A unit ascending and descending load working condition optimization method based on historical working conditions

Abstract

The application discloses a unit ascending and descending load working condition optimization method based on historical working conditions, and collects historical ascending and descending load working conditions by fitting calculation on screening parameters and screening according to average fitting deviation and maximum deviation limit value. In actual matching process, the starting working condition load and the ending target load are set to ensure that the operation requirements of load ascending and descending operation are met. Different business priority needs in different business scenes can be met through different optimization methods, all working conditions under the same load ascending and descending condition are screened through setting a filtering time range, the optimized working condition is ensured to be accurate and reliable according to the optimization standard, the operation parameters under the specified load condition are adjusted according to the ascending and descending load working condition after optimization and the returned index data, the operation state of the unit reaches the optimum, the general unit ascending and descending load working condition optimization method shields business differences, provides an efficient and fast algorithm, greatly saves manpower, improves the calculation efficiency and improves the accuracy of business processing data.

Description

Technical Field

[0001] This invention relates to the field of power generation technology, specifically to optimizing unit load conditions based on historical operating conditions. Background Technology

[0002] Thermal power generation is a complex system. The operating conditions of the unit equipment are constantly changing. Output indicators such as unit load, pollution, and coal consumption are used as evaluation indicators. Factors affecting these evaluation indicators include coal properties (calorific value, sulfur content, etc.) and operation and control (damper, oxygen content, coal feed rate, etc.). Multiple indicators interact with each other. By comparing and analyzing the indicators of the current equipment under similar historical operating conditions, an effective economic and safety analysis of the unit can be provided.

[0003] Finding approximate operating conditions through operating condition matching is an important computational process in various production optimizations based on historical operations. It is used to optimize and match historical production operating conditions based on production data indicators at a specific time to find the optimal operating condition. Then, combined with the current operating parameters, it can identify operational differences and optimize the operation for specific parameters.

[0004] During the load increase and decrease phases of the generating unit, it is in a non-steady-state operation. At this time, the equipment operating parameters are fluctuating. Finding a good method for optimizing the historical operating conditions of the generating unit during load increase and decrease is of great significance for the stable operation of the equipment, improving economic efficiency and environmental protection, and even ensuring the safety of power plant equipment.

[0005] Currently, the common approach is to use historical optimization for steady-state operation under constant load conditions. However, how to optimize operating conditions during load increases and decreases remains a challenge. A common method is to use the load change rate as a single parameter and compare it with historical operating conditions for optimization. However, this method is too simplistic and fails to consider the numerous factors that change during load increases and decreases, making it difficult to provide reliable reference. Summary of the Invention

[0006] To address the challenges in existing technologies, this invention provides a method for optimizing unit load increase / decrease conditions based on historical operating conditions. This method is adaptable to various business scenarios involving matching unit load increase / decrease conditions. By setting optimization conditions based on given initial and target load parameters, the method matches the preferred operating conditions from historical operating data in a case library. Finally, the method obtains the target parameter value for the given operating condition by referencing the parameter curve of the preferred operating condition based on the instantaneous load value of the given operating condition.

[0007] This invention is achieved through the following technical solution:

[0008] A method for optimizing unit load increase / decrease conditions based on historical operating conditions includes the following steps:

[0009] Step 1: Obtain the average load of two consecutive steady-state conditions in the historical operating conditions. When the average load of the two steady-state conditions meets the set conditions, obtain the judgment index sample of the load rise and fall conditions between the two steady-state conditions. The judgment index sample is a parameter that has a linear correlation with the load change.

[0010] Step 2: Based on the judgment index samples and their corresponding load samples obtained in Step 1, fit the sample to obtain the fitting equation. Then, substitute each load sample into the fitting equation to determine the corresponding judgment index calculation value. Compare the judgment index calculation value with the judgment index sample to obtain the maximum fitting deviation and the average fitting deviation of the judgment index.

[0011] Step 3: Compare the maximum fitting deviation and the average fitting deviation with the set threshold. If the maximum fitting deviation and the average fitting deviation are greater than the threshold, change the fitting method, update the fitting equation, and repeat Step 2 until the maximum fitting deviation and the average fitting deviation are less than the threshold, and obtain the operating parameters of the load increase / decrease condition.

[0012] Step 4: Repeat steps 2-4 to traverse the historical steady-state load conditions and obtain the operating parameters for multiple load increase and decrease conditions;

[0013] Step 5: Set the comparison conditions and use their load parameters as screening conditions. At the same time, set optimization rules. Optimize the multiple load increase / decrease conditions obtained in Step 4 according to the screening conditions and optimization rules to obtain the optimal load increase / decrease condition. Optimize the operating parameters of the current condition according to the optimal load increase / decrease condition.

[0014] Preferably, the condition set in step 1 is that the difference between the average load values ​​of the two load steady-state conditions is greater than a set limit or ratio.

[0015] Preferably, the formula for calculating the average fitting deviation in step 2 is as follows:

[0016]

[0017] The formula for calculating the maximum deviation from the fit is as follows:

[0018] β = max(|yf(x)|)

[0019] Where f(x) is the fitted curve of the parameters, y is the actual value of the parameters, and n is the number of samples.

[0020] Preferably, the load parameters in step 5 are the start load value and end load value of the load increase / decrease condition, and a specified time range for filtering is set.

[0021] Preferably, the optimization rule is the maximum fitting deviation and the average fitting deviation of the load.

[0022] Preferably, the specified time range is the time range in historical time where the unit's load increase / decrease status is the same as the current unit's load increase / decrease status.

[0023] Preferably, in step 5, the operating parameters of the optimal load increase / decrease condition are compared with the operating parameters of the current condition, and the operating parameters of the current condition are optimized based on the comparison results.

[0024] A system for optimizing unit load increase / decrease operating conditions based on historical operating conditions is provided. The system executes the optimization method for unit load increase / decrease operating conditions based on historical operating conditions during operation.

[0025] Compared with the prior art, the present invention has the following beneficial technical effects:

[0026] This invention provides a method for optimizing unit load increase / decrease conditions based on historical operating conditions. By setting the initial and target values ​​of the load and then setting a filtering time range, load increase / decrease conditions under the same conditions are screened. Based on the fitting deviation of the screening parameters for each condition, conditions with deviations greater than the set fitting deviation are excluded, ensuring that the screened load increase / decrease conditions have small fluctuations, smooth operation, and are safe and reliable. The selected load increase / decrease conditions are then optimized according to the selection criteria, and the operating parameters are calculated based on the optimized conditions to achieve the optimal operating state of the unit in terms of stability, safety, and economy. This method provides an efficient and fast algorithm, greatly saving manpower, improving calculation efficiency, and improving the accuracy of data in business processing. Attached Figure Description

[0027] Figure 1 This is a flowchart of a method for optimizing unit load increase / decrease conditions based on historical operating conditions, according to the present invention.

[0028] Figure 2 This is the main flowchart of the present invention based on the data collection and processing of unit load increase and decrease conditions;

[0029] Figure 3 This is a schematic diagram of the main steam pressure change curve when the unit of the present invention is operating under load increase and decrease conditions. Detailed Implementation

[0030] The present invention will now be described in further detail with reference to the accompanying drawings. These descriptions are intended to explain the invention and not to limit it.

[0031] See Figure 1-3 The method for optimizing unit load increase / decrease conditions based on historical operating conditions includes the following steps:

[0032] Step 1: Obtain the operating parameters of the unit under load increase and decrease conditions according to the business scenario type. Use the parameters that are linearly related to load changes as judgment indicators and set the threshold of the judgment indicators in the fitted curve of load changes. At the same time, it is necessary to set other relevant parameters and algorithms for the data collection conditions.

[0033] Specifically, the judgment indicators are the main parameters of unit operation. For example, the judgment indicator is the main steam pressure. Set the maximum deviation limit and the average deviation limit between the calculated value and the actual value of the fitted curve of the main steam pressure under load change. Similarly, set the average deviation limit of all values. Other data collection parameters also need to be set, such as coal feed rate and SO2 emissions. Non-fitting algorithms such as average values ​​can be set.

[0034] Step 2: Obtain the average load of two consecutive steady-state operating conditions in the historical operating conditions. When the average load of the two steady-state operating conditions meets the set conditions, obtain the judgment index sample of the load rise and fall between the two steady-state operating conditions.

[0035] In this embodiment, historical load steady-state conditions are stored in a case library. The case library is traversed to obtain the load average of adjacent load steady-state conditions. If the difference between the load averages of two load steady-state conditions is greater than a certain limit or ratio, the main steam pressure sample value and the load value corresponding to the main steam pressure sample value for the time period between the adjacent conditions are read.

[0036] Step 3: Based on the judgment index samples and their corresponding load samples obtained in Step 2, fit the samples to obtain the fitting equation. Then, substitute each load sample into the fitting equation to determine the corresponding judgment index calculation value. Compare the judgment index calculation value with the judgment index samples to obtain the maximum fitting deviation and the average fitting deviation.

[0037] The formula for calculating the average deviation of the fit is as follows:

[0038]

[0039] The formula for calculating the maximum deviation from the fit is as follows:

[0040] β = max(|yf(x)|)

[0041] Where f(x) is the fitted curve of the parameters, y is the actual value of the parameters, and n is the number of samples.

[0042] A fitting equation is obtained by mathematically fitting the sample values ​​of main steam pressure and the corresponding load values ​​for that time period. The load values ​​corresponding to the main steam pressure sample values ​​are then substituted into the equation one by one to calculate the corresponding values ​​on the curve. These calculated values ​​are then compared with the main steam pressure sample values ​​to obtain the maximum and average fitting deviations. Figure 3 The sample values ​​with a medium load of around 480 show the greatest deviation from the fitted curve.

[0043] Step 4: Compare the maximum fitting deviation and the average fitting deviation with the threshold set in Step 1. If the maximum fitting deviation and the average fitting deviation are greater than the threshold, change the fitting method, update the fitting equation, and repeat Step 3 until the maximum fitting deviation and the average fitting deviation are less than the threshold, and obtain the operating parameters for the load increase / decrease condition.

[0044] Specifically, if the maximum and average fitting deviations exceed the limits, another fitting method is used until all fitting methods have been tried. If the maximum and average fitting deviations exceed the thresholds for all fitting methods, the next steady-state load condition is read.

[0045] If the maximum and average deviations of the fit calculation method are less than the limit, the load increase / decrease case is recorded. The basic information of the recorded load increase / decrease includes the start and end times of the load increase / decrease, the load increase / decrease duration (end time minus start time), the average steady-state load value at the start of the increase / decrease, the average steady-state load value at the end of the increase / decrease, the fitted curve of the main steam pressure parameter, and the maximum and average deviations of the fit.

[0046] Step 5: Repeat steps 2-4 to iterate through historical steady-state load conditions and obtain operating parameters for multiple load increase and decrease conditions.

[0047] The process of collecting the above load increase / decrease case studies is performed daily. The load increase / decrease cases that can be collected each day are added to the case study library.

[0048] Step 6: Set the comparison conditions and use their load parameters as screening conditions. At the same time, set optimization rules and optimize the multiple load increase and decrease conditions obtained in Step 5 according to the screening conditions and optimization rules to obtain the optimal load increase and decrease conditions.

[0049] Optimization requires the following conditions: Selecting a comparison operating condition, using the starting and target loads of the generator units in the comparison condition, along with a time range (e.g., 180 days), as the operating condition matching filter conditions; and selecting an optimization method. The optimization method can be the minimum maximum or minimum average deviation of the fitted parameters, or it can be other parameter values ​​such as minimum SO2 emissions. For example, for operational safety and stability, the minimum average deviation of the main steam pressure can be selected.

[0050] Based on the set load increase / decrease start and target conditions, the load increase / decrease case library generated in step 5 is filtered to obtain all load increase / decrease start and target conditions with the same load increase / decrease within 180 days. From the filtered conditions, the optimal load increase / decrease condition is selected based on selection criteria, resulting in the load increase / decrease condition with the smallest average deviation of the main steam pressure.

[0051] Step 7: Compare the optimal operating condition with the current operating condition index parameter values, and optimize the operating parameters of the current operating condition.

[0052] For example, the optimal value of the main steam pressure for any specific load during load rise or fall can be calculated based on the fitted curve and used as a reference value for the operation target for optimization.

[0053] This invention discloses a method for optimizing unit load increase / decrease conditions based on historical operating conditions. It collects historical load increase / decrease conditions by fitting and calculating screening parameters and setting limits based on average and maximum fitting deviations. During the actual matching process, a starting load and a target load are set to ensure that the operational requirements of load increase / decrease operations are met. Different optimization methods can meet the needs of different business priorities in different business scenarios. By setting a filtering time range, all operating conditions under the same load increase / decrease conditions are filtered. Then, the accuracy and reliability of the optimized operating conditions are ensured according to the optimization criteria. Based on the optimized load increase / decrease conditions and the returned index data, the operating parameters under the specified load conditions are adjusted to achieve the optimal operating state of the unit. This general method for optimizing unit load increase / decrease conditions masks business differences, provides a highly efficient and fast algorithm, greatly saves manpower, improves computational efficiency, and enhances the accuracy of data processed in business operations.

[0054] Example 1

[0055] A common situation encountered in thermal power production is that during load increases and decreases, differing experiences with equipment, coal quality, and combustion processes during non-steady-state operation lead to significant non-smooth fluctuations, impacting the unit's economic, safe, and environmentally friendly operation, and even causing unexpected shutdowns. To address this issue and discover better operating methods, historical load increase / decrease conditions can be used as operational guidance. By matching historical load increase / decrease conditions with the unit's real-time operating data and conducting comparative analysis, operational guidance can be provided for current practices.

[0056] Optimizing historical operating conditions for load increases and decreases requires establishing a historical case library of these conditions. The collection of historical cases should be based on a single load increase or decrease scenario, and the load operation must be in a steady state before and after the increase or decrease. The load should change linearly, and some key parameters should also change linearly during the load increase or decrease process. Selecting and collecting such operating conditions can serve as a valuable case library.

[0057] For load, a threshold range of 5MW can be set for load fluctuation during steady-state operation 10 minutes before and after the load rise / fall process. For parameters during the rise / fall process, the deviation of the load on the fitted curve during the rise / fall process can be set to not exceed 5MW, with a maximum deviation of not exceeding 8MW. The deviation of the main steam pressure on the fitted curve during the rise / fall process can be set to not exceed 0.05MPa, with a maximum deviation of not exceeding 0.1MPa. After setting the screening conditions, the historical operating condition screening calculation is started. In this way, a database of excellent rise / fall load operating condition cases can be collected for a period of history.

[0058] Once a robust database of load change scenarios is established, the algorithm can be invoked in real time using the starting load, current load, and target load of the current load change scenario as matching parameters to begin the matching process. Based on a defined search time range, all load change scenarios with the same starting and ending loads within the collected historical load change scenarios are retrieved.

[0059] For each load increase / decrease record, parameters collected from historical cases are read to obtain its load fitting curve and main steam temperature fitting curve. The operating conditions can be filtered based on the fitting deviation and maximum deviation of each parameter to select approximate operating conditions that meet the requirements. For example, if the load start condition is required to be 300MW, the load increase end condition to be 600MW, and the average deviation of the main steam pressure fitting curve to be no greater than 0.04MPa, operating conditions with deviations outside this range are filtered out.

[0060] For operating conditions that match the records, the optimal operating condition is selected according to optimization rules, such as minimizing the deviation of the load fitting curve. If the parameter is a fitted parameter, the fitted curve of that operating condition parameter is substituted into the current load to obtain the target value of the parameter. If the parameter is a non-fitting algorithm, such as the mean, it is directly used as the target parameter.

[0061] Compare and analyze the obtained load increase / decrease parameters with the actual values ​​of the current load increase / decrease conditions. For example, compare the main steam pressure, damper opening, and oxygen content of the current conditions with the values ​​of the current conditions. Recommend that the current operating team make adjustments based on the historical optimal values ​​that can be referenced, improve the operation, and enhance the safety, economy, and environmental friendliness of the unit operation.

[0062] This invention provides a method for optimizing unit load increase / decrease conditions based on historical operating conditions. This method is not only applicable to the real-time matching and optimization scenarios exemplified above, but can also be widely applied to all business scenarios requiring historical operating condition matching. The comparison conditions are not limited to real-time conditions; they can also be historical conditions, or even user-generated hypothetical conditions. This method provides a simple and fast processing procedure for matching and analyzing historical operating conditions.

[0063] The above content is only for illustrating the technical concept of the present invention and should not be construed as limiting the scope of protection of the present invention. Any modifications made to the technical solution based on the technical concept proposed in this invention shall fall within the scope of protection of the claims of this invention.

Claims

1. A method for optimizing unit load increase / decrease conditions based on historical operating conditions, characterized in that, Includes the following steps: Step 1: Obtain the average load of two consecutive steady-state conditions in the historical operating conditions. When the average load of the two steady-state conditions meets the set conditions, obtain the judgment index sample of the load rise and fall conditions between the two steady-state conditions. The judgment index sample is a parameter that has a linear correlation with the load change. The setting condition is that the difference between the average load values ​​of the two steady-state load conditions is greater than the set limit or ratio; Step 2: Based on the judgment index samples and their corresponding load samples obtained in Step 1, fit the sample to obtain the fitting equation. Then, substitute each load sample into the fitting equation to determine the corresponding judgment index calculation value. Compare the judgment index calculation value with the judgment index sample to obtain the maximum fitting deviation and the average fitting deviation of the judgment index. The formula for calculating the average deviation of the fit is as follows: The formula for calculating the maximum deviation from the fit is as follows: Where f(x) is the fitted curve of the parameters, y is the actual value of the parameters, and n is the number of samples; Step 3: Compare the maximum fitting deviation and the average fitting deviation with the set threshold. If the maximum fitting deviation and the average fitting deviation are greater than the threshold, change the fitting method, update the fitting equation, and repeat Step 2 until the maximum fitting deviation and the average fitting deviation are less than the threshold, and obtain the operating parameters of the load increase / decrease condition. Step 4: Repeat steps 2-3 to traverse the historical steady-state load conditions and obtain the operating parameters for multiple load increase and decrease conditions; Step 5: Set the comparison conditions and use the load parameters as the screening criteria, and use the maximum and average deviations of the fitting parameters as the optimization criteria. Based on the screening and optimization criteria, the multiple load increase / decrease conditions obtained in step 4 are optimized to obtain the optimal load increase / decrease condition. The operating parameters of the current condition are then optimized based on the optimal load increase / decrease condition. The load parameters are the start and end load values ​​for the load increase / decrease conditions, and a specified time range for filtering is also set.

2. The method for optimizing unit load increase / decrease conditions based on historical operating conditions according to claim 1, characterized in that, The specified time range is the time range within which the unit's load increase / decrease status is the same as the current unit's load increase / decrease status in historical time.

3. The method for optimizing unit load increase / decrease conditions based on historical operating conditions according to claim 1, characterized in that, In step 5, the operating parameters of the optimal load increase / decrease condition are compared with the operating parameters of the current condition, and the operating parameters of the current condition are optimized based on the comparison results.

4. A system for optimizing unit load increase / decrease operating conditions based on historical operating conditions, characterized in that, When the system is running, it performs the method described in any one of claims 1-3.

Images