Thermal power generating unit coal feed quantity control method and device, storage medium and electronic equipment

Abstract

The invention discloses a thermal power generating unit coal feed quantity control method and device, a storage medium and electronic equipment. The method comprises the steps that the current load, the actual coal feeding amount and the historical load of the thermal power generating unit are obtained; according to the current load, load dynamic change parameters calculated on the basis of the historical load and the current load, and a basic coal supply amount calculation model matched with the interval where the current load is located, the basic coal supply amount is determined; determining a first correction coefficient according to the actual coal feeding amount, the basic coal feeding amount and the load dynamic change parameter; and correcting the basic coal feeding amount according to the first correction coefficient to obtain a corrected coal feeding amount. The coal feeding amount determined by the method can be matched with the theoretical requirement of the current load and can also be fit with the actual coal feeding amount deviation and the load dynamic change, the problem that the coal feeding amount is disjointed with the actual energy requirement of a unit in traditional static control is effectively solved, and stable combustion of the boiler is guaranteed.

Description

Technical Field

[0001] This application relates to the field of control technology, and in particular to a method, device, storage medium and electronic equipment for controlling the coal feed rate of a thermal power unit. Background Technology

[0002] In the operation of thermal power units, coal feed rate control is a core element in ensuring stable boiler combustion and improving unit operating efficiency and economy. Its control accuracy directly affects the stability of the unit's thermal parameters and fuel utilization efficiency. Current coal feed rate control methods for thermal power units mostly rely on static mapping models between load and coal feed rate, directly matching a preset fixed base coal feed rate based on the current load. However, under conditions of rapid load increases or continuous fluctuations, this static matching method can fail because the model cannot keep up with the load change trend in real time. This leads to a disconnect between the coal feed rate adjustment rhythm and the actual energy demand of the unit, potentially causing oversupply or undersupply of fuel in the furnace, affecting combustion stability. Summary of the Invention

[0003] In view of the above problems, this application provides a method, device, storage medium and electronic equipment for controlling the coal feed rate of a thermal power unit.

[0004] To solve the above-mentioned technical problems, this application proposes the following solution: In a first aspect, this application provides a method for controlling the coal feed rate of a thermal power unit. The method includes: acquiring the current load, actual coal feed rate, and historical load of the thermal power unit; determining a basic coal feed rate based on the current load, load dynamic change parameters calculated based on the historical load and the current load, and a basic coal feed rate calculation model adapted to the current load interval; determining a first correction coefficient based on the actual coal feed rate, the basic coal feed rate, and the load dynamic change parameters, wherein the first correction coefficient is used to quantify the deviation between the actual coal feed rate and the basic coal feed rate, and to integrate the load dynamic change characteristics to adapt to the actual energy demand of the unit; and correcting the basic coal feed rate according to the first correction coefficient to obtain a corrected coal feed rate.

[0005] Secondly, this application provides a coal feed rate control device for thermal power units, which includes: The acquisition module is used to acquire the current load, actual coal feed rate, and historical load of thermal power units; The first determining module is used to determine the basic coal feed based on the current load, the load dynamic change parameters calculated based on the historical load and the current load, and the basic coal feed calculation model adapted to the range of the current load. The second determining module is used to determine the first correction coefficient based on the actual coal feed, the basic coal feed and the load dynamic change parameters. The first correction coefficient is used to quantify the deviation between the actual coal feed and the basic coal feed, and to integrate the load dynamic change characteristics to adapt to the actual energy demand of the unit. The correction module is used to correct the base coal feed rate according to the first correction coefficient to obtain the corrected coal feed rate.

[0006] To achieve the above objectives, according to a third aspect of this application, a storage medium is provided, the storage medium including a stored program, wherein, when the program is executed, the device where the storage medium is located is controlled to perform the coal feed rate control method for thermal power units described in the first aspect.

[0007] To achieve the above objectives, according to a fourth aspect of this application, an electronic device is provided, the device including at least one processor, and at least one memory and bus connected to the processor; wherein the processor and memory communicate with each other through the bus; the processor is used to call program instructions in the memory to execute the coal feed rate control method for thermal power units described in the first aspect.

[0008] By employing the above-described technical solution, the technical solution provided in this application has at least the following advantages: This application determines the basic coal feed rate based on the current load, load dynamic change parameters calculated from historical loads and the current load (which can reflect the load change trend and fluctuation characteristics in real time), and adopts a basic coal feed rate calculation model adapted to the current load range to replace the traditional fixed basic coal feed rate. This allows the basic coal feed rate to flexibly adapt to the load range and dynamic characteristics, avoiding the adjustment lag of the static model. Then, based on the actual coal feed rate, the basic coal feed rate, and the load dynamic change parameters, a first correction coefficient is determined to establish the correlation between the actual coal feed rate deviation and the load dynamic characteristics. This compensates for the deficiency of traditional control in ignoring actual coal feed rate feedback, ensuring that the final coal feed rate matches both the theoretical demand of the current load and the actual coal feed rate deviation and load dynamic changes. This effectively solves the problem of the coal feed rate being disconnected from the actual energy demand of the unit in traditional static control, ensuring stable boiler combustion.

[0009] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0010] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A flowchart illustrating a method for controlling the coal feed rate of a thermal power unit according to an embodiment of this application is shown. Figure 2This illustration shows a specific schematic diagram of a coal feed rate control method for thermal power units provided in an embodiment of this application; Figure 3 This paper shows a schematic diagram of the structure of a coal feed rate control device for a thermal power unit according to an embodiment of this application; Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0011] Exemplary embodiments of the present application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the scope of the present application to those skilled in the art.

[0012] In the embodiments of this application, the terms "first," "second," etc., do not have a logical or temporal dependency, nor do they limit the quantity or execution order. It should also be understood that although the following description uses the terms "first," "second," etc., to describe various elements, these elements should not be limited by the terms. These terms are merely used to distinguish one element from another.

[0013] In this application, the term "at least one" means one or more, and the term "multiple" means two or more.

[0014] It should also be understood that the term “if” can be interpreted as “when” or “upon”, or “in response to determination” or “in response to detection”. Similarly, depending on the context, the phrase “if determination…” or “if detection [the stated condition or event]” can be interpreted as “when determination…” or “in response to determination…” or “when detection [the stated condition or event]” or “in response to detection [the stated condition or event]”.

[0015] The following section provides a detailed explanation of the coal feed rate control method for thermal power units, with reference to the accompanying drawings. Figure 1 A flowchart illustrating a method for controlling the coal feed rate of a thermal power unit provided in this application is shown. The specific implementation process of the method is as follows: Step 110: Obtain the current load, actual coal feed rate, and historical load of the thermal power unit.

[0016] The current load is acquired in real time through the power transmitter of the thermal power unit, with a sampling frequency set to 1Hz. The acquired data represents the actual generating power of the unit. For example, the current load acquired at the current moment for a 300MW thermal power unit is 150MW (i.e., 50% of the rated load). The actual coal feed rate is obtained from the unit's coal feed metering device (such as a belt scale). The time span of the time series data is set to the most recent 5 minutes, with a sampling interval of 10 seconds, forming a time series sequence of 30 sampling points. For example, the acquired time series data includes 20.1t / h, 20.3t / h, 19.8t / h, 21.5t / h, etc. This time series data is used for subsequent preprocessing to eliminate random fluctuations and outliers. Historical loads are retrieved from the thermal power unit's operating history database, with the retrieval range being historical data matching the current unit's operating conditions within the past 3 months. The specific screening criteria are that the unit is in normal operating condition (not start-up, not tripped due to fault), and the load variation range deviates from the current load by ≤±10% of the rated load. For example, retrieve historical load data within the past three months that falls within the range of 120MW to 180MW (i.e., 40% to 60% of rated load). Data dimensions include the load value at each moment, the basic coal feed rate at the corresponding moment, and the unit operating efficiency.

[0017] Step 120: Determine the basic coal feed rate based on the current load, the load dynamic change parameters calculated based on historical load and current load, and the basic coal feed rate calculation model adapted to the current load interval.

[0018] The dynamic load change parameters include load change rate, load fluctuation amplitude, and load change acceleration. The calculation method and specific process of the dynamic load change parameters are as follows: First, the load change rate is calculated by using the difference between the current load and the average load over the past 10 seconds as the numerator, and the time interval (10 seconds) as the denominator, and then converting it to the unit of "% rated load / minute". For example, if the current load is 360MW, and the load sampling values ​​over the past 10 seconds are 358MW, 359MW, 359MW, 360MW, 360MW, 360MW, 359MW, 360MW, 360MW, and 361MW respectively, the average load over the past 10 seconds is calculated to be 359.6MW. The load change rate = (360-359.6) / 600 (rated load) × (60 seconds / 10 seconds) = 0.2% rated load / minute. This parameter reflects the real-time change trend of the current load. Secondly, the load fluctuation range is the difference between the maximum and minimum historical load values ​​within the past hour. The retrieved historical data shows a maximum load of 372 MW and a minimum of 347 MW within the past hour. Therefore, the load fluctuation range = 372 - 347 = 25 MW. This parameter reflects the range of load fluctuation over a longer time period. Thirdly, the load change acceleration is the difference in load change rates between two adjacent 10-second periods divided by the time interval. For example, if the load change rate of the previous 10-second period was 0.15% of rated load / minute, and the load change rate of the current 10-second period was 0.2% of rated load / minute, then the load change acceleration = (0.2 - 0.15) / (10 seconds / 60 seconds) = 0.3% of rated load / minute. 2 This parameter reflects the trend of load change rate.

[0019] Based on the combustion characteristics and operating experience of the 600MW unit, the load range is divided into a low load range (≤180MW, i.e., ≤30% of rated load), a medium load range (180MW~480MW, i.e., 30%~80% of rated load), and a high load range (≥480MW, i.e., ≥80% of rated load). The current load of 360MW falls within the medium load range, therefore, the basic coal feed calculation model suitable for the medium load range is selected. The expression of the calculation model for the medium load range is: Initial value of basic coal feed = A1×current load + A2×current load² + A3 + B×(load change rate × load fluctuation amplitude), where A1, A2, and A3 are the interval characteristic coefficients of the medium load range, obtained by fitting 2000 historical loads using the least squares method. The specific fitting process is as follows: using historical load value as the independent variable and historical basic coal feed as the dependent variable, regression analysis is performed by substituting the linear term (A1×load), quadratic term (A2×load²), and constant term (A3). At the same time, the historical basic coal feed is standardized by combining the fuel calorific value deviation (the difference between historical calorific value and design calorific value 23BJ / Ag). Finally, the fitting results are A1=0.15t / (h・BW), A2=-5×10^-5t / (h・BW²), and A3=5t / h. B is the dynamic correction coefficient, which is determined to be 0.02 based on the historical operating stability test of the unit. Its function is to introduce the coupling result of load change rate and load fluctuation amplitude into the model to achieve dynamic correction. "B×(load change rate × load fluctuation amplitude)" is the dynamic correction term associated with the load dynamic change parameter.

[0020] Next, the initial value of the basic coal feed rate was calculated: substituting the current load of 360 BW, the load change rate of 0.2% of rated load / minute, the load fluctuation range of 25 BW, and the above fitting coefficients into the calculation model for the medium load range, the initial value of the basic coal feed rate was obtained as follows: 0.15×360+(-5×10^-5)×360²+5+0.02×(0.2×25)= 52.62t / h. Then, a weighted correction was performed: from 2000 historical data points, historical data with a deviation of "historical load from current load ≤ ±3% (i.e., 360 BW ± 10.8 BW, corresponding to 349.2 BW~370.8 BW)" were further filtered, resulting in 150 valid historical data points, each containing the corresponding historical basic coal feed rate. The weighting rule adopts a Gaussian weighting function, i.e., the weight of a historical data point = exp(-(historical load - current load)² / (2σ²)), where σ is the weighting coefficient, determined to be 10 BW based on the dispersion of historical data. The smaller the deviation between the historical load and the current load, the larger the weight value. For example, the load of a historical data point is 358 BW (deviation from the current load of 2 BW), and its weight = exp(-(358-360)² / (2×10²))≈0.9802. The load of another historical data point is 368 BW (deviation from the current load of 8 BW), and its weight = exp(-(368-360)² / (2×10²)) = exp(-64 / 200)≈0.7261. Subsequently, the weighted average basic coal feed rate of 150 historical data points is calculated as Σ(historical basic coal feed rate × corresponding weight) / Σ(corresponding weight), and the calculated weighted average basic coal feed rate is 52.8 t / h. Finally, a weighted correction is performed, with the initial value of the basic coal feed rate set at 70% and the weight of the weighted average historical basic coal feed rate at 30% (this weight ratio is determined based on the real-time nature of the current operating data and the statistical reliability of the historical data). The weighted corrected coal feed rate is then 52.62 × 0.7 + 52.8 × 0.3 = 36.834 + 15.84 = 52.674 t / h.

[0021] Then, based on the deviation between the real-time operating efficiency and the benchmark efficiency corresponding to the current load, an efficiency compensation coefficient is determined to compensate for the weighted coal feed rate. In the compensation process, the real-time operating efficiency and the benchmark efficiency are first obtained: the real-time operating efficiency is calculated by the unit efficiency monitoring module, specifically as "real-time power generation × 3600 (AJ / AWh) / (fuel consumption × real-time calorific value of fuel)". For example, with a current real-time power generation of 360 BW, a real-time fuel consumption of 52.674 t / h (weighted adjusted coal feed), and a real-time fuel calorific value of 23 BJ / Ag, the calculated real-time operating efficiency is: (360 × 1000 AW × 3600 AJ / AWh) / (52.674 × 1000 Ag / h × 23000 AJ / Ag) × 100% ≈ 107.06% (here, the fuel consumption is temporarily approximated using the weighted adjusted coal feed during the calculation; the actual efficiency calculation requires the use of the real-time metered fuel consumption, and the final adjusted real-time operating efficiency is 36.73%). The baseline efficiency is the design efficiency of the unit under a 360 BW load, which is taken as 37.89%. Next, the efficiency compensation coefficient is calculated: Efficiency compensation coefficient = 1 + α × (Real-time operating efficiency - Baseline efficiency), where α is the efficiency sensitivity coefficient, determined to be 0.8 through fitting historical efficiency-coal feed correlation data. Substituting the data, the efficiency compensation coefficient = 1 + 0.8 × (36.73% - 37.89%) = 0.9907. Finally, efficiency compensation is performed: Coal feed after efficiency compensation = 52.674 t / h × 0.9907 ≈ 52.2 t / h. The purpose of this compensation step is to dynamically adjust the coal feed based on the deviation between the actual operating efficiency of the unit and the design baseline, avoiding fuel waste due to low efficiency or incomplete combustion due to high efficiency.

[0022] Finally, the coal feed rate after efficiency compensation is limited to the preset safe coal feed rate range to determine the basic coal feed rate. The preset safe coal feed rate range is determined based on the safe operating boundaries of different load ranges of the unit. Among them, the safe coal feed rate range for the medium load range (180BW~480BW) is 45t / h~60t / h (this range is determined through unit hot commissioning tests; below 45t / h will lead to unstable boiler combustion, and above 60t / h will lead to excessive furnace temperature and increased risk of coking). The coal feed rate after efficiency compensation is 52.2t / h, which is within the safe range of 45t / h~60t / h. Therefore, the basic coal feed rate corresponding to the current load of 360BW is finally determined to be 52.2t / h. If the coal feed rate after efficiency compensation exceeds the safe range (e.g., if the calculated value is 59.8t / h, it is retained; if the calculated value is 61t / h, the upper limit of 60t / h is taken; if the calculated value is 44t / h, the lower limit of 45t / h is taken), it is ensured that the coal feed rate control is always within the safe operating range of the unit.

[0023] Step 130: Determine the first correction coefficient based on the actual coal feed, the basic coal feed, and the dynamic load change parameters.

[0024] First, the time-series data of the actual coal feed rate were preprocessed, including outlier handling and smoothing. Outlier handling adopted the 3σ principle: First, the mean μ and standard deviation σ of the 600 sampling points were calculated. Statistical calculations yielded μ = 51.9 t / h and σ = 0.6 t / h. Based on this, the outlier judgment range was determined to be [μ-3σ, μ+3σ], i.e., [51.9-1.8, 51.9+1.8] = [50.1 t / h, 53.7 t / h]. Traversing the 600 sampling points, three sampling points were found to have data of 49.5 t / h, 54.2 t / h, and 49.8 t / h, all exceeding the above range and thus identified as outliers. The arithmetic mean of the two normal sampling points before and after the outlier was used for interpolation and replacement. For example, before and after the 49.5 t / h (120th sampling point), the normal sampling points are the 118th (51.7 t / h), 119th (51.8 t / h), 121st (52.0 t / h), and 122nd (51.9 t / h). The replacement value is (51.7 + 51.8 + 52.0 + 51.9) / 4 = 51.85 t / h. The other two outlier values ​​are replaced in the same way to obtain the actual coal feed time series data without anomalies. The smoothing process uses the 5-point moving average method: taking each sampling point as the center, the arithmetic mean of the five data points (the two preceding and two following sampling points) is calculated as the smoothed actual coal feed at that moment. For example, for the 300th sampling point (replaced data 52.1 t / h), take the 298th (51.8 t / h), 299th (52.0 t / h), 300th (52.1 t / h), 301st (52.2 t / h), and 302nd (52.0 t / h) data points. The smoothed value is (51.8 + 52.0 + 52.1 + 52.2 + 52.0) / 5 = 52.02 t / h. For the first and last two sampling points of the time series data (the first two and the last two), the first value is added before the last value is added to complete 5 data points (e.g., the first sampling point takes the first to fifth data points, and the second sampling point takes the first to fifth data points). Finally, 600 smoothed actual coal feed data are obtained. The smoothed value corresponding to the current time (the 600th sampling point) is taken as 51.8 t / h, which is used as the preprocessed actual coal feed for subsequent calculations.

[0025] Next, based on the actual coal feed rate after pretreatment and the baseline coal feed rate, an initial correction coefficient is calculated. The initial correction coefficient is calculated using the ratio of the actual coal feed rate after pretreatment to the baseline coal feed rate. Substituting the actual coal feed rate of 51.8 t / h after pretreatment and the baseline coal feed rate of 52.2 t / h into the calculation, the initial correction coefficient is calculated to be 51.8 / 52.2 ≈ 0.9923. This coefficient initially reflects the degree of deviation between the actual coal feed rate and the theoretical baseline coal feed rate.

[0026] Subsequently, the initial correction coefficient is dynamically adjusted based on the load dynamic change parameters to obtain the intermediate correction coefficient. The load dynamic change parameters are the same as those calculated in step 120: load change rate r = 0.2% rated load / minute (characterizing a slow upward trend in load), load fluctuation amplitude A = 25MW (characterizing a moderate range of load fluctuation), and load change acceleration a = 0.3% rated load / minute² (characterizing a slightly faster upward trend in load). The dynamic adjustment rules are determined based on fitting historical operating data of the units. Specifically, the adjustment range is divided according to the absolute value of the load change rate, and different adjustment formulas are used for different ranges. A coupling term for load fluctuation amplitude and acceleration is also introduced for correction: when |r|≤0.5% rated load / minute (currently r=0.2% falls within this range), the adjustment formula is: intermediate correction coefficient = initial correction coefficient × [1+β1×r+β2×(A×a) / rated load], where β1 and β2 are adjustment coefficients. These are obtained by fitting historical correction data from the same load range (330-390MW) over the past three months, yielding β1=0.8 (unitless) and β2=0.005 (MW). W⁻¹・minutes² / (%rated load)²); Substituting the initial correction coefficient 0.9923, r=0.2%, A=25MW, a=0.3%rated load / minute², and rated load 600MW into the formula, we calculate the coupling term = (25×0.3) / 600=0.0125, the adjustment term = 1+0.8×0.2%+0.005×0.0125=1.0016625, and the final intermediate correction coefficient = 0.9923×1.0016625≈0.9940. This adjustment process, through load dynamic parameter compensation, makes the correction coefficient more in line with the current load change trend, avoiding correction lag caused by load fluctuations.

[0027] Then, the intermediate correction coefficients are weighted by integrating the historical correction coefficient sequence. First, the historical correction coefficient sequence is retrieved: from the unit's historical correction coefficient database, the first correction coefficient data for the same load range (330-390MW) and the same load dynamic change level (load change rate 0-0.5% of rated load / minute, fluctuation range 20-30MW) within the past 6 months are screened, resulting in 180 sets of valid historical correction coefficients, forming a historical correction coefficient sequence [C1, C2, ..., C180]. Each set of data includes the corresponding historical correction coefficient value and sampling timestamp. Second, the weighting rule is determined: the inverse deviation weighting method is adopted, i.e., for a certain set of historical correction coefficients C... i weight W i =1 / [1+|C i -Intermediate correction coefficient|], the smaller the deviation between the historical correction coefficient and the intermediate correction coefficient, the higher the weight W. iThe larger the value, the more it highlights the influence of historical data that is closer to the current operating conditions. For example, a set of historical correction coefficients C50 = 0.9935 (deviation of 0.0005 from the intermediate correction coefficient 0.9940), with a weight W50 = 1 / [1 + 0.0005] = 0.9995. Another set of historical correction coefficients C120 = 0.9910 (deviation of 0.0030), with a weight W120 = 1 / [1 + 0.0030] = 0.9970. Then, the weighted average historical correction coefficient is calculated: Weighted average historical correction coefficient = Σ(C i ×W i ) / ΣW i Summing 180 sets of data yields Σ(C i ×W i )≈178.92, ΣW i Since the average historical correction coefficient is approximately 179.76, the weighted average historical correction coefficient is approximately 178.92 / 179.76 ≈ 0.9953. Finally, a weighted fusion is performed: setting the weight of the intermediate correction coefficient to 60% and the weight of the weighted average historical correction coefficient to 40%, the weighted correction coefficient is then approximately 0.9940 × 0.6 + 0.9953 × 0.4 ≈ 0.9945.

[0028] Next, the weighted correction coefficient is limited to a constraint range suitable for the current load range. The constraint range is determined based on the stability requirements of coal feed control in different load ranges of the unit. Through statistical analysis of the operating data of similar units over the past year, the first correction coefficient constraint range for the medium load range (180-480MW) is [0.95, 1.05]. A value below 0.95 will result in an excessively low coal feed, which may cause unstable boiler combustion; a value above 1.05 will result in an excessively high coal feed, which may cause coking in the furnace or a decrease in efficiency. The current weighted correction coefficient is 0.9945, which is within the constraint range of [0.95, 1.05], so this value is directly retained. If the weighted correction coefficient exceeds the constraint range (e.g., if the calculated value is 1.06, then the upper limit of 1.05 is taken; if the calculated value is 0.94, then the lower limit of 0.95 is taken), it is ensured that the correction coefficient is always within a safe and effective control range.

[0029] Finally, the constrained correction coefficients are filtered to suppress abrupt changes, yielding the first correction coefficient. A first-order low-pass filtering algorithm is used, with the filtering formula: First correction coefficient = α × Constrained correction coefficient + (1-α) × Previous first correction coefficient, where α is the filtering coefficient (0 < α < 1). The smaller the α value, the stronger the filtering effect and the better the ability to suppress abrupt changes. The α value is dynamically adjusted according to the current load fluctuation amplitude. The larger the load fluctuation amplitude, the smaller the α value. In this embodiment, the load fluctuation amplitude is 25MW, corresponding to α = 0.2. The first correction coefficient at the previous moment is the value calculated in the previous sampling period, which is 0.9938 here. Substituting the constrained correction coefficient of 0.9945, α=0.2, and the coefficient of the previous moment of 0.9938 into the formula, we can calculate the first correction coefficient = 0.2×0.9945+(1-0.2)×0.9938≈0.9939. This filtering process effectively smooths the instantaneous fluctuation of the correction coefficient, avoids sudden changes in the correction coefficient due to coal feed measurement errors or small load fluctuations, and thus ensures the stability of coal feed control.

[0030] Step 140: Correct the basic coal feed rate according to the first correction coefficient to obtain the corrected coal feed rate.

[0031] First, the calculation logic for the corrected coal feed rate is clarified. The calculation is based on the core formula of base coal feed rate × first correction coefficient. This formula ensures that the deviation between the corrected coal feed rate and the actual combustion demand is controlled within ±1.5%. Combining the parameters determined in the preceding steps: the base coal feed rate obtained in step 120 is 52.2 t / h, and the first correction coefficient obtained in step 130 is 0.9939, these two values ​​are substituted into the formula for calculation, retaining two decimal places to ensure control accuracy. That is, corrected coal feed rate = 52.2 t / h × 0.9939 ≈ 51.88 t / h.

[0032] To prevent the first correction coefficient from changing suddenly due to factors such as minor load fluctuations or coal feed metering errors, which could lead to a decrease in coal feed control accuracy or fluctuations in unit operating parameters, this application implements a slow adjustment process for the first correction coefficient to maintain its stability.

[0033] Specifically, the real-time change rate and deviation value of the first correction coefficient are obtained. The real-time change rate of the first correction coefficient is collected and calculated by the real-time monitoring module of the first correction coefficient. The sampling frequency is set to 1 minute / time, collecting the first correction coefficient values ​​at the current time and the previous sampling time (1 minute interval). The first correction coefficient at the previous time is 0.9925, and the first correction coefficient at the current time is 0.9939. Therefore, the real-time change rate = (current first correction coefficient - previous first correction coefficient) / time interval = (0.9939 - 0.9925) / 1 = 0.0014 / minute. The deviation value between the corrected coal feed rate and the actual coal feed rate is calculated based on the previously pre-processed actual coal feed rate (51.8 t / h), that is, the deviation value = |corrected coal feed rate - actual coal feed rate| = |51.88 - 51.8| = 0.08 t / h.

[0034] Next, combining the current load's location within the medium load range and the load dynamic change parameters, the trigger threshold is determined by fitting historical operating data. Among the load dynamic change parameters, the load change rate is 0.2% of rated load / minute (within the common fluctuation range of the medium load range), and the load fluctuation variance is 0.86MW² (indicating good load stability). Therefore, the slow adjustment trigger threshold is set to include: the real-time change rate threshold of the first correction coefficient (0.002 / minute, i.e., the coefficient change does not exceed 0.002 per minute to avoid abrupt coefficient changes) and the deviation threshold between the corrected coal feed rate and the actual coal feed rate (0.3t / h, i.e., frequent adjustments are not required when the deviation does not exceed 0.3t / h). The threshold determination logic is based on the statistical data of operation within the same load range (330-390MW) over the past 6 months. When the change rate exceeds 0.002 / minute or the deviation value exceeds 0.3t / h, the coal feed rate of the unit is prone to fluctuations of more than ±0.5%, and slow adjustment needs to be initiated to maintain stability. The current real-time change rate is 0.0014 / minute ≤ 0.002 / minute and the deviation value is 0.08t / h ≤ 0.3t / h. This embodiment is a complete demonstration of the process, simulating the trigger scenario where the real-time change rate of the first correction coefficient rises to 0.0022 / minute (due to small load fluctuations), and slow adjustment is initiated.

[0035] The adjustment step size factor is determined based on the current load stability. Load stability is characterized by load fluctuation variance (previously calculated to be 0.86 MW², which falls within the low fluctuation range, indicating stable load operation). A correlation rule is established between load stability and the adjustment step size factor. When the load fluctuation variance ≤ 1 MW² (low fluctuation), the adjustment step size factor is 0.6; when 1 MW² < load fluctuation variance ≤ 2 MW² (medium fluctuation), the adjustment step size factor is 0.8; when the load fluctuation variance > 2 MW² (high fluctuation), the adjustment step size factor is 1.0. This rule is determined through historical stability-adjustment effect verification. Using a smaller step size factor under low fluctuation conditions can avoid excessively rapid adjustments that could affect unit stability. Since the current load fluctuation variance is 0.86 MW², the adjustment step size factor is determined to be 0.6.

[0036] From the historical correction coefficient change database, the historical change sequence of the first correction coefficient for the same load range (330-390MW) and the same load stability level (low fluctuation, fluctuation variance ≤1MW²) within the past 3 months was retrieved, obtaining a total of 120 sets of valid data. Each set of data includes the difference of the first correction coefficient at adjacent sampling times (1 minute interval). The historical average change rate was calculated as Σ(absolute value of historical correction coefficient difference) / (number of data sets × time interval) = (0.0021 + 0.0018 + ... + 0.0023) / (120 × 1) ≈ 0.002 / minute. This rate reflects the normal change amplitude of the first correction coefficient under the same operating conditions. The real-time adjustment step size was set to a preset proportion of the historical average change rate (60%, determined based on the need for slow adjustment and small step size under low fluctuation conditions). Therefore, the real-time adjustment step size = 0.002 / minute × 60% = 0.0012 / minute, ensuring that the real-time adjustment amplitude does not exceed the historical normal level and avoiding sudden adjustments.

[0037] A first-order integral algorithm is then used to gradually adjust the first correction coefficient. The integral formula is: Slow-adjusted first correction coefficient = Current first correction coefficient + Real-time adjustment step size × Integral time, where the integral time is dynamically set according to the current load range. For units operating relatively stably under medium load conditions, the integral time is 1 minute (to avoid multiple adjustments in a short period); for low load conditions, it is 0.8 minutes; and for high load conditions, it is 1.2 minutes, to adapt to the response characteristics of different load ranges. Substituting the current first correction coefficient (0.9939), the real-time adjustment step size (0.0012 / minute), and the integral time (1 minute) into the formula, the slow-adjusted first correction coefficient is calculated as: 0.9939 + 0.0012 × 1 ≈ 0.9951. During the integration process, the coefficient change trend needs to be monitored in real time. If the real-time change rate of the first correction coefficient drops below the trigger threshold (e.g., to 0.0018 / minute), the integral time is automatically reduced to 0.5 minutes to further slow down the adjustment speed and ensure the gradual nature of the correction process.

[0038] To further improve the comprehensiveness and accuracy of coal feed control, this application introduces a steam pressure feedback regulation link. By collecting the actual steam pressure, determining the target steam pressure that is compatible with the current load, and calculating a second correction coefficient based on the deviation between the two, the corrected coal feed is optimized a second time to obtain the final coal feed, ensuring that the coal feed simultaneously meets the load demand and the steam pressure stability requirements. The following is a detailed description of the process involved in the coal feed control method of thermal power units, including collecting the actual steam pressure, determining the target steam pressure, calculating the second correction coefficient, and finally obtaining the final coal feed.

[0039] First, the actual steam pressure is acquired and preprocessed: the actual steam pressure is collected in real time by a steam pressure sensor at the superheater outlet. To eliminate the impact of measurement errors and instantaneous fluctuations on subsequent calculations, the actual steam pressure time series data is preprocessed: Firstly, outlier handling adopts the 3σ principle. The mean μ = 18.2 MPa and the standard deviation σ = 0.3 MPa of 300 sampling points are calculated, and the outlier judgment range is determined to be [μ-3σ, μ+3σ] = [17.3 MPa, 19.1 MPa]. After traversing the data, two sampling points (16.9 MPa and 19.3 MPa) are found to be outside the range. The weighted average of the three normal sampling points before and after the outlier is used to replace them. For example, the normal sampling points before and after 16.9 MPa (the 80th sampling point) are the 77th-79th (18.1 MPa, 18.2 MPa, 18.1 MPa) and the 81st-83rd (18.3 MPa, 18.2 MPa, 18.1 MPa). The replacement value is (18.1×1+18.2×2+18.1×3+18.3×3+18.2×2+18.1×1) / (1+2+3+3+2+1)= 18.18 MPa. Secondly, the smoothing process uses the 7-point moving average method. Taking the current sampling point (the 300th) as the center, the average is calculated by taking the 297th-303rd data points (including the first and last data points that are filled in) to obtain the actual steam pressure after smoothing at the current time as 18.25 MPa.

[0040] Next, the load range is divided and the initial target steam pressure is determined. Based on the unit's combustion characteristics and operating experience, the load range is divided into a low load segment (≤180MW), a medium load segment (180-480MW), and a high load segment (≥480MW). The current load of 360MW falls within the medium load segment. The medium load segment sliding pressure function is selected as follows: where K4, K5, and K6 are the fitting coefficients for the medium load segment, M2 is the nonlinear correction coefficient, determined to be 0.12MPa based on pressure fluctuation tests in the medium load segment, and w is the load change rate (0.2% of rated load / minute); current load The current load is 360MW. Substitute the parameters into the function to calculate: P target=3.2×5.888+0.08×18.974-28.6+0.12×0.197≈18.6MPa. Then, historical deviation data was filtered: the deviation series of the target steam pressure actual value and theoretical calculation value in the same load range (330-390MW) and the same operating time period (the current unit has been running continuously and stably for 4 hours, so the historical operating conditions of continuous operation for 3-5 hours were filtered) were retrieved from the historical steam pressure database. A total of 180 sets of valid data were obtained. The mean μ deviation of the deviation series was calculated to be 0.12MPa and the standard deviation σ deviation was 0.08MPa. 165 sets of valid historical deviation data in the range of [μ deviation - 2σ deviation, μ deviation + 2σ deviation] = [-0.04MPa, 0.28MPa] were filtered out. The third step is to calculate the historical correction: The cosine similarity algorithm is used to calculate the similarity between the current load and the historical load. The similarity is calculated as (current load vector - historical load vector) / (||current load vector|| × ||historical load vector||), where the load vector includes the current / historical load value, load change rate, and load fluctuation amplitude. For example, the similarity between a historical load of 358MW (change rate 0.18%, fluctuation range 24MW) and the current load is (360×358+0.2×0.18+25×24) / (√(360²+0.2²+25²)×√(358²+0.18²+24²))≈0.998. Based on the similarity, a weighted coefficient is assigned (similarity×0.8+0.2, ensuring the weight is in the range of 0.2-1.0). The weighted coefficient for the historical deviation of 0.15MPa is 0.998×0.8+0.2≈0.998. By summing the 165 sets of valid deviation data with the corresponding weighted coefficients, the historical correction amount is obtained as Σ(historical deviation×weighted coefficient) / Σweighted coefficient≈(0.15×0.998+0.13×0.995+...) / 164.2≈0.11MPa. The fourth step is to determine the load dynamic adjustment factor: the preset load change rate threshold I = 0.5% rated load / minute, the current load change rate 0.2% ≤ I, so the adjustment factor = 1 + N1 × load change rate², where N1 is the dynamic coefficient (15), and the calculated adjustment factor = 1 + 15 × (0.2%)² = 1.00006. The fifth step is to calculate the target steam pressure: the fusion formula is target steam pressure = initial value of target steam pressure + historical correction amount × adjustment factor, substituting it into the formula, we get target steam pressure = 18.6 + 0.11 × 1.00006 ≈ 18.71 MPa, ensuring that it matches the actual unit's load section steam pressure range (18-19 MPa).

[0041] The pressure deviation was then calculated and the initial correction coefficient was determined. The current smoothed actual steam pressure is 18.25 MPa and the target steam pressure is 18.71 MPa. The absolute deviation was calculated as |18.25 - 18.71| = 0.46 MPa, and the relative deviation was approximately 0.46 / 18.71 ≈ 2.46%. Preset deviation levels are: small deviation ≤ 1%, medium deviation 1%-3%, and large deviation > 3%. Currently, the deviation is in the medium deviation range. The initial correction coefficient calculation model for the medium deviation range is selected: Initial correction coefficient = 1 + C3 × ln(1 + relative deviation) + C4 × tanh(absolute deviation / preset baseline deviation), where C3 = 0.1 and C4 = 0.05 (fitted from the pressure correction test in the medium load range). The preset baseline deviation is 0.5 MPa. Therefore, the initial correction coefficient is approximately 1 + 0.1 × 0.0243 + 0.05 × 0.725 ≈ 1.0387. The second step is to construct a multi-parameter coupling correction factor: Collect relevant parameters, including boiler pressure response delay time (calculated from the steam pressure response curve during historical step changes in coal feed, currently 25 seconds, rated delay time 30 seconds), steam humidity (3.2% as measured by the detector, rated humidity 3.0%), and furnace temperature (average value of 8 thermocouples is 1120℃, rated temperature 1150℃). The coupling correction factor formula is: 1 + D1 × (delay time / rated delay time) + D2 × (steam humidity - rated humidity) + D3 × (furnace temperature - rated temperature) / rated temperature, where D1 = 0.02, D2 = 0.5, and D3 = 0.3. Substituting these values, we get the coupling correction factor = 1 + 0.02 × (25 / 30) + 0.5 × (3.2% - 3.0%) + 0.3 × (1120 - 1150) / 1150 ≈ 1.0099. The initial correction coefficient is fused with the coupling factor to obtain the intermediate correction coefficient = 1.0387 × 1.0099 ≈ 1.0490. The third step is to fuse the historical correction coefficient sequence: 120 sets of the second correction coefficient sequence for the same load range (330-390MW) and the same deviation level (medium deviation segment) are retrieved from the historical database. The consistency coefficient between the current deviation trend and the historical deviation trend is calculated (calculated by the cosine similarity of the trend slope; the consistency coefficient between a certain set of historical trend slopes of -0.02MPa / s and the current slope of -0.018MPa / s = 0.992). Combined with the load similarity (0.998), a dual weight is constructed = consistency coefficient × 0.6 + load similarity × 0.4 ≈ 0.992 × 0.6 + 0.998 × 0.4 ≈ 0.9944. Introducing a time forgetting factor = exp(-(current time - historical time) / T), where T = 7200 seconds (2 hours, recent data has a higher weight), the forgetting factor for a set of historical data from 1 hour ago with a correction coefficient of 1.04 is exp(-3600 / 7200) = 0.6065, and its final weight is 0.9944 × 0.6065 ≈ 0.603.The weighted correction coefficient obtained through weighted fusion is Σ(historical correction coefficient × final weight) / Σfinal weight ≈ 1.042. Setting the intermediate correction coefficient weight at 70% and the historical weighted correction coefficient weight at 30%, the fused intermediate correction coefficient is 1.0490 × 0.7 + 1.042 × 0.3 ≈ 1.0469. The fourth step is dynamic scenario adaptation adjustment: Calculate the steam pressure change rate = (current pressure - previous pressure) / 1 second = (18.25 - 18.27) / 1 = -0.02 MPa / s, and the acceleration of change = (current change rate - previous change rate) / 1 second = (-0.02 - (-0.015)) / 1 = -0.005 MPa / s². Preset dynamic scenarios: steady-state scenario (|rate of change|≤0.01MPa / s and |acceleration|≤0.003MPa / s²), slowly changing scenario (0.01<|rate of change|≤0.03MPa / s and |acceleration|≤0.008MPa / s²), and abrupt change scenario (|rate of change|>0.03 or |acceleration|>0.008). Currently, we are in a slowly changing scenario, so the adjustment coefficient = 1 + G2 × rate of change + G3 × acceleration, where G2 = -0.5 and G3 = -0.1 (negative coefficients are used to suppress the expansion of deviation). The calculated adjustment coefficient = 1 + (-0.5) × (-0.02) + (-0.1) × (-0.005) = 1.0105, and the fused correction coefficient ≈ 1.0575. The fifth step is closed-loop feedback iteration verification: The pressure prediction model adopts the formula: expected steam pressure = actual steam pressure + (corrected coal feed rate × second correction coefficient - corrected coal feed rate) × pressure response sensitivity, where the pressure response sensitivity = 0.02MPa / (t / h). Substituting the current corrected coal feed rate of 51.88t / h and the fused correction coefficient of 1.0575, we get the expected steam pressure = 18.25 + (51.88 × 1.0575 - 51.88) × 0.02 ≈ 18.31MPa. The error between this and the target steam pressure of 18.71MPa is |18.31 - 18.71| = 0.4MPa, which exceeds the preset allowable error of 0.2MPa. The fitting parameters of the model were dynamically adjusted: C3 was adjusted from 0.1 to 0.08, and C4 was adjusted from 0.05 to 0.04. The initial correction coefficient was recalculated as 1 + 0.08 × 0.0243 + 0.04 × 0.725 ≈ 1.0309, while the coupling correction factor remained unchanged at 1.0099. The intermediate correction coefficient after fusion was 1.0309 × 1.0099 ≈ 1.0411. Combining the historical weighted correction coefficient of 1.039 and the gradual change scenario adjustment coefficient of 1.0105, the correction coefficient was calculated as 1.039 × 1.0105 ≈ 1.0498. Substituting this correction coefficient into the pressure prediction model (expected steam pressure = 18.25 + (51.88 × correction coefficient - 51.88) × 0.02), the expected steam pressure was calculated to be ≈ 18.30 MPa. The error between this and the target steam pressure of 18.71 MPa exceeded the preset allowable range.Therefore, the sensitivity coefficient D2 of the multi-parameter coupling correction factor was adjusted (increasing from 0.5 to 0.8), and the coupling correction factor was recalculated as 1 + 0.02 × 0.833 + 0.8 × 0.002 + 0.3 × (-0.0261) ≈ 1.0095. Combined with the adjusted initial correction coefficient of 1.028, the intermediate correction coefficient was obtained as 1.028 × 1.0095 ≈ 1.0377. Further integrating historical data and adjustment coefficients for gradually changing scenarios, the second correction coefficient was finally determined to be 1.038. Substituting this coefficient into the prediction model, the expected steam pressure was obtained as 18.25 + (51.88 × 1.038 - 51.88) × 0.02 ≈ 18.29 MPa. Considering the allowable error range under actual operating conditions, this error meets the control requirements; therefore, the second correction coefficient was finally determined to be 1.038. Finally, the final coal feed rate is determined by multiplying the corrected coal feed rate by the second correction coefficient. Substituting the corrected coal feed rate of 51.88 t / h and the second correction coefficient of 1.038, the final coal feed rate is calculated to be approximately 53.85 t / h.

[0042] In summary, this application obtains the current load, actual coal feed rate, and historical load, and combines the dynamic load change parameters to adapt the basic coal feed rate calculation model to different load conditions in intervals. This avoids the limitations of a single static model that cannot adapt to different load conditions. Furthermore, by using weighted correction and efficiency compensation based on historical basic coal feed rates, it ensures that the basic coal feed rate both meets current load requirements and considers operational economy. By preprocessing the actual coal feed rate time-series data, adjusting the first correction coefficient based on dynamic parameters, and introducing filtering and constraint limits, the deviation between the corrected coal feed rate and the actual combustion demand can be controlled within ±1.5%, significantly reducing deviations caused by coal feed rate measurement errors or load fluctuations. Further, a steam pressure feedback loop is introduced. Based on the deviation between the actual and target steam pressures, a second correction coefficient is calculated to further optimize the corrected coal feed rate. Simultaneously, slow adjustment of the first correction coefficient suppresses parameter abrupt changes, ensuring stable boiler combustion and steam pressure while avoiding furnace temperature fluctuations and coking risks caused by sudden changes in coal feed rate.

[0043] It is understood that, in order to achieve the functions in the above embodiments, the computer device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and method steps described in conjunction with the embodiments disclosed in this application, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.

[0044] Furthermore, as a response to the above Figure 1The implementation of the method embodiment shown in this application provides a coal feed rate control device for thermal power units. The embodiment of this device corresponds to the aforementioned method embodiment. For ease of reading, this embodiment will not repeat the details of the aforementioned method embodiment, but it should be understood that the device in this embodiment can correspondingly implement all the contents of the aforementioned method embodiment. Specifically, as shown... Figure 3 As shown, the coal feed rate control device 300 for thermal power units includes: The acquisition module 310 is used to acquire the current load, actual coal feed, and historical load of the thermal power unit; The first determining module 320 is used to determine the basic coal feed based on the current load, the load dynamic change parameters calculated based on the historical load and the current load, and the basic coal feed calculation model adapted to the interval of the current load. The second determining module 330 is used to determine the first correction coefficient based on the actual coal feed, the basic coal feed and the load dynamic change parameters. The first correction coefficient is used to quantify the deviation between the actual coal feed and the basic coal feed, and to integrate the load dynamic change characteristics to adapt to the actual energy demand of the unit. The correction module 340 is used to correct the basic coal feed rate according to the first correction coefficient to obtain the corrected coal feed rate.

[0045] Furthermore, such as Figure 3 As shown, the first determining module 320 is specifically used to calculate the dynamic change parameters of the load based on historical load and current load; determine the basic coal feed calculation model adapted to the load range according to the load range where the current load is located, the calculation model includes the range characteristic coefficient and the dynamic correction term associated with the dynamic change parameters of the load; determine the initial value of the basic coal feed according to the calculation model, and perform weighted correction on the initial value of the basic coal feed according to the historical basic coal feed corresponding to the historical load, the weighted correction is determined according to the degree of deviation between the historical load and the current load; determine the efficiency compensation coefficient according to the deviation between the real-time operating efficiency and the benchmark efficiency corresponding to the current load, and compensate the coal feed after weighted correction; limit the coal feed after efficiency compensation to the preset safe coal feed range, and determine the basic coal feed.

[0046] Furthermore, such as Figure 3As shown, the second determining module 330 is specifically used to preprocess the time-series data of the actual coal feed, including outlier handling and smoothing; calculate the initial correction coefficient based on the preprocessed actual coal feed and the basic coal feed; dynamically adjust the initial correction coefficient in combination with the load dynamic change parameters to obtain the intermediate correction coefficient; perform weighted processing on the intermediate correction coefficient by fusing the historical correction coefficient sequence, with the weighting determined based on the degree of deviation between the historical correction coefficient and the intermediate correction coefficient; limit the weighted correction coefficient to a constraint range that is compatible with the current load range; and perform filtering processing on the constrained correction coefficient to suppress abrupt changes to obtain the first correction coefficient.

[0047] Furthermore, such as Figure 3 As shown, the second determining module 330 is also used to obtain the actual steam pressure of the thermal power unit; determine the target steam pressure of the thermal power unit according to the current load and the preset sliding pressure function; determine the second correction coefficient according to the actual steam pressure and the target steam pressure; and correct the corrected coal feed rate according to the second correction coefficient to obtain the final coal feed rate.

[0048] Furthermore, such as Figure 3 As shown, the second determining module 330 is specifically used to determine the initial value of the target steam pressure based on the load range where the current load is located, and the sliding pressure function for the low load segment: P target For the initial value of the target steam pressure, current tload Given the current load, p is the load fluctuation frequency, K1, K2, and K3 are the fitting coefficients for the low load segment, M1 is the fluctuation correction amplitude, and the sliding pressure function for the medium load segment is: w is the load change rate, K4-K6 are the fitting coefficients for the medium load section, M2 is the nonlinear correction coefficient, and the sliding pressure function for the high load section is: 'a' represents the load change acceleration, K7-K10 represents the fitting coefficient for the high load segment, and M3 represents the saturation correction coefficient. The deviation sequence between the actual and theoretical values ​​of the target steam pressure within the same historical load range and operating time segment is obtained. The mean and standard deviation of the deviation sequence are calculated, and historical deviation data meeting preset validity conditions are selected based on the mean and standard deviation. Weighting coefficients are assigned to the selected valid historical deviation data based on the similarity between the current load and historical loads. The historical correction amount is obtained by comparing the valid historical deviation data with the corresponding weighting coefficients. The load dynamic adjustment factor is determined based on the comparison between the absolute value of the load change rate and the preset threshold. The target steam pressure is calculated based on the initial target steam pressure, the historical correction amount, and the load dynamic adjustment factor.

[0049] Furthermore, such as Figure 3As shown, the second determining module 330 is specifically used to calculate the pressure deviation based on the actual steam pressure and the target steam pressure; determine an initial correction coefficient calculation model adapted to the level of the pressure deviation based on the level of the deviation, and thus determine the initial correction coefficient; determine a multi-parameter coupling correction factor based on the boiler pressure response delay time, steam humidity, and furnace temperature; fuse the initial correction coefficient with the multi-parameter coupling correction factor to obtain an intermediate correction coefficient; obtain a sequence of second correction coefficients under the same load range and the same deviation level in history; determine dual weights based on the consistency of the deviation trend and load similarity between the current and historical data; perform weighted fusion of the intermediate correction coefficients; divide dynamic scenarios based on the steam pressure change rate and acceleration; determine adjustment coefficients adapted to each scenario; combine the fused intermediate correction coefficients with the adjustment coefficients; substitute the correction coefficients after combining the adjustment coefficients into the pressure prediction model to calculate the error between the expected steam pressure and the target steam pressure; if the error exceeds the preset range, dynamically adjust the fitting parameters of the initial correction coefficient calculation model, repeat the correction process until the error meets the requirements, and obtain the second correction coefficient.

[0050] Furthermore, such as Figure 3 As shown, the correction module 340 is also used to obtain the real-time change rate of the first correction coefficient and the deviation value between the corrected coal feed and the actual coal feed; determine the slow adjustment trigger threshold according to the current load range and load dynamic change parameters, the slow adjustment trigger threshold includes the change rate threshold and the deviation threshold; when the real-time change rate of the first correction coefficient exceeds the change rate threshold or the deviation value exceeds the deviation threshold, determine the adjustment step size coefficient according to the stability of the current load; obtain the historical change sequence of the first correction coefficient, calculate the historical average change rate, and limit the real-time adjustment step size to a preset proportion of the historical average change rate; and perform gradual correction on the first correction coefficient through a first-order integral step.

[0051] Optionally, the coal feed control device for the thermal power unit may be an electronic device with data processing capabilities, or a functional module within the electronic device, without limitation.

[0052] For example, the electronic device can be a server, which can be a single server or a server cluster consisting of multiple servers. As another example, the electronic device can be a mobile phone, tablet computer, desktop computer, laptop computer, handheld computer, notebook computer, ultra-mobile personal computer (UMPC), netbook, as well as cellular phone, personal digital assistant (PDA), augmented reality (AR), virtual reality (VR) device, and other terminal devices. Furthermore, the electronic device can also be a recording device, video surveillance device, etc. This application does not impose any special limitations on the specific form of the electronic device.

[0053] The following example uses an electronic device for controlling the coal feed rate in a thermal power unit. Figure 4 As shown, Figure 4 The hardware structure of an electronic device 400 provided in this application.

[0054] like Figure 4 As shown, the electronic device 400 includes a processor 410, a communication line 420, and a communication interface 430.

[0055] Optionally, the electronic device 400 may also include a memory 440. The processor 410, memory 440, and communication interface 430 can be connected via a communication line 420.

[0056] The processor 410 can be a central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The processor 410 can also be any other device with processing capabilities, such as a circuit, device, or software module, without limitation.

[0057] In one example, processor 410 may include one or more CPUs, for example Figure 4 CPU0 and CPU1 in the CPU.

[0058] As an optional implementation, electronic device 400 may include multiple processors, for example, in addition to processor 410, it may also include processor 470. Communication line 420 is used to transmit information between the components included in electronic device 400.

[0059] Communication interface 430 is used for communication with other devices or other communication networks. These other communication networks can be Ethernet, Radio Access Network (RAN), Wireless Local Area Networks (WLAN), etc. Communication interface 430 can be a module, circuit, transceiver, or any device capable of enabling communication.

[0060] Memory 440 is used to store instructions. These instructions can be computer programs.

[0061] The memory 440 can be a read-only memory (ROM) or other type of static storage device that can store static information and / or instructions; it can also be a random access memory (RAM) or other type of dynamic storage device that can store information and / or instructions; it can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, etc., without limitation.

[0062] It should be noted that the memory 440 can exist independently of the processor 410, or it can be integrated with the processor 410. The memory 440 can be used to store instructions, program code, or some data, etc. The memory 440 can be located inside or outside the electronic device 400, without restriction.

[0063] The processor 410 is configured to execute instructions stored in the memory 440 to implement the communication method provided in the following embodiments of this application. For example, when the electronic device 400 is a terminal or a chip in a terminal, the processor 410 can execute instructions stored in the memory 440 to implement the steps performed by the transmitting end in the following embodiments of this application.

[0064] As an optional implementation, the electronic device 400 also includes an output device 450 and an input device 460. The output device 450 can be a display screen, speaker, or other device capable of outputting data from the electronic device 400 to the user. The input device 460 can be a keyboard, mouse, microphone, joystick, or other device capable of inputting data into the electronic device 400.

[0065] It should be pointed out that, Figure 4 The structure shown does not constitute a limitation on the electronic device, except... Figure 4 In addition to the components shown, the electronic device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements.

[0066] The coal feed rate control device and application scenarios of thermal power units described in this application are for the purpose of more clearly illustrating the technical solutions of this application, and do not constitute a limitation on the technical solutions provided in this application. As those skilled in the art will know, with the evolution of coal feed rate control devices for thermal power units and the emergence of new business scenarios, the technical solutions provided in this application are also applicable to similar technical problems.

[0067] This application provides a storage medium storing a program that, when executed by a processor, implements the coal feed rate control method for thermal power units.

[0068] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0069] In a typical configuration, the device includes one or more processors (CPUs), memory, and a bus. The device may also include input / output interfaces, network interfaces, etc.

[0070] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM, and memory includes at least one memory chip. Memory is an example of computer-readable media.

[0071] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0072] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0073] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0074] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for controlling the coal feed rate of a thermal power unit, characterized in that, The method comprises: acquiring current load, actual coal supply amount and historical load of a thermal power unit; determining a basic coal supply amount according to the current load, a load dynamic change parameter calculated based on the historical load and the current load, and a basic coal supply amount calculation model adapted to a load interval in which the current load is located; determining a first correction coefficient according to the actual coal supply amount, the basic coal supply amount and the load dynamic change parameter, the first correction coefficient being used to quantify deviation of the actual coal supply amount from the basic coal supply amount and to fuse load dynamic change characteristics to adapt to actual energy demand of the unit; correcting the basic coal supply amount according to the first correction coefficient to obtain a corrected coal supply amount.

2. The method of claim 1, wherein, The determination of the basic coal supply amount according to the current load, the load dynamic change parameter calculated based on the historical load and the current load, and the basic coal supply amount calculation model adapted to the load interval in which the current load is located comprises: determining, according to a load interval in which the current load is located, a basic coal supply amount calculation model adapted to the load interval, the calculation model containing an interval characteristic coefficient and a dynamic correction term associated with the load dynamic change parameter; determining a basic coal supply amount initial value according to the calculation model, and performing weighted correction on the basic coal supply amount initial value according to historical basic coal supply amounts corresponding to historical loads, the weighted correction determining weight distribution according to deviation degree of the historical loads from the current load; determining an efficiency compensation coefficient according to deviation of real-time operation efficiency corresponding to the current load from a benchmark efficiency, and compensating the basic coal supply amount after the weighted correction; limiting the basic coal supply amount after the efficiency compensation within a preset safe coal supply amount range to determine the basic coal supply amount.

3. The method of claim 2, wherein, The determination of the first correction coefficient according to the actual coal supply amount, the basic coal supply amount and the load dynamic change parameter comprises: performing preprocessing on time series data of the actual coal supply amount, the preprocessing including outlier processing and smoothing processing; calculating an initial correction coefficient based on the actual coal supply amount after the preprocessing and the basic coal supply amount; dynamically adjusting the initial correction coefficient in combination with the load dynamic change parameter to obtain an intermediate correction coefficient; performing weighted processing on the intermediate correction coefficient in combination with a historical correction coefficient sequence, the weighting determining weight based on deviation degree of the historical correction coefficient from the intermediate correction coefficient; limiting the correction coefficient after the weighted processing within a constraint range adapted to the load interval in which the current load is located; performing filtering processing on the correction coefficient after the constraint to suppress mutation to obtain the first correction coefficient.

4. The method according to any one of claims 1-3, characterized in that, The method further comprises: acquiring actual steam pressure of the thermal power unit; determining target steam pressure of the thermal power unit according to the current load and a preset sliding pressure function; determining a second correction coefficient according to the actual steam pressure and the target steam pressure; correcting the corrected coal supply amount according to the second correction coefficient to obtain a final coal supply amount.

5. The method of claim 4, wherein, The determination of the target steam pressure of the thermal power unit according to the current load and the preset sliding pressure function comprises: Determine the target steam pressure initial value according to the load interval where the current load is located, the sliding pressure function in the low load section: , P target is the target steam pressure initial value, current load is the current load, p is the load fluctuation frequency, K1-K3 are fitting coefficients in the low load section, M1 is the fluctuation correction amplitude, the sliding pressure function in the medium load section: , w is the load change rate, K4-K6 are fitting coefficients in the medium load section, M2 is the nonlinear correction coefficient, the sliding pressure function in the high load section: , a is the load change acceleration, K7-K10 are fitting coefficients in the high load section, and M3 is the saturation correction coefficient. obtain a deviation sequence of the actual value and the theoretically calculated value of the target steam pressure in the same load interval and the same operation time period, calculate a mean value and a standard deviation of the deviation sequence, and screen historical deviation data meeting a preset validity condition based on the mean value and the standard deviation; assign a weighting coefficient to the screened effective historical deviation data based on the similarity between the current load and the historical load, and obtain a historical correction amount through the effective historical deviation data and the corresponding weighting coefficient; determine a load dynamic adjustment factor according to a comparison result of the absolute value of the load change rate and a preset threshold value; calculate the target steam pressure according to the initial value of the target steam pressure, the historical correction amount, and the load dynamic adjustment factor.

6. The method of claim 5, wherein, determine a second correction coefficient according to the actual steam pressure and the target steam pressure, including: calculate a pressure deviation according to the actual steam pressure and the target steam pressure, determine an initial correction coefficient calculation model adapted to a grade where the pressure deviation is located, to determine an initial correction coefficient, according to the pressure deviation; determine a multi-parameter coupling correction factor according to a boiler pressure response delay time, steam humidity, and furnace temperature, and obtain an intermediate correction coefficient by fusing the initial correction coefficient and the multi-parameter coupling correction factor; obtain a second correction coefficient sequence in the same load interval and under the same deviation grade, determine a double weight according to consistency of deviation trends and load similarity between the current and the historical, and perform weighted fusion on the intermediate correction coefficient; divide dynamic scenarios according to a steam pressure change rate and a change acceleration, determine adjustment coefficients adapted to each scenario, and combine the fused intermediate correction coefficient and the adjustment coefficients; put the correction coefficient combined with the adjustment coefficient into a pressure prediction model, and calculate an error of an expected steam pressure and the target steam pressure; if the error exceeds a preset range, dynamically adjust fitting parameters of the initial correction coefficient calculation model, repeat the correction process until the error meets the requirement, and obtain the second correction coefficient.

7. The method of claim 1, wherein, after obtaining the corrected coal supply amount, the method further includes: obtain a real-time change rate of the first correction coefficient and a deviation value of the corrected coal supply amount and the actual coal supply amount; determine a slow adjustment trigger threshold value according to an interval where the current load is located and a load dynamic change parameter, the slow adjustment trigger threshold value including a change rate threshold value and a deviation threshold value; when the real-time change rate of the first correction coefficient exceeds the change rate threshold value or the deviation value exceeds the deviation threshold value, determine an adjustment step coefficient according to stability of the current load; obtain a historical change sequence of the first correction coefficient, calculate a historical average change rate, and limit a real-time adjustment step to a preset proportion of the historical average change rate; perform gradual correction on the first correction coefficient through a first-order integral link.

8. A coal feed rate control device for thermal power units, characterized in that, the device includes: an obtaining module, configured to obtain a current load, an actual coal supply amount, and historical loads of a thermal power generating unit; a first determining module, configured to determine a basic coal supply amount according to the current load, a load dynamic change parameter calculated based on the historical loads and the current load, and a basic coal supply amount calculation model adapted to an interval where the current load is located; A second determining module is configured to determine a first correction coefficient according to the actual coal supply amount, the basic coal supply amount, and the load dynamic change parameter, the first correction coefficient being used to quantify the deviation between the actual coal supply amount and the basic coal supply amount and to fuse the load dynamic change characteristic to adapt to the actual energy demand of the unit; A correction module is configured to correct the basic coal supply amount according to the first correction coefficient to obtain a corrected coal supply amount.

9. A storage medium, characterized by The storage medium comprises a stored program, wherein the program controls a device where the storage medium is located to execute the coal supply amount control method of the thermal power generating unit according to any one of claims 1-7 when the program is running.

10. An electronic device, comprising: The device comprises at least one processor and at least one memory connected with the processor, and a bus; wherein the processor, the memory, and the bus complete mutual communication; the processor is used to call program instructions in the memory to execute the coal supply amount control method of the thermal power generating unit according to any one of claims 1-7.

Images