Low-pressure cylinder steam inlet flow online soft measurement method based on multivariable fusion

Abstract

The invention provides a multivariable fusion-based low-pressure cylinder admission flow online soft measurement method, belongs to the technical field of steam turbine operation control, and can at least partially solve the problems of insufficient measurement precision in a small flow area, poor stability under system disturbance and limited adaptability of a single model in the prior art. The method comprises the steps that the steam inlet pressure, temperature, steam exhaust pressure and blast temperature of a low-pressure cylinder and relevant parameters of a regenerative system are collected; respectively calculating a physical estimation amount, a calibration correction amount and a heat regeneration balance amount; the weight coefficient is adaptively set according to the operation working condition, the three types of information sources are fused, and the real-time measurement value of the steam inlet flow of the low-pressure cylinder is obtained.The method has the beneficial effects that the accuracy and stability of the measurement result can be kept under the multiple working conditions of large flow, small flow, system disturbance and the like, and good real-time performance and engineering adaptability are achieved. The method can be widely applied to scenes of steam turbine operation monitoring, performance analysis and protection strategy optimization.

Description

Technical Field

[0001] This invention belongs to the field of steam turbine operation control technology, specifically relating to an online soft measurement method for low-pressure cylinder inlet steam flow based on multivariate fusion. Background Technology

[0002] During the operation of large steam turbines, the low-pressure cylinder inlet steam flow rate is one of the important parameters reflecting the turbine's thermodynamic state, assessing operating efficiency, and triggering protection strategies. This parameter not only affects the overall thermodynamic balance of the turbine but also directly relates to the extraction steam distribution of the regenerator system, the safe operation of the last-stage blades, and the response accuracy of load regulation. Therefore, accurately obtaining the low-pressure cylinder inlet steam flow rate has significant engineering implications.

[0003] Due to limitations in the layout of the low-pressure cylinder inlet pipeline, it is usually impossible to directly measure the steam flow rate at the low-pressure cylinder inlet. Existing technologies typically employ physical estimation methods based on thermodynamic formulas. These methods usually utilize the Flueger formula or other empirical formulas, combined with pressure and temperature measurement points on the low-pressure cylinder inlet side, to obtain steam property data and calculate the estimated flow rate. This method has high reliability near the design operating conditions, but in low-flow-rate regions or under operating conditions deviating from the design point, the calculation results are prone to significant deviations, or even become unusable, due to limitations in the accuracy of the measurement points, errors in extrapolating physical properties, and flow field disturbances.

[0004] In summary, existing technologies for measuring low-pressure cylinder inlet steam flow have certain limitations, making it difficult to simultaneously meet the requirements of accuracy, stability, and real-time performance under complex operating conditions such as wide-range peak shaving, low-load operation, and disturbances in the regenerative system. Therefore, there is an urgent need for an online soft measurement method for low-pressure cylinder inlet steam flow that integrates multi-source information, possesses adaptive capabilities, and can operate stably across the entire operating range, in order to improve the safety, economy, and automation level of turbine operation. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art, and provides an online soft measurement method for low-pressure cylinder inlet steam flow based on multivariate fusion.

[0006] This invention provides a method for online soft measurement of low-pressure cylinder inlet steam flow based on multivariate fusion, comprising: Acquire online measurement data, design parameters, and test parameters of the steam turbine operation and thermal system; Physical estimation of low-pressure cylinder inlet steam flow rate based on the Flueger formula ; By calibrating the blower temperature of the low-pressure cylinder's secondary and final stages, a function relating blower temperature to inlet steam flow rate is established. Exhaust pressure correction is then introduced to obtain the calibration correction amount. ; Based on the measuring points of the low-pressure regenerative system, the regenerative balance quantity is calculated according to the energy conservation and mass conservation equations. ; The weighting coefficient is dynamically determined based on the turbine operating conditions. , , The soft measurement value of the inlet steam flow rate is obtained by fusion. , ,in, ; The soft measurement values ​​are output online to the operation control screen and used as operation monitoring and protection criteria.

[0007] Preferably, the relationship for the blower temperature calibration satisfies: ; in, To calibrate the correction amount, The temperature of the last stage blower in the low-pressure cylinder. This refers to the exhaust pressure of the steam turbine. For the blower temperature calibration function, This is a correction function for the specific volume of steam based on the principle of equal volumetric flow rate.

[0008] Preferably, the step of calibrating the blower temperature includes: A blower temperature calibration test system was constructed. The system is equipped with a fully sealable heating butterfly valve and a bypass steam system. Steam pressure, temperature and flow measurement devices are installed in the bypass steam pipeline system. A blower temperature monitoring system is installed in the secondary and final stages and the tip area of ​​the final stage blades of the low-pressure cylinder of the steam turbine. During turbine start-up, shutdown, or low-load stable operation, the heating butterfly valve of the connecting pipe is fully closed, and the exhaust steam from the intermediate-pressure cylinder enters the low-pressure cylinder through the bypass steam system. After the turbine operation stabilizes, the test data of the inlet steam flow, blower temperature, and exhaust steam pressure are recorded. Based on the fitting of the experimental data, the following was obtained. The correction function is determined based on the design thermodynamic characteristic curve of the steam turbine and the physical property data in the standard steam table. .

[0009] Preferably, the regenerative balance amount The calculations are based on the measurement points of the inlet and outlet temperatures of each heater in the low-pressure regenerative system, the steam pressure at the extraction port, and the condensate flow rate, and the parameters are corrected in combination with the turbine performance test results.

[0010] Preferably, the dynamic tuning of the weighting coefficients is adaptively adjusted based on the turbine operating conditions: When the low-pressure cylinder inlet steam flow rate is close to the design rated flow rate and the operating parameters are close to the design thermodynamic characteristic point, The value is greater than and ; When the steam flow rate at the low-pressure cylinder is at a low flow rate deviating from the design point during operation... The value is greater than and ; When the operating status of the regenerative system is disturbed, causing deviations in the mass flow rate at the measuring points, The value is greater than and .

[0011] Optionally, the online measuring points include at least: Power generation capacity, main steam flow rate, regulating stage pressure, low-pressure cylinder inlet steam pressure and temperature, low-pressure cylinder exhaust steam pressure, low-pressure cylinder secondary and final stage blower temperature, low-pressure regenerator condensate inlet and outlet temperatures, and low-pressure extraction steam pressure.

[0012] Optionally, the weight tuning simultaneously references turbine design parameters, historical operating data, and performance test results, and sets weight smoothing and boundary constraints to ensure... ,and The sum of is 1.

[0013] Optionally, the method employs robust processing and data cleaning for outlier measurement points, including: median filtering, sliding window averaging, amplitude limiting, and missing measurement filling, and... and Set alarms and demotion strategies for extrapolation ranges.

[0014] An online soft measurement device for low-pressure cylinder inlet steam flow includes: The data acquisition module is used to collect online measurement data including power generation, main steam flow, regulating stage pressure, low-pressure cylinder inlet steam pressure and temperature, low-pressure cylinder exhaust steam pressure, low-pressure cylinder secondary and final stage blower temperature, low-pressure regenerator condensate inlet and outlet temperatures, and low-pressure extraction steam pressure. The physical estimation module is used to calculate the physical estimate of the low-pressure cylinder inlet steam flow rate. ; The calibration estimation module is used to manage the blower temperature calibration process and calculate the calibration correction amount. ; The regenerative balance module is used for energy and mass balance calculations. ; The weighting module is used to dynamically adjust the weighting coefficients based on the turbine's operating conditions. ; The fusion output module is used to calculate and output the soft measurement value of the inlet steam flow. .

[0015] Preferably, the calibration estimation module includes: Blower temperature sensor interface unit, bypass steam system parameter acquisition unit, calibration function fitting and version management unit, exhaust pressure correction unit; The weight tuning module includes: The system includes a working condition identification unit, a weight calculation unit based on rules and data statistics, a weight smoothing and boundary constraint unit, and an anomaly rollback strategy unit.

[0016] The beneficial effects of this invention are as follows: By integrating three information sources—physical estimation, calibration correction, and regenerative balance—and combining them with weighted adaptive tuning, high-precision online soft measurement of the low-pressure cylinder inlet steam flow rate is achieved across the entire operating range. When the flow rate is close to the design condition, physical estimation is prioritized; when the flow rate deviates from the design condition, calibration correction is prioritized; and when there is disturbance in the regenerative system or abnormalities at the measuring point, regenerative balance is prioritized, thus balancing measurement accuracy, stability, and adaptability.

[0017] The fusion results can be published to the control system screen in real time and directly used as operating monitoring and protection criteria, which helps to improve the safety, economy and automation level of steam turbine operation. Through multi-source fusion and data governance, the impact of measurement point fluctuations and anomalies on the results is effectively suppressed, making the measurement process more robust and engineering adaptable. Attached Figure Description

[0018] Figure 1 A schematic diagram of the online soft measurement method for low-pressure cylinder inlet steam flow based on multivariate fusion provided in this application. Detailed Implementation

[0019] To enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0020] like Figure 1 As shown in the figure, the online soft measurement method for low-pressure cylinder inlet steam flow based on multivariate fusion provided by the specific embodiments of the present invention includes: Acquire online measurement data, design parameters, and test parameters of the steam turbine operation and thermal system; Physical estimation of low-pressure cylinder inlet steam flow rate based on the Flueger formula ; By calibrating the blower temperature of the low-pressure cylinder's secondary and final stages, a function relating blower temperature to inlet steam flow rate is established. Exhaust pressure correction is then introduced to obtain the calibration correction amount. ; Based on the measuring points of the low-pressure regenerative system, the regenerative balance quantity is calculated according to the energy conservation and mass conservation equations. ; The weighting coefficient is dynamically determined based on the turbine operating conditions. , , The soft measurement value of the inlet steam flow rate is obtained by fusion. , ,in, ; The soft measurement values ​​are output online to the operation control screen and used for operation monitoring and protection criteria.

[0021] Example 1: Detailed Process of Online Soft Measurement Method Figure 1 A schematic diagram of the online soft measurement method provided in this application is shown below. Figure 1 As shown, the method of the present invention is applicable to online soft measurement of the low-pressure cylinder inlet steam flow rate of a steam turbine across the entire operating range, and includes the following steps: S1: Data Acquisition Operating parameters, including low-pressure cylinder inlet pressure, low-pressure cylinder inlet temperature, low-pressure cylinder exhaust pressure, low-pressure cylinder secondary and final stage blower temperature, condensate inlet temperature, condensate outlet temperature, condensate flow rate, and steam pressure and temperature at each extraction port, are obtained from the turbine's distributed control system. All data are synchronized and quality checked, with obvious outliers removed and missing values ​​filled.

[0022] S2: Physical estimation quantity Calculation Based on the Flueger formula, and combined with the measured pressure and temperature on the low-pressure cylinder inlet side, standard steam property data were obtained to calculate the physical estimate of the low-pressure cylinder inlet steam flow rate. This calculation process ensures physical consistency even when deviating from the design operating conditions.

[0023] S3: Calibration correction amount Calculation A calibration function relating the low-pressure cylinder secondary and final stage blower temperature to the inlet steam flow rate was established through offline calibration experiments. During online operation, combined with actual measured exhaust pressure... Introducing an exhaust pressure correction function The corrected calculated value is obtained. Correction function Constructed based on the principle of equal volumetric flow rate, it is used to compensate for the impact of back pressure changes on flow rate estimation.

[0024] S4: Heat recovery balance quantity Calculation Based on the operating parameters of each stage heater in the low-pressure regenerative system, and combining the energy conservation equation and the mass conservation equation, the extraction steam flow rate of each stage is calculated. The results are then substituted back to the steam inlet side of the low-pressure cylinder to obtain the regenerative balance quantity. The energy conservation equation is based on the equality of the condensate temperature rise in the heater and the heat release of the steam, while the mass conservation equation is based on the water balance of the system. Performance test data is incorporated into the calculations to correct for heat loss, leakage, and non-metered branches.

[0025] S5: Weighted Fusion Calculation Based on the current operating condition identification results of the steam turbine, the adaptive tuning weight coefficients are determined. , , ,in The fusion formula is . When the flow rate is close to the design condition, improve The weights; When the flow rate deviates from the design conditions at a small rate, improve The weights; When the regenerative system is disturbed or the measuring point is abnormal, improve The weight.

[0026] The weight adjustment process uses a smoothing algorithm to avoid output fluctuations.

[0027] S6: Online Publishing and Application fusion results as well as , , The weighting coefficients are displayed in real time on the control system screen and serve as inputs for operation monitoring, performance analysis, and protection criteria. When the fusion result is lower than the safety lower limit envelope, a graded alarm and protection action are triggered.

[0028] Example 2: Calibration Test Method To obtain high-precision calibration relationships in the low-flow-rate region, calibration tests must be conducted when the turbine meets the required conditions. The test steps are as follows.

[0029] The first step is to change the low-pressure cylinder inlet steam flow rate under controllable conditions, and after ensuring stable operation, record the low-pressure cylinder inlet steam reference flow rate, secondary and final stage blower temperature, and exhaust steam pressure. The second step involves collecting data from multiple different flow conditions and establishing a calibration function for the relationship between blower temperature and steam flow rate using robust regression or piecewise fitting methods. . The third step involves deriving the exhaust pressure correction function based on the similarity condition of the final stage channel volumetric flow rate and combined with steam property data. . The fourth step is to store the calibration function and the correction function in the version management unit, record the applicable scope and residual statistics, and ensure that they are traceable and updatable during online operation.

[0030] Example 3: Calculation details of regenerative equilibrium quantity In the low-pressure regenerative system, the condensate inlet temperature, condensate outlet temperature, condensate flow rate, steam pressure at the extraction port, and steam temperature are measured for each stage of the heater. According to the principle of energy conservation, the steam extraction flow rate of each stage heater is calculated as follows: Condensate flow rate multiplied by specific heat capacity and temperature rise equals steam extraction flow rate multiplied by the enthalpy difference between steam and condensate outlets minus heat loss. Substituting the steam extraction flow rates at each stage into the mass conservation equation, the steam inlet flow rate of the low-pressure cylinder, i.e., the regenerative balance quantity, is obtained. During the calculation process, performance test data is used to correct for the effects of heat loss, leakage, and bypass branches, in order to improve the accuracy of the results.

[0031] Example 4: Weight Adaptive Strategy The weighting coefficients are adjusted based on the results of the working condition identification. When the turbine load is close to the design value and the thermodynamic characteristic deviation is small The weight is the largest; When the steam turbine is operating at low flow rate and deviates significantly from its design characteristics The weight is the largest; When there is disturbance in the regenerative system or abnormality at the measuring point The one with the highest weight. The weight adjustment uses a smoothing algorithm to avoid output instability caused by instantaneous fluctuations.

[0032] Example 5: Functional Module Composition of a Soft Measurement System The method of this invention can be implemented through software modularization, including a data acquisition module, a physical estimation module, a calibration estimation module, a regenerative balance module, a weighted fusion module, and a result publishing module.

[0033] The modules are connected via a data bus to enable real-time calculation and display.

[0034] The data acquisition module is responsible for collecting and synchronizing data from all measurement points, while the physical estimation module and calibration estimation module calculate the data respectively. and Heat recovery balance module calculation The weight fusion module calculates the final traffic value based on the operating condition identification results. The results publishing module outputs the results to the control system screen and triggers the corresponding alarm or protection logic.

[0035] In summary, the embodiments disclosed herein have at least the following technical effects: Strong adaptability to all operating conditions: When the flow rate is close to the design condition, this invention prioritizes the use of physical estimation quantities based on the Flugel formula to ensure calculation accuracy near the design point; when the flow rate deviates from the design condition, it prioritizes the use of calibration correction quantities based on blower temperature calibration and introducing exhaust pressure correction to improve sensitivity under low load and wide peak shaving conditions; when the regenerative system is disturbed or the measuring point is abnormal, it prioritizes the use of regenerative balance quantities calculated based on the energy conservation and mass conservation equations to ensure stability under complex operating conditions, thereby achieving reliable measurement across the entire operating range.

[0036] Significantly improved measurement accuracy and robustness: By fusing multi-source information, the problem of accuracy degradation under specific operating conditions caused by a single measuring point or a single model is avoided. The adaptive weighting mechanism can dynamically adjust the contribution ratio of each information source according to real-time operating conditions. Combined with data smoothing and outlier management strategies, it effectively suppresses the impact of measuring point fluctuations, sensor drift, and instantaneous disturbances on the measurement results, enabling the fusion results to maintain high accuracy and high stability in long-term operation.

[0037] High feasibility and engineering adaptability: The method of this invention can be implemented based on existing measuring points of the steam turbine and feasible calibration tests, without the need for a large amount of new hardware equipment, resulting in low modification costs and short deployment cycles. Calibration and correction functions are managed using version control and their applicable scope is recorded, facilitating rapid adaptation and updates for different steam turbines and different operating stages, meeting the flexible application needs of engineering sites.

[0038] Excellent real-time performance and integrability: The calculation process of the method of this invention can run in real time in the distributed control system and monitoring system of steam turbines, and the fusion results can be directly used for operation monitoring, performance analysis and protection criteria. The output results and weighting coefficients can be displayed in real time on the control screen, which makes it easy for operators to intuitively grasp the status of the steam turbine, and can be seamlessly integrated with existing protection logic.

[0039] Enhanced Safety and Economy: By enabling high-precision real-time monitoring of the steam flow rate into the low-pressure cylinder, this invention can promptly trigger alarms or protective actions when the flow rate is abnormal or approaching safety boundaries, reducing the risk of equipment damage and unplanned shutdowns. Simultaneously, accurate flow measurement helps optimize turbine operation, improve thermal efficiency, reduce energy consumption, and enhance economic benefits.

[0040] It is understood that the above embodiments are merely exemplary implementations used to illustrate the principles of the present invention, and the present invention is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also considered to be within the scope of protection of the present invention.

Claims

1. A method for online soft measurement of low-pressure cylinder inlet steam flow based on multivariate fusion, characterized in that, include: Acquire online measurement data, design parameters, and test parameters of the steam turbine operation and thermal system; Physical estimation of low-pressure cylinder inlet steam flow rate based on the Flueger formula ; By calibrating the blower temperature of the low-pressure cylinder's secondary and final stages, a function relating blower temperature to inlet steam flow rate is established. Exhaust pressure correction is then introduced to obtain the calibration correction amount. ; Based on the measuring points of the low-pressure regenerative system, the regenerative balance quantity is calculated according to the energy conservation and mass conservation equations. ; The weighting coefficient is dynamically determined based on the turbine operating conditions. , , The soft measurement value of the inlet steam flow rate is obtained by fusion. , ,in, ; The soft measurement values ​​are output online to the operation control screen and used as operation monitoring and protection criteria.

2. The online soft measurement method for low-pressure cylinder inlet steam flow based on multivariate fusion according to claim 1, characterized in that, The relationship for the blower temperature calibration satisfies: ; in, To calibrate the correction amount, The temperature of the last stage blower in the low-pressure cylinder. This refers to the exhaust pressure of the steam turbine. For the blower temperature calibration function, This is a correction function for the specific volume of steam based on the principle of equal volumetric flow rate.

3. The online soft measurement method for low-pressure cylinder inlet steam flow based on multivariate fusion according to claim 1, characterized in that, The steps for calibrating the blower temperature include: A blower temperature calibration test system was constructed. The system is equipped with a fully sealable heating butterfly valve and a bypass steam system. Steam pressure, temperature and flow measurement devices are installed in the bypass steam pipeline system. A blower temperature monitoring system is installed in the secondary and final stages and the tip area of ​​the final stage blades of the low-pressure cylinder of the steam turbine. During turbine start-up, shutdown, or low-load stable operation, the heating butterfly valve of the connecting pipe is fully closed, and the exhaust steam from the intermediate-pressure cylinder enters the low-pressure cylinder through the bypass steam system. After the turbine operation stabilizes, the test data of the inlet steam flow, blower temperature, and exhaust steam pressure are recorded. Based on the fitting of the experimental data, the following was obtained. The correction function is determined based on the design thermodynamic characteristic curve of the steam turbine and the physical property data in the standard steam table. .

4. The online soft measurement method for low-pressure cylinder inlet steam flow based on multivariate fusion according to claim 1, characterized in that, The heat recovery balance amount The calculations are based on the measurement points of the inlet and outlet temperatures of each heater in the low-pressure regenerative system, the steam pressure at the extraction port, and the condensate flow rate, and the parameters are corrected in combination with the turbine performance test results.

5. The online soft measurement method for low-pressure cylinder inlet steam flow based on multivariate fusion according to claim 1, characterized in that, The dynamic tuning of the weighting coefficients is adaptively adjusted based on the turbine operating conditions: When the low-pressure cylinder inlet steam flow rate is close to the design rated flow rate and the operating parameters are close to the design thermodynamic characteristic point, The value is greater than and ; When the steam flow rate at the low-pressure cylinder inlet is at a low flow rate deviating from the design point during operation... The value is greater than and ; When the operating status of the regenerative system is disturbed, causing deviations in the mass flow rate at the measuring points, The value is greater than and .

6. The method according to any one of claims 1 to 5, characterized in that, The online measurement points include at least: Power generation capacity, main steam flow rate, regulating stage pressure, low-pressure cylinder inlet steam pressure and temperature, low-pressure cylinder exhaust steam pressure, low-pressure cylinder secondary and final stage blower temperature, low-pressure regenerator condensate inlet and outlet temperatures, and low-pressure extraction steam pressure.

7. The method according to any one of claims 1 to 5, characterized in that, The weight tuning takes into account turbine design parameters, historical operating data, and performance test results, and sets weight smoothing and boundary constraints to ensure... ,and The sum of is 1.

8. The method according to any one of claims 1 to 5, characterized in that, The method employs robust processing and data cleaning for outlier measurement points. This robust processing and data cleaning includes: median filtering, sliding window averaging, amplitude limiting, and missing measurement filling. and Set alarms and demotion strategies for extrapolation ranges.

9. A soft online measurement device for low-pressure cylinder inlet steam flow, characterized in that, include: The data acquisition module is used to collect online measurement data including power generation, main steam flow, regulating stage pressure, low-pressure cylinder inlet steam pressure and temperature, low-pressure cylinder exhaust steam pressure, low-pressure cylinder secondary and final stage blower temperature, low-pressure regenerator condensate inlet and outlet temperatures, and low-pressure extraction steam pressure. The physical estimation module is used to calculate the physical estimate of the low-pressure cylinder inlet steam flow rate. ; The calibration estimation module is used to manage the blower temperature calibration process and calculate the calibration correction amount. ; The regenerative balance module is used for energy and mass balance calculations. ; The weighting module is used to dynamically adjust the weighting coefficients based on the turbine's operating conditions. ; as well as The fusion output module is used to calculate and output the soft measurement value of the inlet steam flow. .

10. The online soft measurement device for low-pressure cylinder inlet steam flow according to claim 9, characterized in that, The calibration estimation module includes: Blower temperature sensor interface unit, bypass steam system parameter acquisition unit, calibration function fitting and version management unit, exhaust pressure correction unit; The weight tuning module includes: The system includes a working condition identification unit, a weight calculation unit based on rules and data statistics, a weight smoothing and boundary constraint unit, and an anomaly rollback strategy unit.

Images