Thermal power generating unit deep peak regulation energy consumption analysis method

Abstract

The invention provides a thermal power generating unit deep peak regulation energy consumption analysis method, which relates to the technical field of electrical energy and comprises the following steps: monitoring unit equipment in real time to obtain key equipment data and transmitting the key equipment data to a data management system; the data management system evaluates the overall efficiency of the thermal power generating unit based on the received key equipment data to obtain an energy consumption evaluation result; performing thermal efficiency prediction and load optimization analysis on the thermal power generating unit, and determining a real-time adjustment strategy to optimize and adjust the thermal power generating unit in combination with an energy consumption evaluation result; a dynamic efficiency map is created. Key equipment data are collected in real time and transmitted to a data management system; the data management system performs energy consumption evaluation, thermal efficiency prediction and load optimization analysis according to the key equipment data to determine a real-time adjustment strategy to optimize and adjust the thermal power generating unit; the dynamic efficiency map is created, the energy consumption state of the thermal power generating unit under various loads and deep adjustment is displayed, fine management of energy consumption in the thermal power generation process can be achieved, and the energy utilization efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electric energy, and in particular to a method for analyzing energy consumption of deep peak regulation of thermal power units. Background Art

[0002] In recent years, traditional thermal power generation systems have often lacked effective energy consumption monitoring and optimization methods, resulting in significant energy waste and low operational efficiency. The rapid development of the Internet of Things, cloud computing, and artificial intelligence technologies has provided new solutions for energy consumption management in thermal power generation systems. However, existing technologies are mostly limited to single-step monitoring or simple data analysis, lacking systematic energy consumption management methods and intelligent optimization strategies. Therefore, achieving refined energy consumption management in thermal power generation and improving energy efficiency has become a major research focus.

[0003] Therefore, the present invention provides a method for analyzing energy consumption of deep peak regulation of thermal power units. Summary of the Invention

[0004] The present invention provides a method for analyzing energy consumption during deep peak regulation of thermal power units, which is used to collect key equipment data in real time and transmit it to a data management system; the data management system performs energy consumption evaluation, thermal efficiency prediction and load optimization analysis based on the key equipment data to determine a real-time adjustment strategy to optimize and adjust the thermal power units; and a dynamic efficiency map is created to display the energy consumption status of the thermal power units under various loads and deep regulation, thereby realizing refined management of energy consumption during thermal power generation and improving energy utilization efficiency.

[0005] The present invention provides a method for analyzing energy consumption of deep peak regulation of thermal power units, comprising:

[0006] Step 1: Use the set monitoring equipment to monitor the key equipment data of the unit in real time and transmit it to the data management system;

[0007] Step 2: The data management system evaluates the overall efficiency of the thermal power unit based on the received key equipment data and obtains the energy consumption evaluation results;

[0008] Step 3: Predict the thermal efficiency of the current thermal power unit and obtain the thermal efficiency prediction result;

[0009] Step 4: Combining the thermal efficiency prediction results with the energy consumption assessment results to perform load optimization analysis and generate a real-time adjustment strategy to optimize the thermal power unit;

[0010] Step 5: Create a dynamic efficiency map to show the energy consumption status of thermal power units under various loads and deep regulation.

[0011] Preferably, the data management system evaluates the overall efficiency of the thermal power unit based on the received key equipment data to obtain energy consumption evaluation results, including:

[0012] extracting a first power generation amount, a first grid input power, and a first plant power consumption of a thermal power unit within a preset time period from a data management system;

[0013] The first power generation, the first grid input power, and the first plant power consumption are combined to calculate a unit efficiency evaluation coefficient, and output it as an energy consumption evaluation result;

[0014] Extracting a first fuel consumption and a first power generation amount of the thermal power unit within a preset time period from a data management system;

[0015] The heat-to-electricity conversion efficiency is calculated based on the first fuel consumption and the first power generation, and is output as an energy consumption evaluation result.

[0016] Preferably, the calculation formula of the unit efficiency evaluation coefficient is as follows:

[0017] Where p1 is the unit efficiency evaluation coefficient; d0 is the first power generation; d1 is the first power consumption; d r It represents the first grid input power; δ represents the efficiency compensation learning factor.

[0018] Preferably, thermal efficiency prediction is performed on the current thermal power unit to obtain a thermal efficiency prediction result, including:

[0019] Based on the principles of thermodynamics, determine the corresponding thermal efficiency calculation formula for key operating processes;

[0020] Extract a preset amount of historical operating data of thermal power units and corresponding historical efficiency parameters, combine them with the thermal efficiency calculation formula, and train a neural network to obtain a thermal efficiency model;

[0021] The operating parameters of the first unit of the current thermal power unit are input into the thermal efficiency model to obtain a thermal efficiency prediction result.

[0022] Preferably, the key operating processes refer to the combustion process, the turbine power process and the steam turbine power process.

[0023] Preferably, the thermal efficiency prediction result is combined with the energy consumption assessment result to perform load optimization analysis and generate a real-time adjustment strategy to optimize and adjust the thermal power unit, including:

[0024] Combining and analyzing the thermal efficiency prediction result and the energy consumption evaluation result to obtain a first adjustment analysis result;

[0025] With the load optimization goals of minimizing energy consumption and maximizing thermal efficiency, a preset amount of historical operating data of thermal power units is used as training data to train a neural network to obtain a load optimization model.

[0026] The first adjustment analysis result is combined with the first unit operating condition parameter of the current thermal power unit and inputted into the load optimization model to obtain a real-time optimization strategy;

[0027] The real-time adjustment strategy is used to optimize and adjust the thermal power unit.

[0028] Preferably, the thermal efficiency prediction result is combined with the energy consumption assessment result for analysis to obtain a first adjustment analysis result, including:

[0029] Compare the thermal efficiency prediction result with the real-time thermal efficiency result at the current moment, and mark the real-time thermal efficiency result that is smaller than the corresponding thermal efficiency prediction result as the first thermal efficiency parameter;

[0030] If the first thermal efficiency parameter does not exist for the current thermal power unit, and the unit efficiency evaluation coefficient and the heat-to-electricity conversion efficiency in the obtained energy consumption evaluation result are not less than the corresponding set evaluation thresholds, then the unit adjustment strategy of the current thermal power unit is output as the first adjustment analysis result;

[0031] If the current thermal power unit does not have the first thermal efficiency parameter, and the unit efficiency evaluation coefficient or the heat-to-electricity conversion efficiency in the obtained energy consumption evaluation result is greater than the corresponding set evaluation threshold, the unit efficiency evaluation coefficient or the heat-to-electricity conversion efficiency greater than the corresponding set evaluation threshold is marked as an abnormal evaluation parameter;

[0032] Calculating the energy consumption impact coefficient using the abnormality assessment parameter;

[0033] Using the unit efficiency evaluation coefficient or heat-to-electricity conversion efficiency and energy consumption impact coefficient greater than the corresponding set evaluation threshold as matching conditions, extracting energy consumption-optimization treatment measures from the set energy consumption-treatment measure list;

[0034] Outputting the energy consumption impact coefficient and the energy consumption-optimization treatment measures as a first adjustment analysis result;

[0035] If the current thermal power unit has a first thermal efficiency parameter, and the unit efficiency evaluation coefficient and the heat-to-electricity conversion efficiency in the obtained energy consumption evaluation result are not less than the corresponding set evaluation thresholds, then the absolute difference in thermal efficiency between the thermal efficiency prediction result corresponding to the current first thermal efficiency parameter and the real-time thermal efficiency result is obtained;

[0036] Taking the first thermal efficiency parameter and the corresponding thermal efficiency absolute difference as matching conditions, extracting the efficiency-optimization treatment measure from the set thermal efficiency-treatment measure list;

[0037] Outputting the first thermal efficiency parameter, the thermal efficiency absolute difference, and the efficiency-optimization treatment measure as a first adjustment strategy;

[0038] If the current thermal power unit has a first thermal efficiency parameter, and the unit efficiency evaluation coefficient or the heat-to-electricity conversion efficiency in the obtained energy consumption evaluation result is greater than the corresponding set evaluation threshold, the unit efficiency evaluation coefficient or the heat-to-electricity conversion efficiency greater than the corresponding set evaluation threshold is marked as an abnormal evaluation parameter;

[0039] combining the abnormality assessment parameter and the first thermal efficiency parameter to calculate an efficiency impact coefficient;

[0040] The calculation formula of the efficiency impact coefficient is as follows:

[0041] Where G1 is the efficiency impact coefficient; Δf c It is expressed as the absolute difference between the cth abnormal evaluation parameter and the corresponding set evaluation threshold, where c = 1, 2; α c It is expressed as the contribution weight of the cth abnormal evaluation parameter to the energy consumption performance of the unit; γ is expressed as the influence weight of the unit thermal efficiency performance on the calculation efficiency coefficient; Δb i It is expressed as the absolute difference between the thermal efficiency prediction result of the current i-th first thermal efficiency parameter and the real-time thermal efficiency result, where i = [1, n1], n1 represents the number of first thermal efficiency parameters; β i It is represented by the contribution weight of the first thermal efficiency parameter of the i-th unit to the evaluation of the thermal efficiency performance of the unit; σ is represented by the influence weight of the unit energy consumption performance on the calculation efficiency influence coefficient;

[0042] Taking the efficiency impact coefficient as a matching condition, the efficiency comprehensive treatment measure is extracted from the set comprehensive treatment measure list and output as the first adjustment analysis result.

[0043] Preferably, a dynamic efficiency map is created to show the energy consumption status of thermal power units under various loads and deep regulation, including:

[0044] On the pre-installed data visualization platform, based on the geographical location information of the thermal power unit, mark the unit location on the unit map and set the key map parameters of the unit map;

[0045] Adding a data layer on the unit map, combining the data display rules set according to the energy consumption evaluation results and the real-time adjustment strategy to display the energy consumption status of the thermal power unit under different load and deep adjustment conditions;

[0046] The unit map provides a remote monitoring function, ensuring that users can log in to the data management system using smart devices and remotely view the energy consumption status of different units, different loads and deep adjustment conditions;

[0047] The fleet map provides a drill-down function, allowing users to drill down to view more granular data.

[0048] Compared with the prior art, the present invention has the following advantages:

[0049] By collecting key equipment data in real time and transmitting it to the data management system; the data management system conducts energy consumption evaluation, thermal efficiency prediction and load optimization analysis based on key equipment data to determine real-time adjustment strategies to optimize and adjust the thermal power units; creating dynamic efficiency maps to display the energy consumption status of thermal power units under various loads and deep adjustments, it can achieve refined management of energy consumption in the thermal power generation process and improve energy utilization efficiency.

[0050] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0051] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0053] Figure 1 The present invention provides a flowchart of a method for analyzing energy consumption of deep peak regulation of a thermal power unit. DETAILED DESCRIPTION

[0054] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0055] An embodiment of the present invention provides a method for analyzing energy consumption of deep peak regulation of a thermal power unit, as shown in FIG1 , including:

[0056] Step 1: Use the set monitoring equipment to monitor the key equipment data of the unit in real time and transmit it to the data management system;

[0057] Step 2: The data management system evaluates the overall efficiency of the thermal power unit based on the received key equipment data and obtains the energy consumption evaluation results;

[0058] Step 3: Predict the thermal efficiency of the current thermal power unit and obtain the thermal efficiency prediction result;

[0059] Step 4: Combining the thermal efficiency prediction results with the energy consumption assessment results to perform load optimization analysis and generate a real-time adjustment strategy to optimize the thermal power unit;

[0060] Step 5: Create a dynamic efficiency map to show the energy consumption status of thermal power units under various loads and deep regulation.

[0061] In this embodiment, the set monitoring equipment refers to remote sensors and data acquisition equipment pre-installed near the unit equipment, such as electricity meters and heat flow meters; the unit equipment refers to the relevant equipment of the thermal power unit, such as generators, burners, and steam turbines; key equipment data includes steam inlet temperature, pressure, steam flow, power generation, etc.; the data management system refers to a cloud platform for receiving, storing, processing and analyzing large amounts of real-time data, and supports real-time energy consumption analysis; the energy consumption evaluation result refers to the unit efficiency evaluation coefficient and heat-to-electricity conversion efficiency; the thermal power generation influencing parameters refer to the parameters that affect the load of the thermal power unit, such as fuel and air volume; the dynamic efficiency map is used to intuitively display the energy consumption status of the thermal power unit under various loads and deep adjustment.

[0062] The beneficial effects of the above technical solution are: by collecting key equipment data in real time and transmitting it to the data management system; the data management system determines the real-time adjustment strategy to optimize the thermal power units based on energy consumption evaluation, thermal efficiency prediction and load optimization analysis of key equipment data; creates a dynamic efficiency map to display the energy consumption status of thermal power units under various loads and deep adjustments, which can realize the refined management of energy consumption in the thermal power generation process and improve energy utilization efficiency.

[0063] An embodiment of the present invention provides a method for analyzing energy consumption of deep peak load regulation of a thermal power unit. A data management system evaluates the overall efficiency of the thermal power unit based on received key equipment data to obtain an energy consumption evaluation result, including:

[0064] extracting a first power generation amount, a first grid input power, and a first plant power consumption of a thermal power unit within a preset time period from a data management system;

[0065] The first power generation, the first grid input power, and the first plant power consumption are combined to calculate a unit efficiency evaluation coefficient, and output it as an energy consumption evaluation result;

[0066] Extracting a first fuel consumption and a first power generation amount of the thermal power unit within a preset time period from a data management system;

[0067] The heat-to-electricity conversion efficiency is calculated based on the first fuel consumption and the first power generation, and is output as an energy consumption evaluation result.

[0068] In this embodiment, the preset time period is predetermined, generally 12 hours; grid input power refers to the power input from the grid to the thermal power plant; plant power consumption refers to the power consumed by the internal equipment of the thermal power plant; fuel consumption refers to the amount of fuel consumed by the thermal power plant during the power generation process, such as coal and natural gas; the heat-to-electricity conversion efficiency is equal to the first power generation / first fuel consumption × 100%.

[0069] The beneficial effect of the above technical solution is: by evaluating the overall efficiency of the thermal power unit based on the received key equipment data, the energy consumption evaluation results are obtained, which can provide a data basis for the subsequent generation of real-time adjustment strategies, thereby helping to achieve refined management of energy consumption in the thermal power generation process and improve energy utilization efficiency.

[0070] The embodiment of the present invention provides a method for analyzing energy consumption of deep peak regulation of a thermal power unit. The calculation formula of the unit efficiency evaluation coefficient is as follows:

[0071] Where p1 is the unit efficiency evaluation coefficient; d0 is the first power generation; d1 is the first power consumption; d r It represents the first grid input power; δ represents the efficiency compensation learning factor.

[0072] The beneficial effect of the above technical solution is that by calculating the efficiency evaluation coefficient of the computer group, a data basis can be provided for the subsequent generation of real-time adjustment strategies, thereby helping to achieve refined management of energy consumption in the thermal power generation process and improve energy utilization efficiency.

[0073] An embodiment of the present invention provides a method for analyzing energy consumption of deep peak regulation of a thermal power unit, which predicts the thermal efficiency of the current thermal power unit and obtains a thermal efficiency prediction result, including:

[0074] Based on the principles of thermodynamics, determine the corresponding thermal efficiency calculation formula for key operating processes;

[0075] Extract a preset amount of historical operating data of thermal power units and corresponding historical efficiency parameters, combine them with the thermal efficiency calculation formula, and train a neural network to obtain a thermal efficiency model;

[0076] The operating parameters of the first unit of the current thermal power unit are input into the thermal efficiency model to obtain a thermal efficiency prediction result.

[0077] In this embodiment, the key operating processes refer to the combustion process, the turbine power process and the steam turbine power process; the thermal efficiency calculation formula of the combustion process is equal to (combustion output / combustion input) × 100%; the thermal efficiency calculation formula of the turbine power process is equal to (turbine output / heat energy input) × 100%; the thermal efficiency calculation formula of the steam turbine power process is equal to (steam turbine output / steam heat energy input) × 100%; historical operating condition data refers to the historical operation data of the thermal power unit, such as fuel type, combustion temperature, and flow rate; historical efficiency parameters refer to the historical thermal efficiency of the combustion process, the historical thermal efficiency of the turbine power process, and the historical thermal efficiency of the steam turbine power process; the thermal efficiency model is obtained by training using historical operating condition data and corresponding historical efficiency parameters through machine learning methods, and is used to receive new unit operating condition parameters as input and predict the corresponding thermal efficiency; the first unit operating condition parameters refer to the operating condition data of the thermal power unit at the current moment, such as fuel type, combustion temperature, and flow rate.

[0078] The beneficial effect of the above technical solution is: by combining machine learning algorithms, the thermal efficiency of the current thermal power units is predicted to obtain thermal efficiency prediction results, which can provide a data basis for the generation of subsequent adjustment strategies, thereby helping to achieve refined management of energy consumption in the thermal power generation process and improve energy utilization efficiency.

[0079] An embodiment of the present invention provides a method for analyzing energy consumption for deep peak regulation of a thermal power unit. The method combines the thermal efficiency prediction results with the energy consumption assessment results to perform load optimization analysis and generate a real-time adjustment strategy to optimize the thermal power unit. The method includes:

[0080] Combining and analyzing the thermal efficiency prediction result and the energy consumption evaluation result to obtain a first adjustment analysis result;

[0081] With the load optimization goals of minimizing energy consumption and maximizing thermal efficiency, a preset amount of historical operating data of thermal power units is used as training data to train a neural network to obtain a load optimization model.

[0082] The first adjustment analysis result is combined with the first unit operating condition parameter of the current thermal power unit and inputted into the load optimization model to obtain a real-time optimization strategy;

[0083] The real-time adjustment strategy is used to optimize and adjust the thermal power unit.

[0084] In this embodiment, the first adjustment analysis result is an adjustment result obtained by combining the thermal efficiency prediction result with the energy consumption evaluation result; the preset amount is predetermined; the load optimization model is a model obtained by training a neural network using pre-established load-related data as a training data set, and is used to generate an adjustment strategy for the current thermal power unit based on the received unit operating data and the comprehensive analysis results of the thermal efficiency prediction result and the energy consumption evaluation result, wherein the load-related data refers to the pre-processed historical operating data of the thermal power unit and the features related to load optimization extracted from the pre-processed historical operating data of the thermal power unit, such as steam parameters and load demand; the real-time optimization strategy is an adjustment plan output by inputting the first adjustment analysis result and the first unit operating parameter of the current thermal power unit into the load optimization model, aiming to minimize energy consumption and maximize thermal efficiency, thereby improving the operating efficiency and economy of the entire unit.

[0085] The beneficial effect of the above technical solution is: by combining the thermal efficiency prediction results with the energy consumption assessment results for analysis, and inputting the analysis results into the load optimization model, a real-time adjustment strategy is generated to optimize the thermal power units, which can help to achieve refined management of energy consumption in the thermal power generation process and improve energy utilization efficiency.

[0086] An embodiment of the present invention provides a method for analyzing energy consumption of deep peak regulation of a thermal power unit, which combines the thermal efficiency prediction result with the energy consumption assessment result for analysis to obtain a first adjustment analysis result, including:

[0087] Compare the thermal efficiency prediction result with the real-time thermal efficiency result at the current moment, and mark the real-time thermal efficiency result that is smaller than the corresponding thermal efficiency prediction result as the first thermal efficiency parameter;

[0088] If the first thermal efficiency parameter does not exist for the current thermal power unit, and the unit efficiency evaluation coefficient and the heat-to-electricity conversion efficiency in the obtained energy consumption evaluation result are not less than the corresponding set evaluation thresholds, then the unit adjustment strategy of the current thermal power unit is output as the first adjustment analysis result;

[0089] If the current thermal power unit does not have the first thermal efficiency parameter, and the unit efficiency evaluation coefficient or the heat-to-electricity conversion efficiency in the obtained energy consumption evaluation result is greater than the corresponding set evaluation threshold, the unit efficiency evaluation coefficient or the heat-to-electricity conversion efficiency greater than the corresponding set evaluation threshold is marked as an abnormal evaluation parameter;

[0090] Calculating the energy consumption impact coefficient using the abnormality assessment parameter;

[0091] Using the unit efficiency evaluation coefficient or heat-to-electricity conversion efficiency and energy consumption impact coefficient greater than the corresponding set evaluation threshold as matching conditions, extracting energy consumption-optimization treatment measures from the set energy consumption-treatment measure list;

[0092] Outputting the energy consumption impact coefficient and the energy consumption-optimization treatment measures as a first adjustment analysis result;

[0093] If the current thermal power unit has a first thermal efficiency parameter, and the unit efficiency evaluation coefficient and the heat-to-electricity conversion efficiency in the obtained energy consumption evaluation result are not less than the corresponding set evaluation thresholds, then the absolute difference in thermal efficiency between the thermal efficiency prediction result corresponding to the current first thermal efficiency parameter and the real-time thermal efficiency result is obtained;

[0094] Taking the first thermal efficiency parameter and the corresponding thermal efficiency absolute difference as matching conditions, extracting the efficiency-optimization treatment measure from the set thermal efficiency-treatment measure list;

[0095] Outputting the first thermal efficiency parameter, the thermal efficiency absolute difference, and the efficiency-optimization treatment measure as a first adjustment strategy;

[0096] If the current thermal power unit has a first thermal efficiency parameter, and the unit efficiency evaluation coefficient or the heat-to-electricity conversion efficiency in the obtained energy consumption evaluation result is greater than the corresponding set evaluation threshold, the unit efficiency evaluation coefficient or the heat-to-electricity conversion efficiency greater than the corresponding set evaluation threshold is marked as an abnormal evaluation parameter;

[0097] combining the abnormality assessment parameter and the first thermal efficiency parameter to calculate an efficiency impact coefficient;

[0098] The calculation formula of the efficiency impact coefficient is as follows:

[0099] Where G1 is the efficiency impact coefficient; Δf c It is expressed as the absolute difference between the cth abnormal evaluation parameter and the corresponding set evaluation threshold, where c = 1, 2; α c It is expressed as the contribution weight of the cth abnormal evaluation parameter to the energy consumption performance of the unit; γ is expressed as the influence weight of the unit thermal efficiency performance on the calculation efficiency coefficient; Δb i It is expressed as the absolute difference between the thermal efficiency prediction result of the current i-th first thermal efficiency parameter and the real-time thermal efficiency result, where i = [1, n1], n1 represents the number of first thermal efficiency parameters; β i It is represented by the contribution weight of the first thermal efficiency parameter of the i-th unit to the evaluation of the thermal efficiency performance of the unit; σ is represented by the influence weight of the unit energy consumption performance on the calculation efficiency influence coefficient;

[0100] Taking the efficiency impact coefficient as a matching condition, the efficiency comprehensive treatment measure is extracted from the set comprehensive treatment measure list and output as the first adjustment analysis result.

[0101] In this embodiment, the thermal efficiency prediction result refers to the thermal efficiency of the combustion process, the thermal efficiency of the turbine work process, or the thermal efficiency of the steam turbine work process of the thermal power unit at the next moment; the real-time thermal efficiency result refers to the thermal efficiency of the combustion process, the thermal efficiency of the turbine work process, or the thermal efficiency of the steam turbine work process of the thermal power unit at the current moment; the first thermal efficiency parameter refers to the real-time thermal efficiency result that is less than the corresponding thermal efficiency prediction result. For example, there is a real-time thermal efficiency result x1, the corresponding thermal efficiency prediction result is y1, and x1>y1; there is a real-time thermal efficiency result x2, the corresponding thermal efficiency prediction result is y2, and y2>x2; at this time, the real-time thermal efficiency result x2 is used as the first thermal efficiency parameter.

[0102] In this embodiment, the abnormal evaluation parameter refers to a unit efficiency evaluation coefficient or a thermal-to-electric conversion efficiency that is greater than a corresponding set evaluation threshold; the set evaluation threshold is predetermined, wherein the set evaluation threshold of the unit efficiency evaluation coefficient is 0.75; and the set evaluation threshold of the thermal-to-electric conversion efficiency is 0.8.

[0103] In this embodiment, the energy consumption impact coefficient is equal to ∑ c＝1 Δf c α c , used to characterize the energy consumption of the current thermal power unit, where Δf c It is expressed as the absolute difference between the cth abnormal evaluation parameter and the corresponding set evaluation threshold, where c = 1, 2; α c It is expressed as the contribution weight of the cth abnormal evaluation parameter to the energy consumption performance of the unit; the weight assigned to the abnormal evaluation parameter is obtained by solving the matrix constructed after pairwise comparison and relative importance scoring using the hierarchical analysis method.

[0104] In this embodiment, the set energy consumption-treatment measure list is composed of the unit efficiency evaluation coefficient, thermal-electric conversion efficiency, energy consumption impact coefficient value range and corresponding treatment measures; energy consumption-optimization treatment measures refer to measures to reduce energy consumption and improve unit efficiency obtained by matching from the set energy consumption-treatment measure list, such as adjusting the fuel ratio.

[0105] In this embodiment, the absolute difference in thermal efficiency refers to the absolute difference in efficiency between the predicted thermal efficiency result and the real-time thermal efficiency result; the set thermal efficiency-treatment measure list is designed for thermal efficiency optimization and consists of a first thermal efficiency parameter, a range of absolute difference values ​​in thermal efficiency, and corresponding treatment measures; the efficiency-optimization treatment measures refer to measures for improving the thermal efficiency of the unit obtained by matching from the set thermal efficiency-treatment measure list, such as adjusting steam parameters and optimizing the turbine; the efficiency impact coefficient is used to characterize the thermal efficiency and energy consumption level of the current thermal power unit; the weight assigned to the first thermal efficiency parameter is obtained by solving a matrix constructed by pairwise comparison and relative importance scoring of the first thermal efficiency parameters using the hierarchical analysis method; the weight assigned to the unit thermal efficiency performance and the unit energy consumption performance is obtained by solving a matrix constructed by pairwise comparison and relative importance scoring using the hierarchical analysis method; the set comprehensive treatment measure list consists of a range of efficiency impact coefficient values ​​and corresponding treatment measures; the efficiency comprehensive treatment measures refer to treatment measures obtained by matching from the set comprehensive treatment measure list that involve optimization of both energy consumption and thermal efficiency, such as optimizing fuel ratio and adjusting unit load.

[0106] The beneficial effect of the above technical solution is: by combining the thermal efficiency prediction results with the energy consumption assessment results for analysis, the first adjustment analysis results are obtained to provide an effective data basis for the generation of subsequent real-time adjustment strategies, which can help to achieve refined management of energy consumption in the thermal power generation process and improve energy utilization efficiency.

[0107] The embodiment of the present invention provides a method for analyzing energy consumption of thermal power units under deep peak regulation, creating a dynamic efficiency map to display the energy consumption status of thermal power units under various loads and deep regulation, including:

[0108] On the pre-installed data visualization platform, based on the geographical location information of the thermal power unit, mark the unit location on the unit map and set the key map parameters of the unit map;

[0109] Adding a data layer on the unit map, combining the data display rules set according to the energy consumption evaluation results and the real-time adjustment strategy to display the energy consumption status of the thermal power unit under different load and deep adjustment conditions;

[0110] The unit map provides a remote monitoring function, ensuring that users can log in to the data management system using smart devices and remotely view the energy consumption status of different units, different loads and deep adjustment conditions;

[0111] The fleet map provides a drill-down function, allowing users to drill down to view more granular data.

[0112] In this embodiment, the preset data visualization platform refers to a predetermined map visualization platform that supports dynamic data display and interactive functions; the geographic location information refers to the specific location coordinates of the thermal power unit; the key map parameters refer to the zoom level, layer, annotation style, etc.; the data display rules are display rules based on energy consumption assessment results and real-time adjustment strategy settings, for example, different colors are used to represent different energy consumption levels; smart devices refer to portable smart devices, such as mobile phones and tablets; the drill-down function refers to a function that allows users to view finer-grained lower-level data layer by layer, for example, from the basic information of the thermal power unit to the basic information of specific unit equipment, such as equipment type and equipment number.

[0113] The beneficial effect of the above technical solution is: by creating an efficiency map with dynamic display and interactive functions, the energy consumption status of thermal power units under different load and deep adjustment conditions can be intuitively displayed, providing strong support for optimization and adjustment.

[0114] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for analyzing energy consumption of deep peak load regulation of thermal power units, characterized in that: include: Step 1: Use the set monitoring equipment to monitor the key equipment data of the unit equipment in real time and transmit it to the data management system; Step 2: The data management system evaluates the overall efficiency of the thermal power unit based on the received key equipment data to obtain the energy consumption evaluation result; Step 3: Predict the thermal efficiency of the current thermal power unit and obtain the thermal efficiency prediction result; Step 4: Combining the thermal efficiency prediction result with the energy consumption assessment result, performing load optimization analysis, and generating a real-time adjustment strategy to optimize and adjust the thermal power unit; Step 5: Create a dynamic efficiency map to show the energy consumption status of thermal power units under various loads and deep adjustments.

2. A method for analyzing energy consumption of deep peak load regulation of thermal power units according to claim 1, characterized in that: The data management system evaluates the overall efficiency of the thermal power unit based on the key equipment data received and obtains energy consumption evaluation results, including: Extracting a first power generation amount, a first grid input power, and a first plant power consumption of a thermal power unit within a preset time period from a data management system; The first power generation, the first grid input power and the first plant power consumption are combined to calculate the unit efficiency evaluation coefficient, and output it as an energy consumption evaluation result; Extracting a first fuel consumption and a first power generation amount within a preset time period of the thermal power unit from a data management system; The heat-to-electricity conversion efficiency is calculated based on the first fuel consumption and the first power generation, and is output as an energy consumption evaluation result.

3. A method for analyzing energy consumption of deep peak load regulation of thermal power units according to claim 2, characterized in that: The calculation formula of the unit efficiency evaluation coefficient is as follows: In the formula, p1 represents the unit efficiency evaluation coefficient; d0 represents the first power generation; d1 represents the first power consumption; d r It is represented as the first grid input electric energy; δ is represented as the efficiency compensation learning factor.

4. A method for analyzing energy consumption of deep peak load regulation of thermal power units according to claim 1, characterized in that: The thermal efficiency of the current thermal power units is predicted, and the thermal efficiency prediction results are obtained, including: Based on the principles of thermodynamics, determine the corresponding thermal efficiency calculation formula for key operating processes; Extract the historical operating data of the preset amount of thermal power units and the corresponding historical efficiency parameters, combine them with the thermal efficiency calculation formula, and train the neural network to obtain the thermal efficiency model; The operating parameters of the first unit of the current thermal power unit are input into the thermal efficiency model to obtain a thermal efficiency prediction result.

5. A method for analyzing energy consumption of deep peak load regulation of thermal power units according to claim 4, characterized in that: The key operation processes refer to the combustion process, the turbine power process and the steam turbine power process.

6. A method for analyzing energy consumption of deep peak load regulation of thermal power units according to claim 1, characterized in that: The thermal efficiency prediction results are combined with the energy consumption assessment results to perform load optimization analysis and generate a real-time adjustment strategy to optimize the thermal power unit, including: The thermal efficiency prediction result is combined with the energy consumption evaluation result for analysis to obtain a first adjustment analysis result; Taking minimizing energy consumption and maximizing thermal efficiency as the load optimization goals, a preset amount of historical operating data of thermal power units is used as training data to train the neural network to obtain a load optimization model; Inputting the first adjustment analysis result into the load optimization model in combination with the first unit operating condition parameter of the current thermal power unit to obtain a real-time optimization strategy; The real-time adjustment strategy is used to optimize and adjust the thermal power unit.

7. A method for analyzing energy consumption of deep peak load regulation of thermal power units according to claim 6, characterized in that: The thermal efficiency prediction result is combined with the energy consumption assessment result for analysis to obtain a first adjustment analysis result, including: Compare the thermal efficiency prediction result with the real-time thermal efficiency result at the current moment, and mark the real-time thermal efficiency result that is smaller than the corresponding thermal efficiency prediction result as the first thermal efficiency parameter; If the current thermal power unit does not have the first thermal efficiency parameter, and the unit efficiency evaluation coefficient and the heat-to-electricity conversion efficiency in the obtained energy consumption evaluation result are not less than the corresponding set evaluation thresholds, the unit adjustment strategy of the current thermal power unit is output as the first adjustment analysis result; If the current thermal power unit does not have the first thermal efficiency parameter, and the unit efficiency evaluation coefficient or the heat-to-electric conversion efficiency in the obtained energy consumption evaluation result is greater than the corresponding set evaluation threshold, the unit efficiency evaluation coefficient or the heat-to-electric conversion efficiency greater than the corresponding set evaluation threshold is marked as an abnormal evaluation parameter; Calculating the energy consumption impact coefficient using the abnormal evaluation parameter; Taking the unit efficiency evaluation coefficient or the heat-to-electricity conversion efficiency and the energy consumption impact coefficient greater than the corresponding set evaluation threshold as matching conditions, extracting energy consumption-optimization treatment measures from the set energy consumption-treatment measure list; Outputting the energy consumption impact coefficient and the energy consumption-optimization treatment measures as a first adjustment analysis result; If the current thermal power unit has a first thermal efficiency parameter, and the unit efficiency evaluation coefficient and the heat-to-electricity conversion efficiency in the obtained energy consumption evaluation result are not less than the corresponding set evaluation threshold, then the absolute difference in thermal efficiency between the thermal efficiency prediction result corresponding to the current first thermal efficiency parameter and the real-time thermal efficiency result is obtained; Taking the first thermal efficiency parameter and the corresponding thermal efficiency absolute difference as matching conditions, extracting the efficiency-optimization treatment measure from the set thermal efficiency-treatment measure list; Outputting the first thermal efficiency parameter, the thermal efficiency absolute difference, and the efficiency-optimization treatment measure as the first adjustment strategy; If the current thermal power unit has a first thermal efficiency parameter, and the unit efficiency evaluation coefficient or the heat-to-electric conversion efficiency in the obtained energy consumption evaluation result is greater than the corresponding set evaluation threshold, the unit efficiency evaluation coefficient or the heat-to-electric conversion efficiency greater than the corresponding set evaluation threshold is marked as an abnormal evaluation parameter; The abnormality assessment parameter and the first thermal efficiency parameter are combined to calculate the efficiency impact coefficient; The calculation formula of the efficiency impact coefficient is as follows: In the formula, G1 represents the efficiency impact coefficient; Δf c It is expressed as the absolute difference between the cth abnormal evaluation parameter and the corresponding set evaluation threshold, where c = 1, 2; α c It is represented by the contribution weight of the cth abnormal evaluation parameter to the energy consumption performance of the unit; γ is represented by the influence weight of the thermal efficiency performance of the unit on the calculation efficiency influence coefficient; Δb i It is represented by the absolute difference between the thermal efficiency prediction result of the current i-th first thermal efficiency parameter and the real-time thermal efficiency result, where i = [1, n1], n1 represents the number of first thermal efficiency parameters; β i It is represented by the contribution weight of the i-th first thermal efficiency parameter to the evaluation of the thermal efficiency performance of the unit; σ is represented by the influence weight of the unit energy consumption performance on the calculation efficiency influence coefficient; The efficiency impact coefficient is used as a matching condition, and the efficiency comprehensive processing measure is extracted from the set comprehensive processing measure list and output as the first adjustment analysis result.

8. A method for analyzing energy consumption of deep peak load regulation of thermal power units according to claim 1, characterized in that: Create dynamic efficiency maps to show the energy consumption status of thermal power units under various loads and deep adjustments, including: On the preset data visualization platform, the location of the unit is marked on the unit map according to the geographical location information of the thermal power unit, and the key map parameters of the unit map are set; Adding a data layer on the unit map, combining the data display rules set according to the energy consumption evaluation results and the real-time adjustment strategy, to display the energy consumption status of the thermal power unit under different loads and deep adjustment conditions; The unit map provides a remote monitoring function, ensuring that users can log in to the data management system using smart devices and remotely view the energy consumption status of different units, different loads and deep adjustment conditions; The fleet map provides a drill-down function, allowing the user to view more granular underlying data layer by layer.

Images