A Soft Measurement Method, System, Device and Medium for Heating Extraction Steam Flow

Abstract

The present invention discloses a method, system, device and medium for soft measurement of heating extraction steam flow rate. The method for soft measurement of heating extraction steam flow rate is used for measuring the heating extraction steam flow rate during the zero output operation of the low-pressure cylinder of a steam turbine, and includes: when the low-pressure cylinder of the steam turbine operates at zero output, obtaining the steam flow rate passing through the last stage of the intermediate-pressure cylinder, obtaining the cooling steam flow rate of the low-pressure cylinder, and obtaining the inlet steam flow rate of a low-pressure heater communicated with the exhaust steam of the intermediate-pressure cylinder; calculating to obtain the heating extraction steam flow rate, and the calculation expression is, G = G0 - G h - G LPC ; in the formula, G is the heating extraction steam flow rate, G0 is the steam flow rate passing through the last stage of the intermediate-pressure cylinder, G LPC is the cooling steam flow rate of the low-pressure cylinder, G h is the inlet steam flow rate of the low-pressure heater communicated with the exhaust steam of the intermediate-pressure cylinder; the time stamps of G, G0, G LPC and G h are consistent. The present invention can indirectly calculate the heating steam flow rate and simultaneously meet the steady-state and variable load conditions.

Description

Technical Field

[0001] The present invention belongs to the cross - field of steam turbine technology, information technology and measurement technology in thermal power plants, and particularly relates to a soft - measurement method, system, device and medium for extraction steam flow rate for heating. Background Technique

[0002] In recent years, with the rapid development of new - energy power generation, in order to ensure the stability of the power system, higher requirements are put forward for the operation flexibility of thermal power units. More and more thermal power units have completed flexibility transformation, and the zero - output condition of the low - pressure cylinder has become one of the main operation modes of thermal power units during the heating season. Under the zero - output condition of the low - pressure cylinder, the extraction steam flow rate for heating is one of the important factors characterizing the overall operation economy of the unit and is also one of the important monitoring parameters to meet the requirements of heat users.

[0003] At present, the measurement forms of the heating steam flow rate and the existing defects include:

[0004] (1) Direct measurement is carried out through throttling devices. However, due to factors such as low pressure, large specific volume, low flow velocity of heating steam, and wide diameter of heating pipelines, the measurement error of the throttling device is large, and it is difficult to ensure accuracy; in some cases, due to the unreasonable layout of heating steam pipelines, the installation conditions of throttling devices are not met, and direct measurement cannot be carried out.

[0005] (2) Indirectly calculate the heating steam flow rate through the heat absorption of the water side of the heat - network heat exchanger. However, since the distance from the steam extraction port of the steam turbine to the heat - network heat exchanger is long, the delay of the calculation result is large, and it is difficult to effectively guide the operation of the steam turbine.

[0006] (3) Calculate the heating steam flow rate through the heat balance and flow balance of the steam turbine thermal system. However, this method is only applicable to steady - state operation conditions, and most actual operation conditions do not meet this requirement.

[0007] In summary, it is urgent to develop a new soft - measurement method for the extraction steam flow rate for heating during the zero - output operation of the low - pressure cylinder of the steam turbine. Summary of the Invention

[0008] The purpose of the present invention is to provide a soft - measurement method, system, device and medium for extraction steam flow rate for heating to solve one or more of the above - mentioned technical problems. The soft - measurement method for extraction steam flow rate for heating provided by the present invention is specifically a soft - measurement method for extraction steam flow rate for heating during the zero - output operation of the low - pressure cylinder of the steam turbine. Through the measurement data of other measuring points, the heating steam flow rate can be indirectly calculated, and both steady - state and variable - load conditions are satisfied.

[0009] To achieve the above - mentioned purpose, the present invention adopts the following technical solutions:

[0010] A method for soft measurement of extraction steam flow rate provided in the first aspect of the present invention is used for measuring the extraction steam flow rate during the zero output operation of the low-pressure cylinder of a steam turbine, and includes the following steps:

[0011] During the zero output operation of the low-pressure cylinder of the steam turbine, obtain the steam flow rate passing through the last stage of the intermediate-pressure cylinder, obtain the cooling steam flow rate of the low-pressure cylinder, and obtain the inlet steam flow rate of the low-pressure heater connected to the exhaust of the intermediate-pressure cylinder;

[0012] Calculate to obtain the extraction steam flow rate, and the calculation expression is G = G0 - G h -G LPC ; where G is the extraction steam flow rate, G0 is the steam flow rate passing through the last stage of the intermediate-pressure cylinder, G LPC is the cooling steam flow rate of the low-pressure cylinder, and G h is the inlet steam flow rate of the low-pressure heater connected to the exhaust of the intermediate-pressure cylinder; the time stamps of G, G0, and G LPC and G h are consistent;

[0013] Among them, the step of obtaining the inlet steam flow rate of the low-pressure heater connected to the exhaust of the intermediate-pressure cylinder includes: during the zero output operation of the low-pressure cylinder of the steam turbine, based on the pre-obtained time compensation amount, collect the inlet water temperature, inlet water flow rate, inlet steam pressure, inlet steam temperature, drain temperature, water level, and outlet water temperature of the low-pressure heater connected to the exhaust of the intermediate-pressure cylinder; use the pre-trained heater inlet steam flow rate prediction model to obtain the inlet steam flow rate of the low-pressure heater connected to the exhaust of the intermediate-pressure cylinder.

[0014] A further improvement of the method of the present invention is that the step of obtaining the steam flow rate passing through the last stage of the intermediate-pressure cylinder includes:

[0015] Obtain the steam flow rate passing through the last stage of the intermediate-pressure cylinder through calculation; in the formula, F ν is the reference characteristic flow area of the stage, ν0 is the specific volume of the steam at the inlet of the stage, p0 is the steam pressure at the inlet of the stage, and π is the ratio of the steam pressure after the stage to the steam pressure before the stage.

[0016] A further improvement of the method of the present invention is that the step of obtaining the cooling steam flow rate of the low-pressure cylinder includes: measured by a flow meter installed on the cooling steam bypass under the zero output condition of the low-pressure cylinder.

[0017] A further improvement of the method of the present invention is that the heater inlet steam flow rate prediction model is a GRU neural network model.

[0018] A further improvement of the method of the present invention is that the step of obtaining the pre-trained heater inlet steam flow rate prediction model includes:

[0019] Obtain a training sample set; each training sample in the training sample set includes an input sample value and an output sample value. The input sample value includes sample values of the inlet water temperature, inlet water flow rate, inlet steam pressure, inlet steam temperature, drain water temperature, water level, and outlet water temperature of the low-pressure heater connected to the extraction steam of the intermediate-pressure cylinder. The output sample value is the sample value of the inlet steam flow rate of the low-pressure heater connected to the extraction steam of the intermediate-pressure cylinder corresponding to the input sample value;

[0020] Train the GRU neural network model based on the training sample set until a preset convergence condition is reached to obtain the pre-trained heater inlet steam flow prediction model.

[0021] A further improvement of the method of the present invention is that the obtaining step of each training sample in the training sample set includes:

[0022] Obtain the historical monitoring data of the inlet water temperature, inlet water flow rate, inlet steam pressure, inlet steam temperature, water level, drain water temperature, outlet water temperature, steam pressure at the inlet of the last stage of the intermediate-pressure cylinder, steam temperature at the inlet of the last stage of the intermediate-pressure cylinder, extraction steam pressure of the intermediate-pressure cylinder, inlet steam pressure of the low-pressure cylinder, inlet steam temperature of the low-pressure cylinder, and steam pressure at the outlet of the first stage of the low-pressure cylinder of the low-pressure heater connected to the extraction steam of the intermediate-pressure cylinder within a predetermined time under non-heating conditions;

[0023] Based on the obtained historical monitoring data, through Calculate the steam flow rate G passed through the last stage of the intermediate-pressure cylinder corresponding to each group of data M respectively, and through Calculate the steam flow rate G passed through the first stage of the low-pressure cylinder corresponding to each group of data L ; where F ν is the reference characteristic flow area of the stage, ν0 is the specific volume of the steam at the inlet of the stage, p0 is the steam pressure at the inlet of the stage, and π is the ratio of the steam pressure after the stage to the steam pressure before the stage; calculate the inlet steam flow rate G of the low-pressure heater connected to the extraction steam of the intermediate-pressure cylinder corresponding to each group of data c = G M - G L ;

[0024] Based on the pre-obtained time compensation amount, align the historical monitoring data or calculated data of the inlet water temperature, inlet water flow rate, inlet steam pressure, inlet steam temperature, water level, drain water temperature, outlet water temperature, and inlet steam flow rate of the low-pressure heater connected to the extraction steam of the intermediate-pressure cylinder in time; among them, the time compensation amounts of the inlet steam flow rate, inlet steam pressure, inlet steam temperature, and water level are the same;

[0025] The monitored values of the inlet water temperature, inlet water flow rate, inlet steam pressure, inlet steam temperature, water level, drain temperature, and outlet water temperature of the low-pressure heater connected to the extraction steam from the intermediate-pressure cylinder after time alignment are used as input sample values; the calculated value of the inlet steam flow rate of the low-pressure heater connected to the extraction steam from the intermediate-pressure cylinder after time alignment is used as the output sample value; an independent training sample is formed by the input sample value and the corresponding output sample value.

[0026] A further improvement of the method of the present invention lies in that the obtaining steps of the pre-obtained time compensation amount specifically include:

[0027] Calculate the Pearson correlation coefficients between the monitored data of the inlet water temperature, inlet water flow rate, inlet steam pressure, inlet steam temperature, and drain temperature of the low-pressure heater connected to the extraction steam from the intermediate-pressure cylinder and the outlet water temperature at different delay times within an average heat exchange cycle time of one heater; the delay time corresponding to the maximum Pearson correlation coefficient is used as the time compensation amount of the parameter relative to the outlet water temperature.

[0028] The larger value among the time compensation amounts corresponding to the inlet water temperature and inlet water flow rate is used as the common time compensation amount for both; the larger value among the time compensation amounts corresponding to the inlet steam pressure and inlet steam temperature is used as the common time compensation amount for both; the water level is consistent with the time compensation amounts of the inlet steam pressure and inlet steam temperature.

[0029] Among them, the calculation expression of the average heat exchange cycle of one heater is,

[0030]

[0031] In the formula, T is the average heat exchange cycle of one heater, L vapor is the average path length of the steam side of the heater, v vapor is the designed flow velocity of the steam side of the heater, L water is the average path length of the water side of the heater, v water is the designed flow velocity of the water side of the heater.

[0032] A heat extraction steam flow soft measurement system provided in the second aspect of the present invention is used for measuring the heat extraction steam flow rate during the zero output operation of the low-pressure cylinder of the steam turbine, and includes:

[0033] The first flow rate acquisition module is used to acquire the steam flow rate passing through the last stage of the intermediate-pressure cylinder, acquire the cooling steam flow rate of the low-pressure cylinder, and acquire the inlet steam flow rate of the low-pressure heater connected to the extraction steam from the intermediate-pressure cylinder during the zero output operation of the low-pressure cylinder of the steam turbine;

[0034] The second flow rate acquisition module is used to calculate and obtain the heat extraction steam flow rate, and the calculation expression is, G = G0 - G h -G LPC; where G is the extraction steam flow rate for heating, G0 is the steam flow rate passing through the last stage of the intermediate pressure cylinder, G LPC is the cooling steam flow rate of the low pressure cylinder, G h is the inlet steam flow rate of the low pressure heater connected to the exhaust steam of the intermediate pressure cylinder; G, G0, G LPC is consistent with the time stamp of G h ;

[0035] Among them, the step of obtaining the inlet steam flow rate of the low pressure heater connected to the exhaust steam of the intermediate pressure cylinder includes: when the low pressure cylinder of the steam turbine operates with zero output, based on the pre-obtained time compensation amount, collecting the inlet water temperature, inlet water flow rate, inlet steam pressure, inlet steam temperature, drain temperature, water level and outlet water temperature of the low pressure heater connected to the exhaust steam of the intermediate pressure cylinder; using the pre-trained heater inlet steam flow rate prediction model to obtain the inlet steam flow rate of the low pressure heater connected to the exhaust steam of the intermediate pressure cylinder.

[0036] An electronic device provided in the third aspect of the present invention includes:

[0037] At least one processor; and,

[0038] A memory communicatively connected to the at least one processor; wherein,

[0039] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the heating extraction steam flow rate soft measurement method as described in any one of the above of the present invention.

[0040] A computer-readable storage medium provided in the fourth aspect of the present invention stores a computer program, and when the computer program is executed by a processor, it implements the heating extraction steam flow rate soft measurement method as described in any one of the above of the present invention.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] The soft measurement method for heating extraction steam flow provided by the present invention is specifically a soft measurement method for heating extraction steam flow when the low-pressure cylinder of a steam turbine is running at zero output. The heating steam flow can be indirectly calculated through the measurement data of other measuring points, and the steady-state and variable load conditions can be satisfied at the same time. Specifically and illustratively, the method of the present invention can be used for the soft measurement of heating extraction steam flow when a large condensing steam turbine in a thermal power plant is running in a low-pressure cylinder zero output mode. Specifically and explanatoryally, the method of the present invention back-calculates the flow rate of the last stage of the intermediate pressure cylinder in real time through the reference characteristic flow area of the stage, and then divides the exhaust flow of the intermediate pressure cylinder of the steam turbine into different directions. The method comprises three parts. The GRU neural network model is used to predict the flow rate of the exhaust steam from the intermediate pressure cylinder of the steam turbine to the heater in real time. The cooling steam flow rate to the low pressure cylinder is obtained in real time through the direct measuring point installed in the cooling steam bypass. The heating steam flow rate is obtained by deducting the flow rate to the heater and the low pressure cylinder from the total exhaust steam of the intermediate pressure cylinder. When the method of the present invention is implemented, no additional measuring points need to be installed. The heating steam flow rate under steady state and variable load conditions can be obtained only through the measurement data of conventional measuring points combined with formulas and the GRU neural network model. The method has fast calculation speed and high data accuracy, which can fully meet the actual use requirements of the project. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art; obviously, the drawings described below are some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 It is a schematic flow chart of a method for soft measurement of heating extraction steam flow rate when the low-pressure cylinder of a steam turbine is running at zero output in a specific embodiment of the present invention;

[0045] Figure 2 It is a schematic diagram of the exhaust destination of the intermediate pressure cylinder in a specific embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0047] It should be noted that the terms "first", "second", etc. in the description, claims and above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0048] The following further describes the present invention in detail with reference to the drawings:

[0049] A method for soft measurement of heating extraction steam flow in an embodiment of the present invention is used for measuring the heating extraction steam flow during the zero output operation of the low-pressure cylinder of a steam turbine, and includes the following steps:

[0050] During the zero output operation of the low-pressure cylinder of the steam turbine, obtain the steam flow passing through the last stage of the intermediate-pressure cylinder; obtain the cooling steam flow of the low-pressure cylinder; obtain the inlet steam flow of the low-pressure heater connected to the exhaust of the intermediate-pressure cylinder;

[0051] Calculate to obtain the heating extraction steam flow, and the calculation expression is, G = G0 - G h -G LPC ; where G is the heating extraction steam flow, G0 is the steam flow passing through the last stage of the intermediate-pressure cylinder, G LPC is the cooling steam flow of the low-pressure cylinder, G h is the inlet steam flow of the low-pressure heater connected to the exhaust of the intermediate-pressure cylinder; the time stamps of G, G0, G LPC and G h are consistent;

[0052] Among them, the step of obtaining the inlet steam flow of the low-pressure heater connected to the exhaust of the intermediate-pressure cylinder includes: during the zero output operation of the low-pressure cylinder of the steam turbine, based on the pre-obtained time compensation amount, collect the inlet water temperature, inlet water flow, inlet steam pressure, inlet steam temperature, drain temperature, water level and outlet water temperature of the low-pressure heater connected to the exhaust of the intermediate-pressure cylinder; use the pre-trained inlet steam flow prediction model of the heater to obtain the inlet steam flow of the low-pressure heater connected to the exhaust of the intermediate-pressure cylinder.

[0053] The method for soft measurement of heating extraction steam flow provided by the embodiment of the present invention is specifically a method for soft measurement of heating extraction steam flow during the zero output operation of the low-pressure cylinder of a steam turbine. Through the measurement data of other measuring points, the heating steam flow can be indirectly calculated, and it can meet both steady-state and variable load conditions at the same time.

[0054] Please refer toFigure 1 , a soft measurement method for the heating extraction steam flow rate during the zero output operation of the low-pressure cylinder of a steam turbine according to an embodiment of the present invention, the implementation steps are as follows:

[0055] (1) Calculate the steam flow rate G0 passing through the last stage of the intermediate pressure cylinder, with the unit of kg / s. In the formula, F

[0056] is the reference characteristic flow area of this stage, with the unit of m ν ; ν0 is the specific volume of steam at the inlet of this stage, with the unit of m 2 / kg, which is calculated by the IAPWS-IF97 formula based on the steam pressure and temperature at the inlet of the stage; p0 is the steam pressure at the inlet of this stage, with the unit of Pa, which is directly obtained through the measuring point; π is the ratio of the steam pressure after this stage to the steam pressure before the stage. 3 Specifically and explanatorily, the stage refers to the flow part between any two adjacent extraction ports (including the inlet port and the exhaust port) from the steam inlet of the steam turbine to the exhaust port.

[0057] Specifically and explanatorily, F

[0058] can be calculated and obtained through the data in the steam turbine thermal characteristics book or the performance test data. In the steam turbine heat balance diagram, the inlet and outlet pressures, temperatures, and the flow rate of each stage of the steam turbine can be obtained, so as to calculate the reference characteristic flow area of this stage; in the steam turbine performance test data, the flow rate of the last stage of the intermediate pressure cylinder can be obtained by subtracting the extraction flow rates of each extraction port of the intermediate pressure cylinder from the inlet flow rate of the intermediate pressure cylinder. Combining the inlet and outlet pressures and temperatures of the last stage, the reference characteristic flow area of this stage can be calculated. ν Specifically and explanatorily, F can be calculated and obtained through the data in the steam turbine thermal characteristics book or the performance test data. In the steam turbine heat balance diagram, the inlet and outlet pressures, temperatures, and the flow rate of each stage of the steam turbine can be obtained, so as to calculate the reference characteristic flow area of this stage; in the steam turbine performance test data, the flow rate of the last stage of the intermediate pressure cylinder can be obtained by subtracting the extraction flow rates of each extraction port of the intermediate pressure cylinder from the inlet flow rate of the intermediate pressure cylinder. Combining the inlet and outlet pressures and temperatures of the last stage, the reference characteristic flow area of this stage can be calculated.

[0059] (2) For the low-pressure heaters connected to the exhaust of the intermediate pressure cylinder, align the real-time acquisition data of the inlet water temperature, inlet water flow rate, inlet steam pressure, inlet steam temperature, drain temperature, water level, and outlet water temperature of the heater according to the time compensation amount of each parameter.

[0060] Specifically and explanatorily, generally, part of the steam from the exhaust of the intermediate pressure cylinder enters the low-pressure heater. The flow path of water or steam in the heater is relatively long, and there is a certain time delay in the change of the inlet parameters being reflected in the change of the outlet parameters. Therefore, it is necessary to align each parameter through the time compensation amount.

[0061] Assume that the time compensation amount of the inlet steam pressure for the outlet water temperature of the heater is -5 seconds, which means that after the change of the inlet steam pressure of the heater, it takes about 5 seconds for the change to be conducted to the change of the outlet water temperature of the heater. Then, the outlet water temperature of the heater at time T needs to be aligned with the inlet steam pressure of the heater at time T - 5 seconds.

[0062] (3) Normalize the time-aligned data and input it into the heater steam inlet flow prediction model. Denormalize the model output to obtain the real-time heater steam inlet flow rate G. h , G h is consistent with the timestamps of the steam inlet pressure, steam inlet temperature, and water level in the input data.

[0063] (4) Calculate the heating steam extraction flow rate G after cylinder splitting through G = G0 - G h - G LPC , where G LPC is the low-pressure cylinder cooling steam flow rate, measured by the flowmeter installed in the cooling steam bypass under the zero-output condition of the low-pressure cylinder; during calculation, G, G0, and G LPC must be consistent with the timestamp of G h .

[0064] Please refer to Figure 2 , Figure 2 , which shows the conventional layout after the zero-output transformation of the low-pressure cylinder of the steam turbine. When the steam turbine operates under the zero-output condition of the low-pressure cylinder, the butterfly valve of the medium-low pressure connecting pipe is completely closed, and the exhaust steam flow rate of the medium-pressure cylinder is divided into three parts: one part goes to the heater, one part goes to the heating pipeline, and one part goes to the low-pressure cylinder through the cooling steam bypass as cooling steam; therefore, by subtracting the flow rate to the heater and the cooling steam flow rate from the exhaust steam flow rate of the medium-pressure cylinder, the heating steam extraction flow rate can be obtained.

[0065] The time compensation amounts of the above parameters are calculated in advance before establishing the heater steam inlet flow model, and the method is as follows: calculate the Pearson correlation coefficients between the outlet water temperature of the heater and the inlet water temperature, inlet water flow rate, steam inlet pressure, steam inlet temperature, and drain temperature of the low-pressure heater connected to the exhaust steam of the medium-pressure cylinder at different delay times within one average heat exchange cycle time of the heater respectively. The delay time corresponding to the maximum Pearson correlation coefficient is used as the time compensation amount of this parameter relative to the outlet water temperature of the heater. Take the larger value of the time compensation amounts corresponding to the inlet water temperature and inlet water flow rate of the heater as their common time compensation amount; take the larger value of the time compensation amounts corresponding to the steam inlet pressure and steam inlet temperature as their common time compensation amount; the time compensation amounts of the water level are the same as those of the steam inlet pressure and steam inlet temperature. Since the time compensation amount is calculated based on the outlet water temperature of the heater, the time compensation amount of the outlet water temperature of the heater is 0, as shown in Table 1 specifically.

[0066] Table 1. Time Compensation Amount of Heater Outlet Water Temperature

[0067] Serial number Parameter Time compensation amount 1 Heater inlet water temperature <![CDATA[T1]]> 2 Heater inlet water flow rate <![CDATA[T1]]> 3 Heater inlet steam pressure <![CDATA[T2]]> 4 Heater inlet steam temperature <![CDATA[T2]]> 5 Heater drain temperature <![CDATA[T3]]> 6 Heater water level <![CDATA[T2]]> 7 Heater outlet water temperature 0

[0068] The following takes the time compensation amount of the inlet steam pressure of the heater for the outlet water temperature as an example to illustrate the calculation process. Assume that the average heat exchange cycle of the heater is 20 seconds, and the data acquisition cycle is 1 second. When the delay time takes each integer value between [-20, 20], the Pearson correlation coefficient between the acquired data sequence of the heater outlet water temperature (with a length of 20 seconds) and the acquired data sequence of the heater inlet steam pressure (with a length of 20 seconds and considering the delay time) is calculated respectively. The delay time corresponding to the maximum Pearson correlation coefficient is the time compensation amount of the heater inlet steam pressure relative to the outlet water temperature.

[0069] Specifically exemplary in the embodiments of the present invention, the steps for constructing the inlet steam flow prediction model of the heater are as follows:

[0070] (1) Obtain the historical monitoring data of the inlet water temperature, inlet water flow, inlet steam pressure, inlet steam temperature, water level, drain temperature, outlet water temperature, steam pressure at the inlet of the last stage of the intermediate pressure cylinder, steam temperature at the inlet of the last stage of the intermediate pressure cylinder, exhaust steam pressure of the intermediate pressure cylinder, inlet steam pressure of the low pressure cylinder, inlet steam temperature of the low pressure cylinder, and steam pressure at the outlet of the first stage of the low pressure cylinder of the low pressure heater connected to the exhaust steam of the intermediate pressure cylinder during a predetermined time under non-heating conditions.

[0071] (2) Respectively calculate the steam flow rate G passing through the last stage of the intermediate pressure cylinder corresponding to each group of data, and respectively calculate the steam flow rate G M passing through the first stage of the low pressure cylinder corresponding to each group of data. Before calculating G and G L , the respective F M and F L corresponding to these two stages need to be pre-calculated through the data in the steam turbine thermal characteristics book or the performance test data. ν

[0072] (3) Calculate the flow rate G c of the exhaust steam of the intermediate pressure cylinder going to the heater = G M - G L .

[0073] (4) Align the historical monitoring data of the heater inlet water temperature, inlet water flow, inlet steam pressure, inlet steam temperature, water level, drain temperature, outlet water temperature, and inlet steam flow, or the data obtained from the calculations in (2) and (3) above, according to the time compensation amount of each parameter. The time compensation amounts of the inlet steam flow, inlet steam pressure, inlet steam temperature, and water level are the same.

[0074] (5) Use the heater inlet water temperature, inlet water flow, inlet steam pressure, inlet steam temperature, water level, drain temperature, and outlet water temperature as input parameters, and the inlet steam flow as the output parameter. Use the time-aligned historical data as training data to train the GRU neural network model.

[0075] Before modeling, it is necessary to pre-normalize the input and output parameters. Generally, the normalization is carried out in the range of [0, 1]. The upper and lower limits of the parameters are obtained by considering a certain margin based on the upper and lower limits of the historical normal monitoring data.

[0076] (6) Adjust the model parameters of the GRU neural network to obtain the optimal prediction model. Parameter tuning can adopt optimization methods such as grid search.

[0077] In the embodiment of the present invention, the average heat exchange cycle of the above-mentioned one heater can be calculated by the following formula:

[0078]

[0079] In the formula, T is the average heat exchange cycle of one heater, with the unit of s; L vapor is the average path length of the steam side of the heater, with the unit of m; v vapor is the designed flow velocity of the steam side of the heater, with the unit of m / s; L water is the average path length of the water side of the heater, with the unit of m; v water is the designed flow velocity of the water side of the heater, with the unit of m / s.

[0080] Furthermore, when the flow path structure of the steam turbine changes due to factors such as structural transformation, the method of the present invention can adapt to the new flow path structure by correcting the reference characteristic flow area of the last stage of the intermediate pressure cylinder and the first stage of the low pressure cylinder with new performance test data, and at the same time correcting the GRU neural network prediction model of the inlet steam flow of the heater.

[0081] In summary, the soft measurement method for the extraction steam flow rate during the zero output operation of the low-pressure cylinder of a steam turbine provided by the embodiments of the present invention first calculates the steam flow rate passing through the last stage of the intermediate-pressure cylinder through the reference characteristic flow area and the real-time measured data of the DCS. Then, the exhaust steam flow rate of the intermediate-pressure cylinder is divided into three parts: the cooling steam flow rate going to the low-pressure cylinder has a direct measuring point; the steam flow rate going to the heat supply station is the parameter to be calculated; the steam flow rate going to the heater is the key to the solution. Considering the hysteresis of the heater parameters, a GRU neural network model is established based on the inlet steam flow rate of the heater obtained under the non-heating condition of the steam turbine and other monitored parameter data of the heater after time alignment. With the help of the memory characteristics of the GRU network, the accuracy of the prediction of the inlet steam flow rate of the heater is improved, thereby realizing the calculation of the extraction steam flow rate under the zero output condition of the low-pressure cylinder. When implementing this method, no additional measuring points need to be installed. Only by combining the measured data of the conventional measuring points with the formula and the GRU neural network model, the extraction steam flow rate under the steady state and variable load conditions can be obtained, and the calculation speed is fast and the data accuracy is high, which can fully meet the usage requirements in engineering practice. When the installation conditions for the extraction steam flow rate measuring device are available on site, the direct measurement result can be assisted and verified through this method; when the installation conditions for the extraction steam flow rate measuring device cannot be met on site, the calculation result of this method can be directly used as the basis for the heat supply regulation or economic calculation of the unit.

[0082] The following is the device embodiment of the present invention, which can be used to execute the method embodiment of the present invention. For the details not disclosed in the device embodiment, please refer to the method embodiment of the present invention.

[0083] In another embodiment of the present invention, a soft measurement system for the extraction steam flow rate is provided, which is used for measuring the extraction steam flow rate during the zero output operation of the low-pressure cylinder of a steam turbine, and includes:

[0084] A first flow rate acquisition module, configured to acquire the steam flow rate passing through the last stage of the intermediate-pressure cylinder, the cooling steam flow rate of the low-pressure cylinder, and the inlet steam flow rate of the low-pressure heater communicated with the exhaust steam of the intermediate-pressure cylinder during the zero output operation of the low-pressure cylinder of the steam turbine;

[0085] A second flow rate acquisition module, configured to calculate and obtain the extraction steam flow rate, and the calculation expression is G = G0 - G h -G LPC ; where G is the extraction steam flow rate, G0 is the steam flow rate passing through the last stage of the intermediate-pressure cylinder, G LPC is the cooling steam flow rate of the low-pressure cylinder, G h is the inlet steam flow rate of the low-pressure heater communicated with the exhaust steam of the intermediate-pressure cylinder; the time stamps of G, G0, G LPC and G h are consistent;

[0086] Among them, the step of obtaining the inlet steam flow rate of the low-pressure heater connected to the extraction steam of the intermediate-pressure cylinder includes: when the low-pressure cylinder of the steam turbine operates with zero output, based on the pre-obtained time compensation amount, collect the inlet water temperature, inlet water flow rate, inlet steam pressure, inlet steam temperature, drain temperature, water level and outlet water temperature of the low-pressure heater connected to the extraction steam of the intermediate-pressure cylinder; use the pre-trained heater inlet steam flow rate prediction model to obtain the inlet steam flow rate of the low-pressure heater connected to the extraction steam of the intermediate-pressure cylinder.

[0087] In another embodiment of the present invention, a computer device is provided. The computer device includes a processor and a memory. The memory is used to store a computer program. The computer program includes program instructions. The processor is used to execute the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of the soft measurement method of the extraction steam flow rate for heating.

[0088] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory). The computer-readable storage medium is a memory device in a computer device and is used to store programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and, of course, the extended storage medium supported by the computer device. The computer-readable storage medium provides a storage space, and this storage space stores the operating system of the terminal. And, one or more instructions suitable for being loaded and executed by the processor are stored in this storage space. These instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. One or more instructions stored in the computer-readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the soft measurement method of the extraction steam flow rate for heating in the above embodiments.

[0089] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0090] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of flows and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0091] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means implement the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0092] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 block or multiple blocks.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: still modifications or equivalent substitutions can be made to the specific embodiments of the present invention, and any modification or equivalent substitution that does not depart from the spirit and scope of the present invention should be covered by the protection scope of the claims of the present invention.

Claims

1. A soft measurement method for the extraction steam flow rate, which is used for measuring the extraction steam flow rate during the zero output operation of the low-pressure cylinder of a steam turbine, is characterized in that It includes the following steps: When the low-pressure cylinder of the steam turbine operates at zero output, obtain the steam flow rate passing through the last stage of the intermediate-pressure cylinder, obtain the cooling steam flow rate of the low-pressure cylinder, and obtain the inlet steam flow rate of the low-pressure heater connected to the exhaust steam of the intermediate-pressure cylinder; Calculate the extraction steam flow rate for heating. The calculation formula is: G = G0 - G h -G LPC ; where G is the extraction steam flow rate for heating, G0 is the steam flow rate passing through the last stage of the intermediate pressure cylinder, G LPC is the cooling steam flow rate of the low pressure cylinder, and G h is the inlet steam flow rate of the low pressure heater connected to the exhaust of the intermediate pressure cylinder; The timestamps of G, G0, and G LPC and G h are consistent; Among them, the step of obtaining the inlet steam flow rate of the low-pressure heater connected to the exhaust steam of the intermediate-pressure cylinder includes: when the low-pressure cylinder of the steam turbine operates at zero output, based on the pre-obtained time compensation amount, collect the inlet water temperature, inlet water flow rate, inlet steam pressure, inlet steam temperature, drain temperature, water level and outlet water temperature of the low-pressure heater connected to the exhaust steam of the intermediate-pressure cylinder; use the pre-trained heater inlet steam flow rate prediction model to obtain the inlet steam flow rate of the low-pressure heater connected to the exhaust steam of the intermediate-pressure cylinder; The step of obtaining the steam flow rate passing through the last stage of the intermediate-pressure cylinder includes: By calculating the steam flow rate passing through the last stage of the intermediate pressure cylinder; where F ν is the reference characteristic flow area of the stage, ν0 is the specific volume of the steam at the inlet of the stage, p0 is the steam pressure at the inlet of the stage, and π is the steam pressure ratio after the stage to that before the stage; The specific steps for obtaining the pre-obtained time compensation amount include: Calculate the Pearson correlation coefficients between the monitored data of the inlet water temperature, inlet water flow rate, inlet steam pressure, inlet steam temperature, and drain temperature of the low-pressure heater connected to the exhaust steam of the intermediate-pressure cylinder and the outlet water temperature at different delay times within an average heater heat exchange cycle time; take the delay time corresponding to the maximum Pearson correlation coefficient as the time compensation amount of the parameter relative to the outlet water temperature; Take the larger value of the time compensation amounts corresponding to the inlet water temperature and inlet water flow rate as the common time compensation amount for both; take the larger value of the time compensation amounts corresponding to the inlet steam pressure and inlet steam temperature as the common time compensation amount for both; the water level is consistent with the time compensation amounts of the inlet steam pressure and inlet steam temperature; Among them, the calculation expression for the average heater heat exchange cycle is, Wherein, T is the average heat exchange period of a heater, and L vapor is the average path length on the steam side of the heater, and v vapor is the designed flow velocity on the steam side of the heater, and L water is the average path length on the water side of the heater, and v water is the designed flow velocity on the water side of the heater.

2. The soft measurement method for the extraction steam flow rate of heat supply according to claim 1, wherein The step of obtaining the cooling steam flow rate of the low-pressure cylinder includes: measured by a flow meter installed in the cooling steam bypass under the zero-output condition of the low-pressure cylinder.

3. A soft measurement method for the extraction steam flow rate in heat supply, according to claim 1, characterized in that The heater inlet steam flow rate prediction model is a GRU neural network model.

4. A soft measurement method for the extraction steam flow rate of heat supply according to claim 3, characterized in that, The steps for obtaining the pre-trained heater inlet steam flow rate prediction model include: Obtain a training sample set; each training sample in the training sample set includes an input sample value and an output sample value. The input sample value includes the sample values of the inlet water temperature, inlet water flow rate, inlet steam pressure, inlet steam temperature, drain temperature, water level and outlet water temperature of the low-pressure heater connected to the exhaust steam of the intermediate-pressure cylinder, and the output sample value is the inlet steam flow rate sample value of the low-pressure heater connected to the exhaust steam of the intermediate-pressure cylinder corresponding to the input sample value; Train the GRU neural network model based on the training sample set until the preset convergence condition is reached to obtain the pre-trained heater inlet steam flow rate prediction model.

5. A soft measurement method for the heating extraction steam flow according to claim 4, characterized in that The steps for obtaining each training sample in the training sample set include: Obtain the historical monitoring data of the inlet water temperature, inlet water flow rate, inlet steam pressure, inlet steam temperature, water level, drain temperature, outlet water temperature, steam pressure at the inlet of the last stage of the intermediate-pressure cylinder, steam temperature at the inlet of the last stage of the intermediate-pressure cylinder, exhaust steam pressure of the intermediate-pressure cylinder, inlet steam pressure of the low-pressure cylinder, inlet steam temperature of the low-pressure cylinder, and steam pressure at the outlet of the first stage of the low-pressure cylinder within a predetermined time under non-heating conditions; Based on the obtained historical monitoring data, through calculate the steam flow rate G passing through the last stage of the intermediate pressure cylinder corresponding to each group of data respectively M , through calculate the steam flow rate G passing through the first stage of the low pressure cylinder corresponding to each group of data respectively L ; where F ν is the reference characteristic flow area of the stage, ν0 is the specific volume of the steam at the inlet of the stage, p0 is the steam pressure at the inlet of the stage, and π is the steam pressure ratio after the stage to before the stage; calculate the inlet steam flow rate G of the low pressure heater connected to the exhaust of the intermediate pressure cylinder corresponding to each group of data c = G M - G L ; Based on the pre-acquired time compensation amount, perform time alignment on the historical monitoring data or calculated data of the inlet water temperature, inlet water flow rate, inlet steam pressure, inlet steam temperature, water level, drain temperature, outlet water temperature, and inlet steam flow rate of the low-pressure heater connected to the extraction steam from the intermediate-pressure cylinder; among them, the time compensation amounts of the inlet steam flow rate, inlet steam pressure, inlet steam temperature, and water level are the same. Use the monitored values of the inlet water temperature, inlet water flow rate, inlet steam pressure, inlet steam temperature, water level, drain temperature, and outlet water temperature of the low-pressure heater connected to the extraction steam from the intermediate-pressure cylinder after time alignment as input sample values; use the calculated value of the inlet steam flow rate of the low-pressure heater connected to the extraction steam from the intermediate-pressure cylinder after time alignment as the output sample value; the input sample value and the corresponding output sample value form an independent training sample.

6. A soft measurement system for the heating extraction steam flow rate, which is used for measuring the heating extraction steam flow rate during the zero output operation of the low-pressure cylinder of a steam turbine, is characterized in that, It includes: A first flow rate acquisition module, configured to acquire the steam flow rate passing through the last stage of the intermediate-pressure cylinder when the low-pressure cylinder of the steam turbine operates at zero output. Acquire the cooling steam flow rate of the low-pressure cylinder. Acquire the inlet steam flow rate of the low-pressure heater connected to the extraction steam from the intermediate-pressure cylinder. The second flow acquisition module is used to calculate and obtain the extraction steam flow for heating. The calculation expression is G = G0 - G h - G LPC ; where G is the extraction steam flow for heating, G0 is the steam flow passing through the last stage of the intermediate pressure cylinder, G LPC is the cooling steam flow of the low pressure cylinder, and G h is the inlet steam flow of the low pressure heater connected to the exhaust of the intermediate pressure cylinder; The timestamps of G, G0, G LPC and G h are consistent; Among them, the step of acquiring the inlet steam flow rate of the low-pressure heater connected to the extraction steam from the intermediate-pressure cylinder includes: when the low-pressure cylinder of the steam turbine operates at zero output, based on the pre-acquired time compensation amount, collect the inlet water temperature, inlet water flow rate, inlet steam pressure, inlet steam temperature, drain temperature, water level, and outlet water temperature of the low-pressure heater connected to the extraction steam from the intermediate-pressure cylinder; use the pre-trained inlet steam flow rate prediction model of the heater to obtain the inlet steam flow rate of the low-pressure heater connected to the extraction steam from the intermediate-pressure cylinder. The step of acquiring the steam flow rate passing through the last stage of the intermediate-pressure cylinder includes: By calculating, the steam flow rate passing through the last stage of the intermediate pressure cylinder is obtained; where F ν is the reference characteristic flow area of the stage, ν0 is the specific volume of the steam at the inlet of the stage, p0 is the steam pressure at the inlet of the stage, and π is the ratio of the steam pressure after the stage to the steam pressure before the stage; The specific step of acquiring the pre-acquired time compensation amount includes: Calculate the Pearson correlation coefficients between the monitored data of the inlet water temperature, inlet water flow rate, inlet steam pressure, inlet steam temperature, and drain temperature of the low-pressure heater connected to the extraction steam from the intermediate-pressure cylinder and the outlet water temperature at different delay times within an average heat exchange cycle time of the heater; use the delay time corresponding to the maximum Pearson correlation coefficient as the time compensation amount of the parameter relative to the outlet water temperature. Use the larger value among the time compensation amounts corresponding to the inlet water temperature and inlet water flow rate as their common time compensation amount; use the larger value among the time compensation amounts corresponding to the inlet steam pressure and inlet steam temperature as their common time compensation amount; the water level is consistent with the time compensation amounts of the inlet steam pressure and inlet steam temperature. Among them, the calculation expression of the average heat exchange cycle of one heater is, Wherein, T is the average heat exchange period of a heater, L vapor is the average path length of the steam side of the heater, v vapor is the designed flow velocity of the steam side of the heater, L water is the average path length of the water side of the heater, v water is the designed flow velocity of the water side of the heater.

7. An electronic device, characterized in that, It includes: At least one processor; And, A memory communicatively connected to the at least one processor; among them, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the heating extraction steam flow rate soft measurement method according to any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the heating extraction steam flow rate soft measurement method according to any one of claims 1 to 5.

Images