module analyzes the proportion of various costs and provides comparative analysis results of various costs and historical cost data;

[0067] The resource allocation module will derive the corresponding optimization plan based on the results of the cost analysis to guide operators to perform optimization operations;

[0068] The data analysis module analyzes the data, calculates the average calorific value of the inventory fuel, and calculates the remaining quantity of fuel on a certain day based on the average calorific value. Based on the prediction results of the prediction module, the decision module calculates the cost required for procurement.

[0069] Among them, fuel cost data includes coal supply data, coal price data and coal quality data, which are obtained through the SIS system;

[0070] Auxiliary power consumption cost data include auxiliary current data, auxiliary voltage data and auxiliary power factor data. The current and voltage data are obtained through the SIS system, and the power factor is the default value; the pollution data include NOx emission concentration, SO2 emission concentration, dust emission concentration and the cost of exceeding the emission standard of each pollutant;

[0071] Environmental protection cost data include ammonia injection costs and limestone slurry usage costs. The ammonia injection costs are obtained by multiplying the ammonia injection flow rate by the ammonia price, and the limestone slurry usage is obtained by multiplying the limestone slurry flow rate by its price. The flow data are all taken from the SIS system.

[0072] The maintenance cost data is the average maintenance cost per kWh of thermal power plants. The annual maintenance cost is obtained based on the average statistics of previous years, and the annual power generation is obtained based on the power generation plan. The data sources are all from the ERP system.

[0073] Fixed cost is the average value of fixed cost per kWh of thermal power plant. The annual fixed cost is obtained by allocating the fixed cost of the units. The data source is the ERP system.

[0074] The coal yard operation data includes the coal storage quantity in the coal yard, the coal quality ratio in the coal yard, etc. The coal quality in the coal yard includes the calorific value, sulfur content, volatile matter, moisture content and ash content of the stored coal. The above information can be collected by recording and uploading various information by personnel from various departments.

[0075] Furthermore, the data collection module collects historical fuel purchase information, including purchase records, prices, purchase quantities and purchase times, and collects fuel consumption data, including fuel consumption and inventory, and collects supply chain information, including supplier information records, fuel quality and fulfillment rates, as well as real-time cost data as well as coal yard operation data and unit operation data.

[0076] Furthermore, the data processing module can merge data from different sources to create a unified view, specifically by combining different data sets D1, D2, ..., D n Merge to achieve data integration:

[0077]

[0078] Among them, D i represents all data sets, f(D i ) represents the merging operation of the data sets, and then extracting the data from the original data source:

[0079]

[0080] Among them, E represents the operation extracted from the data source, and D raw represents the original data after extraction, D source Represents a data source;

[0081] Then perform the conversion on the obtained data:

[0082] D transfromed =T(D raw )={t(d)|d∈Draw}

[0083] Where T represents the conversion operation, D transfromed Represents the transformed data;

[0084] Then load the transformed data into the database:

[0085] D final =L(D transfromed )

[0086] Among them, L represents the load operation, D final Represents the data loaded into the database.

[0087] Furthermore, the calculation of the calorific value by the data analysis module includes:

[0088] The time period from the day after the last fuel delivery to the day of the next fuel delivery is denoted as k, and the remaining fuel inventory in the previous stage is denoted as X k-1 The average calorific value of the remaining fuel is expressed as Q k-1 ;

[0089] The average calorific value Q of the total amount of fuel in stage k k It is expressed as:

[0090]

[0091] in, represents the sum of the calorific values ​​of the different fuels purchased in stage k, P cfr represents the fuel redemption rate, x i，k represents the fuel purchase quantity in stage k, Q i Indicates the calorific value of the fuel at this stage, X k，0 It indicates the sum of the remaining quantity in the previous stage and the fuel quantity in this stage.

[0092] Furthermore, the process of the data analysis module calculating the remaining amount of fuel on a certain day according to the average calorific value includes:

[0093] X a It is expressed as the inventory on day a in stage k, X a-1 represents the inventory volume on the day before day a, then X a The calorific value can be expressed as the total calorific value Q of the previous day k X a-1 , minus the calorific value NE consumed by power generation on that day a *z, and then divided by the average calorific value of the stored fuel:

[0094]

[0095] Where N represents the fuel consumption rate per kilowatt-hour, Ea It represents the electricity generation on that day, and z represents the calorific value per kilogram of fuel.

[0096] Furthermore, the prediction process of the prediction module is as follows:

[0097] Represent fuel consumption data through time series analysis:

[0098] C(t)=a*C(t-1)+∈(t)

[0099] Among them, C(t) is the fuel consumption at time t, is the autoregressive coefficient, and ∈(t) is the error term;

[0100] Establish a prediction model and use the autoregressive integrated moving average model to express it:

[0101]

[0102] in, θ1, θ q are model parameters, e(t) represents the white noise error term;

[0103] To take seasonality into account, the seasonally decomposed time series is used to adjust the trend:

[0104] C(t)=T(t)+S(t)+R(t)

[0105] Among them, T(t) is the trend component, S(t) is the seasonal component, and R(t) is the residual.

[0106] Furthermore, the decision-making process of the decision-making module includes:

[0107] Obtain the required fuel consumption C(t) and use it as the amount of fuel to be purchased in the next stage; multiply the fuel amount by the unit fuel cost x to obtain the purchase cost:

[0108] C(t)=C(t)*x

[0109] Among them, C(x) represents the purchase cost.

[0110] Furthermore, the analysis process of the cost analysis module includes: obtaining the proportion of cost components in various aspects according to the results calculated by the cost calculation module; comparing the current proportion with the historical proportion to obtain a comparison result; when the proportion of a certain cost component is higher than the historical statistical level by a certain degree, it is considered that this cost component is unreasonable and resource optimization allocation is required.

[0111] The specific degree of excess can be set by the staff. When it is higher than the set value, it is considered unreasonable and resource optimization configuration is required.

[0112] Specifically, regarding the cost composition ratio of each part, you can refer to the following content: the sum of the cost ratios of each aspect is 100%, which is composed of the cost ratios of each aspect. The cost ratio of each aspect is a percentage of the total cost. Through the corresponding percentages, you can understand the cost ratio of the corresponding aspect in each aspect of the thermal power plant.

[0113] Furthermore, the configuration methods of the resource configuration module include:

[0114] When the fuel cost is too high, a strategy of burning low-priced coal is proposed under the premise of ensuring safe operation, and a plan for purchasing low-priced coal is proposed to reduce fuel costs and meet the inventory requirements of power plants; the specific calculation process of the specific purchasing plan has been given in the above content, which will not be detailed here;

[0115] When the power consumption cost of the auxiliary machine is too high, the main part of the power consumption is found by comparing the historical power consumption of each auxiliary machine, and the following solution is proposed: energy-saving optimization is carried out for this part to reduce the power consumption cost; the solution given by the resource configuration module is the above content. As for how to perform energy-saving optimization, the staff can perform specific operations. The solution given by the resource configuration module only indicates that this part needs to be energy-saving optimized; technical personnel in this field can also preset corresponding optimization methods and contents for different parts in advance. When the energy-saving optimization is required for the subsequent detection of the policy part, the resource configuration module can directly call the preset content at that time to display it, so that the staff can directly operate according to the corresponding content. The other solutions mentioned below can be implemented in the above manner and will not be described in detail here;

[0116] When the environmental protection cost is too high, the following solution is proposed: on the basis of ensuring that the environmental protection does not exceed the standard, by appropriately increasing the emission concentration of NOx, SO2 and dust, reducing the use of ammonia and limestone slurry, and thus reducing the cost of ammonia and limestone slurry;

[0117] When the pollution discharge cost is too high, the following solutions are proposed: take environmental protection emission reduction measures to reduce the emission level of pollutants, reduce the assessment of the unit, and reduce the load operation when necessary;

[0118] When maintenance costs are too high, the following solution is proposed: reduce equipment loss and maintenance costs by strengthening equipment optimization and inspection measures.

[0119] The working principle of the present invention is as follows:

[0120] This solution uses the data collection module to collect data related to electricity costs, real-time costs, and coal yard operations, and the data is processed by the data processing module. After that, the cost calculation module calculates the costs of various aspects. The cost analysis module analyzes the cost composition ratio of various aspects based on the calculation results. The resource allocation module provides resource allocation optimization solutions based on the aspects corresponding to the higher proportion of the cost composition ratio, thereby achieving cost control and realizing intelligent operation and management;

[0121] As for coal procurement, this solution uses the data acquisition module to collect historical procurement information, fuel consumption, inventory and other information. The collection of this information can be achieved by uploading and entering historical records to provide data support for subsequent data analysis and other aspects. The data processing module will integrate and ERT the data, that is, extract, convert, extract and load the data. The conversion extraction includes data cleaning, formatting and reconstruction, thereby ensuring data consistency in this way. The data processed by the data processing module will be transmitted by the central control system to the data analysis module and the prediction module. The data analysis module is used to query the fuel inventory quantity on a certain day. The prediction module can predict the fuel consumption within a period of time based on the collected historical data, and use it as the quantity to be purchased, and the decision-making module can calculate the purchase cost based on the fuel consumption, thereby realizing automatic calculation, realizing the smart operation of thermal power plants, and the management of the inventory fuel quantity.

[0122] The above embodiments are only preferred embodiments of the present invention. Those skilled in the art can derive other embodiments from the above embodiments without creative work. Therefore, this application protects not only the above embodiments, but also the scope consistent with the principles and features of this application.

Claims

1. A smart management system for a thermal power plant, characterized in that: It includes a data acquisition module for acquiring cost data, a data processing module for processing the acquired data, a data analysis module for analyzing the acquired data, a cost calculation module for calculating real-time cost, a cost analysis module for analyzing cost, a prediction module for predicting purchase quantity, and a resource allocation module for deriving a resource allocation optimization plan according to the cost analysis result. The data acquisition module, the data processing module, the data analysis module, the cost calculation module, the cost analysis module, the resource allocation module and the prediction module are respectively connected to a central control system, the central control system is connected to a display module and a decision module, the decision module is used to calculate the cost required for purchase, and the data analysis module is used to analyze the remaining quantity of fuel on a certain day according to the acquired data.

2. The intelligent operation and management system for a thermal power plant according to claim 1, characterized in that: The data collection module is used to collect data on fuel inventory and procurement, as well as data related to electricity costs, real-time costs, and coal yard operations; The data processing module is used to integrate and process the collected data to facilitate subsequent data analysis; The cost calculation module calculates the real-time cost, which includes variable cost and fixed cost. The variable cost includes fuel cost, sewage cost, maintenance cost, auxiliary power consumption cost and environmental protection cost. The fixed cost includes the annual average electricity cost. The cost analysis module analyzes the proportion of various costs and provides comparative analysis results of various costs with historical cost data; The resource allocation module will derive a corresponding optimization plan based on the results of the cost analysis to guide operators to perform optimization operations; The data analysis module analyzes the data, calculates the average calorific value of the inventory fuel, and calculates the remaining amount of fuel on a certain day based on the average calorific value, and calculates the cost required for procurement through the decision module based on the prediction results of the prediction module.

3. The intelligent operation and management system of a thermal power plant according to claim 2, characterized in that: The data acquisition module collects historical fuel purchase information, including purchase records, prices, purchase quantities and purchase times, and collects fuel consumption data, including fuel consumption and inventory, and collects supply chain information, including supplier information records, fuel quality and fulfillment rates, as well as real-time cost data and coal yard operation data and unit operation data.

4. The intelligent operation and management system of a thermal power plant according to claim 2, characterized in that: The data processing module can merge data from different sources to create a unified view, specifically, different data sets D1, D2, ..., D n Merge to achieve data integration: Among them, D i represents all data sets, f(D i ) represents the merging operation of the data sets, and then extracting the data from the original data source: Among them, E represents the operation extracted from the data source, and D raw represents the original data after extraction, D source Represents a data source; Then perform the conversion on the obtained data: D transfromed =T(D raw )={t(d)|d∈D raw } Where T represents the conversion operation, D transfromed Represents the transformed data; Then load the transformed data into the database: D final =L(D transfromed ) Among them, L represents the load operation, D final Represents the data loaded into the database.

5. The intelligent operation and management system of a thermal power plant according to claim 2, characterized in that: The calculation of the calorific value by the data analysis module includes: The time period from the day after the last fuel delivery to the day of the next fuel delivery is denoted as k, and the remaining fuel inventory in the previous stage is denoted as X k-1 The average calorific value of the remaining fuel is expressed as Q k-1 ; The average calorific value Q of the total amount of fuel in stage k k It is expressed as: in, represents the sum of the calorific values ​​of the different fuels purchased in stage k, P cfr represents the fuel redemption rate, x i，k represents the fuel purchase quantity in stage k, Q i Indicates the calorific value of the fuel at this stage, X k，0 It indicates the sum of the remaining quantity in the previous stage and the fuel quantity in this stage.

6. The intelligent operation and management system of a thermal power plant according to claim 5, characterized in that: The process of the data analysis module calculating the remaining amount of fuel on a certain day according to the average calorific value includes: X a It is expressed as the inventory on day a in stage k, X a-1 represents the inventory volume on the day before day a, then X a The calorific value can be expressed as the total calorific value Q of the previous day k X a-1 , minus the calorific value NE consumed by power generation on that day a *z, and then divided by the average calorific value of the stored fuel: Where N represents the fuel consumption rate per kilowatt-hour, E a It represents the electricity generation on that day, and z represents the calorific value per kilogram of fuel.

7. The intelligent operation and management system of a thermal power plant according to claim 2, characterized in that: The prediction process of the prediction module is as follows: Represent fuel consumption data through time series analysis: C(t)=a*C(t-1)+∈(t) Among them, C(t) is the fuel consumption at time t, is the autoregressive coefficient, and ∈(t) is the error term; Establish a prediction model and use the autoregressive integrated moving average model to express it: in, θ1, θ q are model parameters, e(t) represents the white noise error term; To take seasonality into account, the seasonally decomposed time series is used to adjust the trend: C(t)=T(t)+S(t)+R(t) Among them, T(t) is the trend component, S(t) is the seasonal component, and R(t) is the residual.

8. The intelligent operation and management system of a thermal power plant according to claim 7, characterized in that: The decision-making process of the decision-making module includes: Obtain the required fuel consumption C(t) and use it as the amount of fuel to be purchased in the next stage; multiply the fuel amount by the unit fuel cost x to obtain the purchase cost: C(t)=C(t)*x Among them, C(x) represents the purchase cost.

9. The intelligent operation and management system of a thermal power plant according to claim 2, characterized in that: The analysis process of the cost analysis module includes: obtaining the cost composition ratio of each aspect according to the result calculated by the cost calculation module; comparing the current ratio with the historical ratio to obtain the comparison result; when the proportion of a certain cost composition is higher than the historical statistical level by a certain degree, it is considered that this cost composition is unreasonable and resource optimization allocation is required.

10. The intelligent operation and management system of a thermal power plant according to claim 2, characterized in that: The configuration method of the resource configuration module includes: When fuel costs are too high, a strategy of burning low-priced coal is proposed while ensuring safe operation, and a plan for purchasing low-priced coal is proposed to reduce fuel costs and meet the power plant's inventory requirements; When the power consumption cost of the auxiliary machine is too high, the main part of the power consumption is found through the comparison of the historical power consumption of each auxiliary machine, and the following solutions are proposed: energy-saving optimization is carried out for this part to reduce the power consumption cost; When the environmental protection cost is too high, the following solution is proposed: on the basis of ensuring that the environmental protection does not exceed the standard, by appropriately increasing the emission concentration of NOx, SO2 and dust, reducing the use of ammonia and limestone slurry, and thus reducing the cost of ammonia and limestone slurry; When the pollution discharge cost is too high, the following solutions are proposed: take environmental protection emission reduction measures to reduce the emission level of pollutants, reduce the assessment of the unit, and reduce the load operation when necessary; When maintenance costs are too high, the following solution is proposed: reduce equipment loss and maintenance costs by strengthening equipment optimization and inspection measures.

Images