Steam flow distribution method, device, equipment and medium
By obtaining the real-time load rate and unit consumption of the boiler, and optimizing steam distribution using performance models and genetic algorithms, the problem of inaccurate steam distribution during boiler operation is solved and energy utilization efficiency is improved.
Patent Information
- Application Number
- CN202411292508.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-14
- Publication Date
- 2024-11-29
AI Technical Summary
During the actual operation of the boiler, due to the lack of real-time adjustment capabilities and effective data utilization methods, it is difficult to dynamically adjust according to the actual operation data of the boiler, resulting in insufficient steam distribution and affecting the energy utilization efficiency of the boiler.
By obtaining the total steam demand of the boiler cluster and the real-time load rate and real-time unit consumption of the target boiler under the first operating condition, the upper and lower limits of the load rate are determined using the load rate-uniform performance model, and the target is determined based on the genetic algorithm to find the best The amount of steam distribution that the boiler should distribute.
Accurate calculation of steam distribution volume is achieved, excessive or insufficient steam distribution is avoided, energy waste is reduced, boilers can operate under optimal operating conditions, and energy conversion efficiency is improved.
Smart Images

Figure CN119042608A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of boiler control, and in particular to a steam flow distribution method, device, equipment and medium. Background Art
[0002] With the continuous development of industrial production, boilers, as important energy conversion equipment, operate efficiently and stably, which is not only related to the economic benefits of enterprises, but also directly affects environmental protection and energy utilization efficiency. However, in the actual operation process, the performance of boilers is often affected by many factors and changes, such as fluctuations in fuel quality, changes in environmental conditions, and natural wear of equipment. These factors work together to cause the actual operating performance of the boiler to gradually deviate from the optimal state at the time of leaving the factory, and the relationship between the load rate and unit energy consumption (unit consumption) also changes. Therefore, how to accurately reflect the actual operating characteristics of the boiler and optimize the steam flow distribution has become a key issue in improving boiler operating efficiency and reducing energy consumption and emissions.
[0003] At present, boiler operation management mainly relies on traditional monitoring systems and manual experience judgment. Although boilers undergo rigorous testing before leaving the factory to determine their optimal load rate-unit consumption curve, in actual operation, due to the lack of real-time adjustment capabilities and effective data utilization methods, it is often difficult to make dynamic adjustments based on the actual operation data of the boiler, resulting in inaccurate steam distribution and affecting the energy efficiency of the boiler. Summary of the invention
[0004] Based on the above problems, the present application provides a steam flow distribution method, device, equipment and medium, which can avoid excessive or insufficient steam distribution and reduce energy waste by accurately calculating the steam distribution amount. Moreover, it can enable the boiler to operate under the optimal working conditions and improve the energy conversion efficiency.
[0005] The embodiments of the present application disclose the following technical solutions:
[0006] In a first aspect, the present application discloses a steam flow distribution method, the method comprising:
[0007] Obtaining a total steam demand of a boiler cluster, and a real-time load rate and a real-time unit consumption of a target boiler of the boiler cluster under a first operating condition;
[0008] By inputting the real-time load rate and the real-time unit consumption into a load rate-unit consumption performance model, a first performance curve matching the real-time load rate and the real-time unit consumption is determined, wherein the first performance curve represents a corresponding relationship between the load rate and the unit consumption under the first working condition;
[0009] Determining an upper limit and a lower limit of a load rate under the first operating condition according to the first performance curve;
[0010] The steam distribution amount to be allocated to the target boiler is determined by optimizing using a genetic algorithm according to the total steam demand, the load rate upper limit and the load rate lower limit.
[0011] Optionally, the method for constructing the load rate-unit consumption performance model includes:
[0012] Acquire a historical data set of the target boiler, wherein the historical data set includes boiler load rate, instantaneous gas consumption and instantaneous steam flow;
[0013] Performing data cleaning on the historical data set to obtain a cleaned historical data set;
[0014] According to the historical data set after cleaning, a plurality of performance curves are fitted, wherein the plurality of performance curves represent the corresponding relationship between the boiler load rate after cleaning and the boiler unit consumption after cleaning under different working conditions, wherein the boiler unit consumption after cleaning is the ratio of the instantaneous gas consumption after cleaning to the instantaneous steam flow rate after cleaning;
[0015] A load rate-unit consumption performance model is constructed according to the multiple performance curves.
[0016] Optionally, the historical data set further includes a boiler operating state, and the boiler operating state includes a normal operating state;
[0017] The step of performing data cleaning on the historical data set to obtain a cleaned historical data set includes:
[0018] The historical data in which the boiler operation state is not in the normal operation state is removed from the historical data set to obtain a cleaned historical data set.
[0019] Optionally, performing data cleaning on the historical data set to obtain a cleaned historical data set includes:
[0020] If the historical data in the historical data set is greater than an upper threshold corresponding to the historical data, and / or less than a lower threshold corresponding to the historical data, the historical data is removed from the historical data set to obtain a cleaned historical data set.
[0021] Optionally, performing data cleaning on the historical data set to obtain a cleaned historical data set includes:
[0022] If there are multiple historical data with repeated values in the historical data set, a cleaned historical data set is obtained by retaining only one historical data among the multiple historical data.
[0023] Optionally, fitting a plurality of performance curves according to the cleaned historical data set includes:
[0024] Dividing the cleaned historical data set into intervals to obtain multiple data bands;
[0025] Performing curve fitting on the multiple data bands respectively to obtain multiple performance curve segments corresponding to the multiple data bands;
[0026] A plurality of performance curves are obtained by integrating the plurality of performance curve segments.
[0027] Optionally, the method for obtaining the real-time load rate and real-time unit consumption of the target boiler of the boiler cluster under the first working condition includes:
[0028] Obtaining the boiler instantaneous steam flow, boiler rated steam capacity and boiler instantaneous gas consumption of the target boiler of the boiler cluster under the first operating condition;
[0029] According to the instantaneous steam flow of the boiler, the rated steam capacity of the boiler and the instantaneous gas consumption of the boiler, the real-time load rate and the real-time unit consumption are obtained, the real-time load rate is the ratio of the instantaneous steam flow of the boiler to the rated steam capacity of the boiler, and the real-time unit consumption is the ratio of the instantaneous gas consumption of the boiler to the instantaneous steam flow of the boiler.
[0030] In a second aspect, the present application discloses a steam flow distribution device, the device comprising: a data acquisition module, a curve determination module, an upper and lower limit determination module and a flow distribution module;
[0031] The data acquisition module is used to obtain the total steam demand of the boiler cluster, and the real-time load rate and real-time unit consumption of the target boiler of the boiler cluster under the first working condition;
[0032] The curve determination module is used to determine a first performance curve matching the real-time load rate and the real-time unit consumption by inputting the real-time load rate and the real-time unit consumption into a load rate-unit consumption performance model, wherein the first performance curve represents a corresponding relationship between the load rate and the unit consumption under the first working condition;
[0033] The upper and lower limit determination module is used to determine the load rate upper limit and the load rate lower limit under the first working condition according to the first performance curve;
[0034] The flow distribution module is used to determine the steam distribution amount to be allocated to the target boiler by optimizing using a genetic algorithm according to the total steam demand, the load rate upper limit and the load rate lower limit.
[0035] Optionally, the load rate-unit consumption performance model construction device comprises: a first construction module, a second construction module, a third construction module and a fourth construction module;
[0036] The first construction module is used to obtain a historical data set of the target boiler, wherein the historical data set includes a boiler load rate, an instantaneous gas consumption, and an instantaneous steam flow rate;
[0037] The second construction module is used to perform data cleaning on the historical data set to obtain a cleaned historical data set;
[0038] The third construction module is used to fit a plurality of performance curves according to the cleaned historical data set, wherein the plurality of performance curves represent the corresponding relationship between the boiler load rate after cleaning and the boiler unit consumption after cleaning under different working conditions, wherein the boiler unit consumption after cleaning is the ratio of the instantaneous gas consumption after cleaning to the instantaneous steam flow rate after cleaning;
[0039] The fourth construction module is used to construct a load rate-unit consumption performance model according to the multiple performance curves.
[0040] Optionally, the historical data set also includes a boiler operating status, and the boiler operating status includes a normal operating status; the second construction module is specifically used to remove historical data in which the boiler operating status is not in the normal operating state from the historical data set to obtain a cleaned historical data set.
[0041] Optionally, the second construction module is specifically used to: if the historical data in the historical data set is greater than an upper threshold corresponding to the historical data, and / or less than a lower threshold corresponding to the historical data, obtain a cleaned historical data set by removing the historical data from the historical data set.
[0042] Optionally, the second construction module is specifically used to: if there are multiple historical data with repeated values in the historical data set, obtain a cleaned historical data set by retaining only one historical data among the multiple historical data.
[0043] Optionally, the third construction module is specifically used to: divide the cleaned historical data set into intervals to obtain multiple data bands; perform curve fitting on the multiple data bands respectively to obtain multiple performance curve segments corresponding to the multiple data bands; and obtain multiple performance curves by integrating the multiple performance curve segments.
[0044] Optionally, the data acquisition module includes: a first acquisition module and a second acquisition module;
[0045] The first acquisition module is used to acquire the boiler instantaneous steam flow, boiler rated steam capacity and boiler instantaneous gas consumption of the target boiler of the boiler cluster under the first operating condition;
[0046] The second acquisition module is used to obtain the real-time load rate and the real-time unit consumption according to the instantaneous steam flow of the boiler, the rated steam capacity of the boiler and the instantaneous gas consumption of the boiler, wherein the real-time load rate is the ratio of the instantaneous steam flow of the boiler to the rated steam capacity of the boiler, and the real-time unit consumption is the ratio of the instantaneous gas consumption of the boiler to the instantaneous steam flow of the boiler.
[0047] In a third aspect, the present application discloses a steam flow distribution device, the device comprising: a memory and a processor;
[0048] The memory is used to store programs;
[0049] The processor is used to execute the program to implement the various steps of the steam flow distribution method as described in the first aspect.
[0050] In a fourth aspect, the present application discloses a computer-readable medium having a computer program stored thereon, wherein when the computer program is executed by a processor, each step of the steam flow distribution method described in the first aspect is implemented.
[0051] Compared with the prior art, this application has the following beneficial effects:
[0052] The embodiment of the present application provides a steam flow distribution method, device, equipment and medium. The method first obtains the total steam demand of the boiler cluster, and the real-time load rate and real-time unit consumption of the target boiler under the first working condition. Secondly, the real-time load rate and real-time unit consumption are input into the pre-constructed load rate-unit consumption performance model, and the load rate upper limit and load rate lower limit under the first working condition are determined according to the first performance curve output by the load rate-unit consumption performance model. Then, the total steam demand, the load rate upper limit and the load rate lower limit are combined, and the steam distribution amount to be allocated to the target boiler is determined by genetic algorithm optimization to meet production needs and optimize energy utilization. Therefore, the steam flow distribution method can avoid excessive or insufficient steam distribution and reduce energy waste by accurately calculating the steam distribution amount. In addition, it can enable the boiler to operate under the optimal working condition and improve energy conversion efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0053] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0054] Figure 1 A flow chart of a steam flow distribution method provided in an embodiment of the present application;
[0055] Figure 2 A flow chart of another steam flow distribution method provided in an embodiment of the present application;
[0056] Figure 3 A flowchart of data cleaning provided in an embodiment of the present application;
[0057] Figure 4 A schematic diagram of data cleaning provided in an embodiment of the present application;
[0058] Figure 5 A schematic diagram of a performance curve of a load rate-unit consumption performance model provided in an embodiment of the present application;
[0059] Figure 6 A schematic diagram of a steam flow distribution device provided in an embodiment of the present application;
[0060] Figure 7 A schematic diagram of a computer-readable medium provided for an embodiment of the present application. DETAILED DESCRIPTION
[0061] As described above, the current boiler operation management mainly relies on traditional monitoring systems and manual experience judgment. Although the boiler will undergo rigorous testing before leaving the factory to determine its optimal load rate-unit consumption curve, in the actual operation process, due to the lack of real-time adjustment capabilities and effective data utilization methods, it is often difficult to make dynamic adjustments based on the actual operation data of the boiler, resulting in inaccurate steam distribution and affecting the energy efficiency of the boiler.
[0062] After research, the inventor has proposed a steam flow distribution method, device, equipment and medium. The steam flow distribution method provided in the embodiment of the present application can avoid excessive or insufficient steam distribution and reduce energy waste by accurately calculating the steam distribution amount. In addition, it can enable the boiler to operate under the optimal working conditions and improve the energy conversion efficiency.
[0063] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0064] See also Figure 1 , which is a flow chart of a steam flow distribution method provided in an embodiment of the present application.
[0065] S101: Obtain the total steam demand of the boiler cluster, and the real-time load rate and real-time unit consumption of the target boiler of the boiler cluster under the first working condition.
[0066] The total steam demand of a boiler cluster refers to the total amount of steam that all boilers in the boiler cluster need to produce together, that is, the total amount of steam that the boiler cluster needs to provide in order to meet specific process or production requirements.
[0067] The real-time load rate refers to the ratio of the actual operating power or capacity of the target boiler under the first operating condition to its designed maximum power or capacity. It reflects the current operating status and efficiency of the target boiler and is an important indicator for evaluating the performance of the target boiler.
[0068] Real-time unit consumption refers to the amount of fuel consumed by the target boiler in the process of generating unit steam. Real-time unit consumption is related to the energy efficiency and operating cost of the target boiler. By monitoring real-time unit consumption, we can understand the energy utilization of the target boiler, discover potential energy waste problems, and take corresponding measures to optimize it.
[0069] S102: By inputting the real-time load rate and the real-time unit consumption into the load rate-unit consumption performance model, a first performance curve matching the real-time load rate and the real-time unit consumption is determined, and the first performance curve represents the corresponding relationship between the load rate and the unit consumption under the first working condition.
[0070] By inputting the real-time load rate and the real-time unit consumption into the load rate-unit consumption performance model, the load rate-unit consumption performance model will analyze these data and determine the first performance curve that matches the real-time load rate and the real-time unit consumption among the multiple performance curves included in the load rate-unit consumption performance model. Among them, the first performance curve may be an empirical formula, a set of data points, or a curve obtained by data fitting. This first performance curve characterizes the corresponding relationship between the load rate and the unit consumption of the boiler under the first operating condition (i.e., the operating condition corresponding to the current real-time load rate and the real-time unit consumption). Once the first performance curve is determined, it can be used to guide the operation of the target boiler. For example, the load distribution, fuel supply or operating parameters of the boiler can be adjusted according to the performance curve to optimize steam production, reduce energy consumption and reduce operating costs.
[0071] S103: Determine the load rate upper limit and the load rate lower limit under the first operating condition according to the first performance curve.
[0072] There are usually many key points on the first performance curve, such as the highest efficiency point, the safe operation boundary point, the performance sharp drop point, etc. The upper limit of the load rate is usually set before the performance sharp drop point or the safe operation boundary point. That is to say, if the first performance curve shows that the performance begins to drop significantly after a certain load rate, or reaches the maximum safe load of the boiler, then this load rate can be used as the upper limit of the load rate.
[0073] The setting of the lower limit of the load rate is usually based on considerations of economy and operational stability. If the boiler's operating efficiency is extremely low at a certain load rate, or there is a risk of unsafe operation, then this load rate can be used as the lower limit of the load rate.
[0074] Exemplarily, assume that the first performance curve shows that: when the load rate is 70%, the target boiler reaches the highest efficiency; when the load rate exceeds 85%, the efficiency of the target boiler begins to drop significantly; and when the load rate is lower than 30%, the target boiler operates unstably and has extremely low efficiency. Then the upper limit of the load rate can be set to 85% to ensure that the target boiler operates within an efficient and safe range. At the same time, the lower limit of the load rate is set to 30% to avoid inefficient and unstable operation of the target boiler at low load rates. It should be noted that the above values are only examples, and this application does not limit the specific values of the upper and lower limits of the load rate.
[0075] S104: According to the total steam demand, the upper limit of the load rate and the lower limit of the load rate, a genetic algorithm is used to optimize and determine the steam allocation amount that should be allocated to the target boiler.
[0076] Since the first performance curve provides the upper and lower limits of the load factor of the target boiler under the first working condition, the steam distribution amount to be allocated to the target boiler can be determined by genetic algorithm optimization according to the total steam demand, the upper and lower limits of the load factor. Once the steam distribution amount of the target boiler is determined, the steam distribution can be achieved by adjusting the operating parameters of the boiler (such as the fuel supply, the steam valve opening, etc.).
[0077] Specifically, the use of genetic algorithm to find the optimal steam distribution amount to be allocated to the target boiler refers to: first, a set of possible steam distribution amounts (i.e., individuals) of the target boiler is randomly generated as the initial population of the genetic algorithm. Secondly, by defining one or more fitness functions, the pros and cons of each individual are evaluated. In the steam flow distribution method provided in the embodiment of the present application, the fitness function takes into account multiple factors, such as the operating efficiency of the target boiler, whether the load rate is within a safe range (i.e., not exceeding the upper limit of the load rate and not less than the lower limit of the load rate), and whether the total steam demand is met. Subsequently, according to the result of the fitness function, multiple individuals with higher fitness are selected as parent individuals, and new offspring individuals are generated by exchanging partial information in multiple parent individuals. Subsequently, partial information of the offspring individuals is randomly changed, and multiple iterations are performed until a certain termination condition is met (such as reaching the maximum number of iterations, the fitness reaches a predetermined threshold, etc.). Finally, after multiple iterations, the genetic algorithm will converge to one or more optimal solutions or approximately optimal solutions. These solutions represent the amount of steam that the target boiler should allocate under the conditions of a given total steam demand, an upper limit of the load rate, and a lower limit of the load rate.
[0078] In summary, the present application discloses a steam flow distribution method, which can avoid excessive or insufficient steam distribution and reduce energy waste by accurately calculating the steam distribution amount. Moreover, it can enable the boiler to operate under optimal conditions and improve energy conversion efficiency.
[0079] See also Figure 2 , which is a flow chart of another steam flow distribution method provided in an embodiment of the present application. The method comprises:
[0080] S201: Obtain historical data sets.
[0081] The historical data set includes boiler load rate, boiler operating status, boiler instantaneous gas consumption, boiler instantaneous steam flow, boiler rated steam capacity, boiler flue gas oxygen content, boiler exhaust temperature, boiler burner opening, etc.
[0082] Among them, the boiler load rate refers to the percentage of the boiler's current output power to its rated power. The boiler operating status includes information on whether the boiler is in normal operation, standby, fault, etc., which helps to identify abnormal operating conditions and conduct targeted analysis. The boiler's instantaneous gas consumption indicates the boiler's gas consumption at a certain moment. The boiler's instantaneous steam flow indicates the amount of steam generated by the boiler at a certain moment. The boiler's rated steam capacity indicates the maximum steam production capacity of the boiler when it is designed. The boiler's flue gas oxygen content reflects the residual oxygen in the boiler's combustion process and is an important basis for evaluating the sufficiency of combustion and adjusting combustion parameters. The boiler burner opening indicates the opening of the burner regulating valve or damper, which directly affects the fuel supply and combustion efficiency.
[0083] S202: Clean the historical data set to obtain a cleaned historical data set.
[0084] See also Figure 3 , which is a flow chart of data cleaning provided in an embodiment of the present application.
[0085] First, the historical data in the historical data set is aggregated to obtain an aggregated historical data set. Data aggregation helps to integrate scattered and fine-grained data into aggregated data that is easier to analyze and process, thereby improving subsequent computing efficiency.
[0086] Exemplarily, the instantaneous steam flow in the historical data set of the boiler may be aggregated according to the time window, that is, the instantaneous steam flow in the historical data set of the boiler may be added according to the time window to obtain the total steam flow in the time window.
[0087] Secondly, pattern recognition is performed on the aggregated historical data set, and the aggregated historical data set is filtered according to the pattern recognition result to obtain a filtered historical data set.
[0088] Exemplarily, the operation mode of the boiler includes a stable operation mode, an unstable operation mode, and a non-operation mode. For the boiler load rate in the aggregated historical data set, what is needed is the boiler load rate in the stable operation mode, while the boiler load rate in the unstable operation mode and the non-operation mode cannot accurately reflect the performance state of the boiler, and the boiler load rate in the unstable operation mode and the non-operation mode will interfere with the generation of the performance curve, so the boiler load rate in the unstable operation mode and the non-operation mode (i.e., the boiler load rate that is not in a normal operation state) needs to be eliminated, and the boiler load rate in the stable operation mode is screened, thereby obtaining the screened historical data set.
[0089] Subsequently, the filtered historical data set is subjected to single value cleaning to obtain a single value cleaned historical data set. Single value cleaning refers to removing outliers and duplicate values in the filtered historical data set. These outliers may be caused by measurement errors, equipment failures, or data entry errors, while duplicate values may be caused by repeated operations or system failures during data recording.
[0090] In one example, for numerical data such as the instantaneous gas consumption and instantaneous steam flow of the boiler, the threshold method can be used to eliminate outliers. The threshold method is a way of detecting outliers, which identifies and eliminates data that exceeds a preset range by setting a threshold. Specifically, an upper threshold and / or a lower threshold are set based on the experience of using the boiler or domain knowledge; the filtered historical data set is cleaned with single values using the upper threshold and / or the lower threshold, and historical data that is greater than the upper threshold corresponding to the historical data and / or less than the lower threshold corresponding to the historical data is eliminated.
[0091] In other examples, for numerical data such as instantaneous gas consumption and instantaneous steam flow of boilers, duplicate values can be removed by using the duplicate value elimination method. Specifically, if there are multiple historical data with repeated values in the filtered historical data set, only one historical data among the multiple historical data is retained to obtain a single value cleaned historical data set.
[0092] Then, the historical data set after single value cleaning is subjected to association cleaning to obtain the historical data set after association cleaning. Association cleaning refers to the step of identifying and eliminating abnormal data according to the logical relationship or business rules between data.
[0093] For example, if the boiler burner opening in the historical data set after single value cleaning is 0, then theoretically the boiler instantaneous steam flow and boiler instantaneous gas consumption should also be 0 (or close to 0, considering possible measurement errors). If the boiler instantaneous steam flow and boiler instantaneous gas consumption are not 0 (or not close to 0), then the historical data set of "boiler burner opening-boiler instantaneous steam flow-boiler instantaneous gas consumption" is removed or replaced with a reasonable value (such as 0), so as to obtain the historical data set after association cleaning.
[0094] Finally, the historical data set after association cleaning is filtered to obtain the cleaned historical data set. The purpose of filtering is to reduce the random noise and abnormal fluctuations in the historical data set after association cleaning through smoothing, so as to obtain more stable and representative data, providing a reliable basis for subsequent data analysis and modeling.
[0095] Exemplarily, the historical data set after association cleaning can be subjected to sliding window filtering. Sliding window filtering smoothes the data by sliding a fixed-size window on the data of the historical data set after association cleaning and calculating certain statistics (such as mean, median, etc.) of the data in the window. This method can effectively reduce the random noise in the data while retaining the overall trend of the data. However, it should be noted that the size of the sliding window needs to be selected according to the degree of smoothness to be achieved. A larger sliding window will produce smoother data, but may result in the loss of some details of the data.
[0096] It should be noted that for the order of the above processing steps, it is necessary to ensure that pattern recognition is performed before single value cleaning and association cleaning, because pattern recognition relies on coherent data, so this process needs to be completed before cleaning, otherwise the amount of data finally cleaned will be very small. In addition, it is necessary to ensure that data filtering processing needs to be performed after single value cleaning and association cleaning, otherwise it will pollute the original data and create new noise.
[0097] See also Figure 4 , which is a schematic diagram of data cleaning provided by an embodiment of the present application. Among them, taking the historical data set including boiler load rate, boiler instantaneous gas consumption and boiler instantaneous steam flow as an example:
[0098] The relationship between boiler load rate and boiler steam unit consumption (i.e., the ratio of boiler instantaneous gas consumption to boiler instantaneous steam flow rate) before data cleaning of boiler A and boiler B can be respectively as follows: Figure 4 (a) and Figure 4 As shown in (b) in . Figure 4 (a) and Figure 4(b) in the figure shows the natural relationship between boiler load rate and boiler steam consumption. Although this relationship contains noise and outliers, it generally reflects the trend that boiler steam consumption decreases as boiler load rate increases.
[0099] The relationship between boiler load rate and boiler steam consumption after averaging boiler A and boiler B can be shown as follows: Figure 4 (c) and Figure 4 As shown in (d) in the figure. Mean processing calculates the average value of historical data through a sliding window or other means, thereby smoothing out fluctuations. However, the disadvantage of mean processing is that it masks the true trend of data changes, especially when the number of data points is small or the window size is not selected properly. Figure 4 In (c) and (d), it can be seen that the distribution of boiler load rate and boiler steam consumption after mean processing is more concentrated, and the change trend is leveled, which no longer obviously reflects the trend of boiler steam consumption decreasing with increasing load rate.
[0100] The relationship between the boiler load rate and the boiler steam unit consumption obtained after the boiler A and the boiler B are cleaned as in step S202 can be respectively as follows: Figure 4 (e) and Figure 4 As shown in (f) in . Figure 4 (e) and Figure 4 As shown in (f), the cleaning of step S202 not only removes noise and outliers, making the distribution of boiler load rate and boiler steam consumption more reasonable after cleaning, but also shows that the boiler steam consumption decreases monotonically with the increase of boiler load rate. This trend is consistent with the actual operating characteristics of the boiler, indicating that the cleaning method of step S202 effectively improves the accuracy and reliability of the data.
[0101] S203: Obtain the cleaned boiler load rate and boiler unit consumption according to the cleaned historical data set.
[0102] In the steam flow distribution method provided in the embodiment of the present application, if the cleaned historical data set obtained in step S202 includes the cleaned boiler load rate, the cleaned boiler load rate is directly obtained. If the cleaned historical data obtained in step S202 does not include the cleaned boiler load rate, the cleaned boiler load rate is calculated by the following formula (1):
[0103] f 负荷率 =g 蒸汽流量 ÷g 额定容量 (1)
[0104] Among them, f 负荷率 is the boiler load rate after cleaning, g 蒸汽流量 is the instantaneous steam flow rate of the boiler after cleaning, g 额定容量is the rated steam capacity of the boiler after cleaning. Formula (1) calculates the boiler load rate by the ratio of the instantaneous steam flow rate of the boiler to the rated steam capacity.
[0105] And, the boiler unit consumption after cleaning is calculated by the following formula (2):
[0106] q 单耗 =q 燃气耗量 ÷g 蒸汽流量 (2)
[0107] Among them, q 单耗 is the boiler unit consumption after cleaning, q 燃气耗量 is the instantaneous gas consumption of the boiler after cleaning, g 蒸汽流量 is the instantaneous steam flow rate of the boiler after cleaning. Formula (2) calculates the unit consumption of the boiler by the ratio of the instantaneous gas consumption of the boiler to the instantaneous steam flow rate, that is, the amount of gas consumed per unit of steam.
[0108] S204: fitting multiple performance curves according to the boiler load rate and boiler unit consumption after cleaning.
[0109] Multiple performance curves represent the corresponding relationship between the boiler load rate and the boiler unit consumption after cleaning under different working conditions. The purpose of curve fitting is to find a mathematical curve that can best describe the distribution and change trend of boiler load rate and boiler unit consumption.
[0110] Exemplarily, multiple performance curves may be generated by using a variety of curve fitting methods such as linear regression, polynomial regression, and nonlinear regression.
[0111] In some specific implementations, since the boiler load rate and boiler unit consumption after cleaning may present a wider data band distribution, in order to improve the accuracy and reliability of the fitting, the following steps are usually taken:
[0112] First, the cleaned boiler load rate and boiler unit consumption are divided into multiple smaller data subsets according to one or some dimensions (such as boiler load rate, boiler unit consumption, or a combination of the two), each of which is called a "data band". These data bands should be narrow enough to ensure that the change trend or characteristics of the data are relatively consistent within each data band. In this way, curve fitting can be performed on the data in each interval separately, rather than fitting the entire data set at one time.
[0113] Then, for each divided data band, select a suitable mathematical model (such as linear model, polynomial model, nonlinear model, etc.) to perform curve fitting. After completing the curve fitting of all data bands, these fitted curves are integrated together to form a complete performance curve chart (including multiple performance curves). This performance curve chart shows the relationship between boiler load rate and boiler unit consumption. In addition, due to the interval division and separate fitting, this performance curve chart can more accurately reflect the unit consumption characteristics of the data at different load rates.
[0114] S205: Construct a load rate-unit consumption performance model according to the multiple performance curves.
[0115] Based on the performance curve fitted in step S204, a load rate-unit consumption performance model is constructed. This load rate-unit consumption performance model will be able to predict or optimize the distribution of steam flow according to the current boiler load rate and / or other related parameters to achieve the purpose of improving energy utilization efficiency, reducing energy consumption, etc.
[0116] S206: Obtain the total steam demand of the boiler cluster, and the real-time load rate and real-time unit consumption of the target boiler of the boiler cluster under the first working condition.
[0117] It can be understood that steps S206-S209 are similar to the above-mentioned steps S101-S104 and will not be described in detail here.
[0118] S207: Determine a first performance curve matching the real-time load rate and the real-time unit consumption by inputting the real-time load rate and the real-time unit consumption into a load rate-unit consumption performance model.
[0119] S208: Determine the load rate upper limit and the load rate lower limit under the first operating condition according to the first performance curve.
[0120] S209: Based on the total steam demand, the upper limit of the load rate and the lower limit of the load rate, a genetic algorithm is used to optimize and determine the steam allocation amount that should be allocated to the target boiler.
[0121] In summary, the present application discloses a steam flow distribution method, which can avoid excessive or insufficient steam distribution and reduce energy waste by accurately calculating the steam distribution amount. Moreover, it can enable the boiler to operate under optimal conditions and improve energy conversion efficiency.
[0122] See also Figure 6 , which is a schematic diagram of a steam flow distribution device provided in an embodiment of the present application. The steam flow distribution device 300 includes: a data acquisition module 301, a curve determination module 302, an upper and lower limit determination module 303 and a flow distribution module 304;
[0123] The data acquisition module 301 is used to obtain the total steam demand of the boiler cluster, and the real-time load rate and real-time unit consumption of the target boiler of the boiler cluster under the first working condition;
[0124] A curve determination module 302 is used to determine a first performance curve matching the real-time load rate and the real-time unit consumption by inputting the real-time load rate and the real-time unit consumption into a load rate-unit consumption performance model, wherein the first performance curve represents a corresponding relationship between the load rate and the unit consumption under a first working condition;
[0125] The upper and lower limit determination module 303 is used to determine the upper and lower limits of the load factor under the first working condition according to the first performance curve;
[0126] The flow distribution module 304 is used to determine the steam distribution amount to be allocated to the target boiler by using a genetic algorithm according to the total steam demand, the upper limit of the load factor and the lower limit of the load factor.
[0127] In some specific implementations, a device for constructing a load rate-unit consumption performance model includes: a first construction module, a second construction module, a third construction module, and a fourth construction module;
[0128] The first building module is used to obtain a historical data set of a target boiler, the historical data set including boiler load rate, instantaneous gas consumption and instantaneous steam flow;
[0129] The second construction module is used to clean the historical data set to obtain a cleaned historical data set;
[0130] The third construction module is used to fit multiple performance curves according to the historical data set after cleaning, and the multiple performance curves represent the corresponding relationship between the boiler load rate after cleaning and the boiler unit consumption after cleaning under different working conditions. The boiler unit consumption after cleaning is the ratio of the instantaneous gas consumption after cleaning to the instantaneous steam flow rate after cleaning;
[0131] The fourth building module is used to build a load rate-unit consumption performance model according to multiple performance curves.
[0132] In some specific implementations, the historical data set also includes the boiler operating status, which includes the normal operating status; the second construction module is specifically used to remove historical data in which the boiler operating status is not in the normal operating state from the historical data set to obtain a cleaned historical data set.
[0133] In some specific implementations, the second construction module is specifically used to: if the historical data in the historical data set is greater than an upper threshold corresponding to the historical data, and / or less than a lower threshold corresponding to the historical data, then the historical data is removed from the historical data set to obtain a cleaned historical data set.
[0134] In some specific implementations, the second construction module is specifically used for: if there are multiple historical data with repeated values in the historical data set, obtaining a cleaned historical data set by retaining only one historical data among the multiple historical data.
[0135] In some specific implementations, the third construction module is specifically used to: divide the cleaned historical data set into intervals to obtain multiple data bands; perform curve fitting on the multiple data bands respectively to obtain multiple performance curve segments corresponding to the multiple data bands; and obtain multiple performance curves by integrating multiple performance curve segments.
[0136] In some specific implementations, the data acquisition module 301 includes: a first acquisition module and a second acquisition module;
[0137] A first acquisition module is used to acquire the boiler instantaneous steam flow, boiler rated steam capacity and boiler instantaneous gas consumption of a target boiler of the boiler cluster under a first operating condition;
[0138] The second acquisition module is used to obtain the real-time load rate and real-time unit consumption according to the instantaneous steam flow of the boiler, the rated steam capacity of the boiler and the instantaneous gas consumption of the boiler. The real-time load rate is the ratio of the instantaneous steam flow of the boiler to the rated steam capacity of the boiler, and the real-time unit consumption is the ratio of the instantaneous gas consumption of the boiler to the instantaneous steam flow of the boiler.
[0139] In summary, the present application discloses a steam flow distribution device, which can avoid excessive or insufficient steam distribution and reduce energy waste by accurately calculating the steam distribution amount. Moreover, it can enable the boiler to operate under optimal conditions and improve energy conversion efficiency.
[0140] The embodiment of the present application also provides a corresponding steam flow distribution device and a computer-readable medium for implementing the steam flow distribution method provided in the embodiment of the present application.
[0141] Among them, the steam flow distribution device includes a memory and a processor, the memory is used to store instructions or codes, and the processor is used to execute instructions or codes so that the device executes a steam flow distribution method of any embodiment of the present application.
[0142] See also Figure 7 , which is a schematic diagram of a computer-readable medium provided in an embodiment of the present application. The computer-readable medium 400 stores a computer program 411, which implements the above-mentioned Figure 1 Steps of the steam flow distribution method.
[0143] It should be noted that in the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0144] It should be noted that the machine-readable medium mentioned above in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
[0145] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.
[0146] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.
[0147] Although several specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present application. Certain features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination.
[0148] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.
Claims
1. A steam flow distribution method, characterized in that: The method comprises: Obtaining a total steam demand of a boiler cluster, and a real-time load rate and a real-time unit consumption of a target boiler of the boiler cluster under a first operating condition; By inputting the real-time load rate and the real-time unit consumption into a load rate-unit consumption performance model, a first performance curve matching the real-time load rate and the real-time unit consumption is determined, wherein the first performance curve represents a corresponding relationship between the load rate and the unit consumption under the first working condition; Determining an upper limit and a lower limit of a load rate under the first operating condition according to the first performance curve; The steam distribution amount to be allocated to the target boiler is determined by optimizing using a genetic algorithm according to the total steam demand, the load rate upper limit and the load rate lower limit.
2. The method according to claim 1, characterized in that The method for constructing the load rate-unit consumption performance model comprises: Acquire a historical data set of the target boiler, wherein the historical data set includes boiler load rate, instantaneous gas consumption and instantaneous steam flow; Performing data cleaning on the historical data set to obtain a cleaned historical data set; According to the historical data set after cleaning, a plurality of performance curves are fitted, wherein the plurality of performance curves represent the corresponding relationship between the boiler load rate after cleaning and the boiler unit consumption after cleaning under different working conditions, wherein the boiler unit consumption after cleaning is the ratio of the instantaneous gas consumption after cleaning to the instantaneous steam flow rate after cleaning; A load rate-unit consumption performance model is constructed according to the multiple performance curves.
3. The method according to claim 2, characterized in that The historical data set also includes boiler operating status, and the boiler operating status includes a normal operating status; The step of performing data cleaning on the historical data set to obtain a cleaned historical data set includes: The historical data in which the boiler operation state is not in the normal operation state is removed from the historical data set to obtain a cleaned historical data set.
4. The method according to claim 2, characterized in that: The step of performing data cleaning on the historical data set to obtain a cleaned historical data set includes: If the historical data in the historical data set is greater than an upper threshold corresponding to the historical data, and / or less than a lower threshold corresponding to the historical data, the historical data is removed from the historical data set to obtain a cleaned historical data set.
5. The method according to claim 2, characterized in that: The step of performing data cleaning on the historical data set to obtain a cleaned historical data set includes: If there are multiple historical data with repeated values in the historical data set, a cleaned historical data set is obtained by retaining only one historical data among the multiple historical data.
6. The method according to claim 2, characterized in that The step of fitting multiple performance curves according to the cleaned historical data set includes: Dividing the cleaned historical data set into intervals to obtain multiple data bands; Performing curve fitting on the multiple data bands respectively to obtain multiple performance curve segments corresponding to the multiple data bands; A plurality of performance curves are obtained by integrating the plurality of performance curve segments.
7. The method according to claim 1, characterized in that The method for obtaining the real-time load rate and real-time unit consumption of the target boiler of the boiler cluster under the first working condition includes: Obtaining the boiler instantaneous steam flow, boiler rated steam capacity and boiler instantaneous gas consumption of the target boiler of the boiler cluster under the first operating condition; According to the instantaneous steam flow of the boiler, the rated steam capacity of the boiler and the instantaneous gas consumption of the boiler, the real-time load rate and the real-time unit consumption are obtained, the real-time load rate is the ratio of the instantaneous steam flow of the boiler to the rated steam capacity of the boiler, and the real-time unit consumption is the ratio of the instantaneous gas consumption of the boiler to the instantaneous steam flow of the boiler.
8. A steam flow distribution device, characterized in that: The device comprises: a data acquisition module, a curve determination module, an upper and lower limit determination module and a flow distribution module; The data acquisition module is used to obtain the total steam demand of the boiler cluster, and the real-time load rate and real-time unit consumption of the target boiler of the boiler cluster under the first working condition; The curve determination module is used to determine a first performance curve matching the real-time load rate and the real-time unit consumption by inputting the real-time load rate and the real-time unit consumption into a load rate-unit consumption performance model, wherein the first performance curve represents a corresponding relationship between the load rate and the unit consumption under the first working condition; The upper and lower limit determination module is used to determine the load rate upper limit and the load rate lower limit under the first working condition according to the first performance curve; The flow distribution module is used to determine the steam distribution amount to be allocated to the target boiler by optimizing using a genetic algorithm according to the total steam demand, the load rate upper limit and the load rate lower limit.
9. A steam flow distribution device, characterized in that: The device comprises: a memory and a processor; The memory is used to store programs; The processor is used to execute the program to implement each step of the steam flow distribution method according to any one of claims 1 to 7.
10. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the steam flow distribution method according to any one of claims 1 to 7 is implemented.
