A method for evaluating the health state of a thermal power unit

Abstract

The present application relates to the technical field of thermal power unit state evaluation, and particularly relates to a thermal power unit operation health state evaluation method.The present application takes unit load, coal calorific value entering the furnace and environmental temperature as independent variables, and adaptively adjusts the width of a sliding window according to the change rate of the unit load, effectively distinguishes the working condition fluctuation and the real deterioration of equipment, improves the accuracy of the evaluation result, and provides a guidance basis for the operation personnel;The present application divides abnormal equipment and non-abnormal equipment according to the efficiency attenuation value and the exogenous enthalpy value deviation, and matches the corresponding evaluation period, realizes the differentiated configuration of evaluation resources, and reduces the consumption of computing resources while ensuring the monitoring strength of abnormal equipment.

Description

Technical Field

[0001] This invention relates to the field of thermal power unit condition assessment technology, specifically to a method for assessing the operational health status of thermal power units. Background Technology

[0002] Thermal power units are transitioning from base load operation to deep peak shaving operation. Under deep peak shaving conditions, the unit operating parameters deviate significantly from the design values, and the equipment failure rate increases. In order to reduce the safety risks and economic losses caused by unplanned outages, it is necessary to conduct real-time health status assessments of thermal power units to ensure the safe and stable operation of the power grid, extend the service life of equipment, and improve the economic efficiency of unit operation.

[0003] Existing technologies mainly employ methods such as over-limit alarms based on fixed thresholds and static modeling based on historical data. These existing technologies have the following shortcomings: First, fixed thresholds cannot adapt to large load fluctuations under deep peak shaving conditions, which can easily lead to missed or false judgments. Second, static models cannot keep up with the gradual deterioration of equipment performance, resulting in a systematic deviation between the evaluation benchmark and the actual state of the equipment, leading to insufficient evaluation accuracy and making it difficult to take effective maintenance measures based on the evaluation results.

[0004] Second, the performance evaluations of the turbine flow path, regenerator, and boiler heating surfaces are conducted independently, lacking a unified evaluation framework and making it difficult to achieve a comprehensive health assessment at the system level. Furthermore, once the evaluation strategy is determined, it remains fixed, failing to consider the differences in health risks among different pieces of equipment and unable to dynamically adjust as the equipment's condition evolves. This results in inefficient allocation and utilization of evaluation resources. Summary of the Invention

[0005] The technical solution adopted by the present invention to solve its technical problem is: a method for assessing the operating health status of thermal power units, including the following steps: based on the unit load, the calorific value of the coal fed into the furnace and the ambient temperature, a reference baseline is constructed within a sliding window for the turbine's flow area, the heater terminal temperature difference and the boiler flue gas temperature, and a residual sequence is obtained by combining real-time data.

[0006] Based on the temperature, pressure, and flow rate of the working fluid at the inlet and outlet of each device, the difference between the input enthalpy and the output enthalpy is calculated; the enthalpy deviation is obtained by correcting the difference through the residual sequence.

[0007] The net enthalpy deviation is obtained by subtracting the component transmitted from upstream to downstream from the enthalpy deviation along the direction of disturbance transmission determined by the flow direction of the working fluid.

[0008] Based on the pressure of the imported working medium and the flow rates of the imported and exported working mediums, the net enthalpy deviation is divided into exogenous enthalpy deviation and endogenous enthalpy deviation.

[0009] The efficiency degradation value of each device is determined based on the cumulative amount of endogenous enthalpy deviation; the abnormal devices and evaluation cycle are determined based on the amplitude and rate of change of exogenous enthalpy deviation.

[0010] Based on the assessment cycle, the fault modes of each device and abnormal devices are diagnosed, and the efficiency decay value is combined to generate a single device health score, which is then summarized level by level to generate a whole machine assessment report including the device maintenance level.

[0011] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0012] 1. This invention uses unit load, calorific value of coal fed into the furnace, and ambient temperature as independent variables, and adaptively adjusts the sliding window width according to the rate of change of unit load. This solves the problems of missed or misjudged judgments due to large load fluctuations under deep peak shaving conditions when using fixed thresholds, and the systematic deviation between the evaluation benchmark and the actual state of the equipment caused by the inability of static models to follow the gradual deterioration of equipment performance. It achieves effective differentiation between operating condition fluctuations and actual equipment deterioration, improves the accuracy of evaluation results, and provides guidance for operators.

[0013] 2. Based on the unit load, the calorific value of the coal fed into the furnace, and the ambient temperature, this invention constructs a reference baseline for the turbine flow area, heater terminal temperature difference, and boiler flue gas temperature within a sliding window. By distinguishing between exogenous enthalpy deviation and endogenous enthalpy deviation, it solves the problem of the performance evaluation of the three types of equipment being carried out independently and lacking a unified evaluation framework, and realizes a comprehensive health status evaluation at the whole unit level.

[0014] 3. This invention classifies abnormal and non-abnormal devices based on efficiency decay value and exogenous enthalpy deviation, and matches corresponding evaluation cycles. This solves the problems of fixed evaluation strategies, failure to consider differences in health risks among different devices, inability to dynamically adjust with the evolution of device status, and inefficient allocation and utilization of evaluation resources. It achieves differentiated allocation of evaluation resources, reducing computational resource consumption while ensuring the monitoring of abnormal devices. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of the method flow of the present invention;

[0017] Figure 2 This is a schematic diagram of the process for obtaining the residual sequence in this invention;

[0018] Figure 3 This is a schematic diagram of the process for obtaining the enthalpy deviation in this invention;

[0019] Figure 4 This is a schematic diagram illustrating the process for identifying faulty devices in this invention. Detailed Implementation

[0020] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the invention. Furthermore, it should be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not drawn to actual scale.

[0021] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit the invention or its application or use. Techniques, methods, and apparatus known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and apparatus should be considered part of the specification.

[0022] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0024] The specific scheme of the method for assessing the operational health status of thermal power units provided by the present invention will be described in detail below with reference to the accompanying drawings.

[0025] Please see Figure 1 and Figure 2 As shown, the present invention provides a method for assessing the operational health status of thermal power units, including: step S1, based on the unit load, the calorific value of the coal fed into the furnace and the ambient temperature, constructing a reference baseline for the turbine's flow area, the heater terminal temperature difference and the boiler flue gas temperature within a sliding window, and obtaining a residual sequence by combining real-time data.

[0026] Thermal power unit operation is characterized by frequent fluctuations in deep peak shaving, dynamic changes in coal quality, and seasonal differences in ambient temperature. To distinguish between operating condition fluctuations and actual equipment degradation, and to avoid false alarms and missed alarms, this step selects the turbine's flow area, heater terminal temperature difference, and boiler flue gas temperature as dependent variables, corresponding to the three stages of heat energy flow, heat energy recovery, and heat energy release during thermal power unit operation, respectively. Simultaneously, unit load, calorific value of the incoming coal, and ambient temperature are introduced as independent variables to establish a unified multivariate dynamic benchmark. This allows for comparison of the three types of equipment under the same evaluation system, providing a data foundation for subsequent evaluations.

[0027] In this embodiment, the unit load is read from the power transmitter; the calorific value of the coal fed into the furnace is measured in real time by an online coal quality analyzer on the coal conveyor belt; and the ambient temperature is measured by a temperature sensor located outside the turbine hall or boiler room.

[0028] To balance fitting accuracy and noise resistance, 10 sampling times are taken backward from the current sampling time to form the fitting period. The unit load within the fitting period is linearly fitted, and the slope obtained from the fitting is used as the real-time rate of change. The above linear fitting process is existing technology and will not be described in detail here.

[0029] Next, historical data of the thermal power unit during its healthy operation period are obtained from the historical database of the distributed control system of the thermal power unit; the historical change rate is obtained using the same calculation method as the real-time change rate mentioned above; the historical change rates are arranged in ascending order to construct a historical change sequence; the 20th percentile of the historical change sequence is taken as the lower limit of the change rate reference interval, and the 80th percentile of the historical change sequence is taken as the upper limit of the change rate reference interval.

[0030] The healthy operating period is selected from historical data within 30 days after the last major overhaul with the smallest time difference from the current sampling time; the major overhaul is defined as a Class A overhaul as specified in the equipment maintenance guidelines for coal-fired power plants, after which the thermal power unit has completed break-in, commissioning, and is operating stably; the 30-day data volume is sufficient to cover the main load conditions of the thermal power unit and is statistically representative. When the thermal power unit has not undergone a major overhaul or less than 30 days have passed since the overhaul, referring to the industry default benchmark, the lower limit of the rate of change reference interval is taken as one percent of the rated load, and the upper limit of the rate of change reference interval is taken as three percent of the rated load; the rated load is taken as the rated power recorded on the thermal power unit's nameplate.

[0031] When the real-time rate of change is less than the lower limit of the rate of change reference interval, it indicates that the unit is in a stable operating state. At this time, the sliding window width is set to twice the reference width to enhance statistical stability and suppress measurement noise.

[0032] When the real-time rate of change is greater than the upper limit of the reference range, it indicates that the unit is in a variable load state. At this time, the sliding window width is set to half of the reference width to improve the response speed to changes in operating conditions.

[0033] When the real-time rate of change is greater than or equal to the lower limit of the rate of change reference interval and less than or equal to the upper limit of the rate of change reference interval, the width of the sliding window is taken as the reference width.

[0034] The reference width is determined by the unit's rotor time constant and reheater time constant. Specifically, the rotor time constant reflects the magnitude of the turbine rotor's mechanical inertia, and the reheater time constant reflects the magnitude of the steam volume inertia within the reheater. Together, they determine the unit's response time to external disturbances. The specific determination method is as follows: calculate the sum of the rotor time constant and the reheater time constant, multiply the result by a safety factor, and obtain the reference width. For example, the safety factor is taken as 1.2. The rotor time constant and the reheater time constant are determined through on-site step tests, and the test process is based on existing technology.

[0035] After determining the width of the sliding window, the corresponding width of the sliding window is truncated forward from the current sampling time, and historical data points within the sliding window are extracted to form a data subset for weighted regression fitting.

[0036] In the weighted regression fitting, unit load, calorific value of coal fed into the furnace, and ambient temperature were used as independent variables, while turbine flow area, heater terminal temperature difference, and boiler exhaust temperature were used as dependent variables to independently establish a reference baseline. Specifically, for each stage of the turbine, the flow area was used as the dependent variable; for the regenerating heater, the heater terminal temperature difference was used as the dependent variable; and for the boiler heating surface, the boiler exhaust temperature was used as the dependent variable.

[0037] The calculation process for the flow area of ​​a steam turbine is as follows: Based on the thermal design data provided by the turbine manufacturer, the division of the turbine into stages is determined. A stage refers to a steam work unit consisting of a set of stationary blades and a set of moving blades. All stages between two adjacent regenerative extraction ports are grouped into one stage group. Within the same stage group, the steam flow rate of each stage is approximately equal, and the flow area remains constant. The steam inlet of the corresponding stage group is designated as the stage group inlet, and the steam outlet of the corresponding stage group is designated as the stage group outlet. The location of the regenerative extraction port is determined by the turbine manufacturer during the thermal design phase and recorded in the thermal design data provided by the manufacturer. The thermal design data includes thermal calculation sheets, design specifications, and thermal system diagrams.

[0038] For each stage of the steam turbine, the corresponding flow area is determined based on a modified form of the Freuger formula, and the calculation formula is as follows:

[0039] ;

[0040] Where A is the flow area, in square meters; The absolute temperature of the inlet steam of each stage group is measured in K and is measured by temperature sensors installed on the steam pipes at the inlet of each stage group. The absolute pressure of the steam at the stage outlet is measured in MPa by a pressure sensor installed on the extraction steam pipeline at the outlet of each stage. The absolute pressure of the steam at the inlet of each stage, expressed in MPa, is measured by pressure sensors installed on the cylinder walls at the inlet of each stage. A change in the flow area indicates a change in the geometric parameters of the flow path within the stage, and can serve as a diagnostic criterion for performance degradation of this component.

[0041] G represents the steam flow rate of each stage of the steam turbine, measured in kg / s. G is obtained through mass and energy balance calculations of the unit's thermodynamic system, specifically including the following steps:

[0042] The first step involves reading the pressure, temperature, and high-pressure cylinder exhaust pressure from the distributed control system. The pressure after the regulating stage refers to the steam pressure after the steam flows past the first-stage (regulating stage) moving blades of the turbine, measured by a pressure sensor installed on the outside of the high-pressure inner cylinder. The temperature after the regulating stage refers to the steam temperature after the first-stage moving blades of the turbine, measured by a thermocouple installed above the upper cylinder. The high-pressure cylinder exhaust pressure is measured by a pressure sensor installed on the high-pressure cylinder exhaust pipe. The main steam flow rate is then calculated using another variation of the Freuger formula.

[0043] ;

[0044] in, Main steam flow rate, in kg / s; The design steam flow rate is expressed in kg / s; Pressure after the regulating stage, in MPa; To design the pressure after the regulating stage; Temperature after regulation stage, in K; The temperature after the regulating stage is designed, and the unit is K. This is the exhaust pressure of the high-pressure cylinder, expressed in MPa. The design pressure for the high-pressure cylinder exhaust is expressed in MPa. , , and All of this information was obtained from technical data provided by the turbine manufacturer.

[0045] The second step involves drawing regenerated steam from the extraction ports between each stage of the steam turbine and transporting it through extraction pipelines to the corresponding regenerated heaters. For each regenerated heater, the extraction steam temperature, extraction steam pressure, feedwater inlet temperature, feedwater outlet temperature, feedwater inlet pressure, feedwater outlet pressure, feedwater flow rate, and condensate temperature are read from the distributed control system.

[0046] Specifically, the extraction steam temperature is measured by a temperature sensor installed on the extraction steam pipeline, and the extraction steam pressure is measured by a pressure sensor installed on the extraction steam pipeline; the feedwater inlet temperature and feedwater outlet temperature are measured by temperature sensors installed on the inlet feedwater pipeline and outlet feedwater pipeline of the regenerator, respectively; the feedwater inlet pressure and feedwater outlet pressure are measured by pressure sensors installed on the inlet feedwater pipeline and outlet feedwater pipeline of the regenerator, respectively; the feedwater flow rate is read from the feedwater flow rate measurement point of the distributed control system; and the condensate temperature is measured by a temperature sensor installed on the condensate pipeline.

[0047] Next, the feedwater inlet specific enthalpy, feedwater outlet specific enthalpy, extraction steam specific enthalpy, and condensate specific enthalpy are determined using an industrial standard function library of water and steam thermodynamic properties built into the distributed control system. Specifically, the feedwater inlet temperature and pressure are used as inputs to output the feedwater inlet specific enthalpy; the feedwater outlet temperature and pressure are used as inputs to output the feedwater outlet specific enthalpy; the extraction steam temperature and pressure are used as inputs to output the extraction steam specific enthalpy; and the condensate temperature is used as input to output the condensate specific enthalpy. This function library is compiled based on industrial standards for water and steam thermodynamic properties and is well-known in the field, so it will not be elaborated upon here. The above determination process is prior art and will not be elaborated upon here.

[0048] Next, calculate the extraction steam flow rate corresponding to each regenerating heater. The specific calculation formula is as follows:

[0049] ;

[0050] in, The extraction steam flow rate for each regenerating heater is expressed in kg / s. The water supply flow rate is expressed in kg / s. , These are the specific enthalpy at the feedwater outlet and the specific enthalpy at the feedwater inlet, respectively. The specific enthalpy of extraction vapor. The values ​​are hydrophobic specific enthalpy, and the units are all kJ / kg.

[0051] The third step is to subtract the sum of the extraction steam flow rate and the differential flow rate of shaft seal leakage and other losses corresponding to all upstream regenerative heaters of each group from the main steam flow rate to obtain the steam flow rate of each group. Among them, based on the flow direction of the working fluid in the thermal system, the equipment through which the working fluid first flows is the upstream. The flow direction of the working fluid in the thermal system is determined according to the technical drawings in the thermal power plant design data. The differential flow rate of shaft seal leakage and other losses is approximately taken as the leakage rate under the design conditions provided by the turbine manufacturer.

[0052] The calculation process for the heater terminal temperature difference is as follows: subtract the feedwater outlet temperature of the regenerator from the saturation temperature corresponding to the extraction steam pressure of the regenerator to obtain the terminal temperature difference. When the terminal temperature difference increases, it indicates that the heat exchanger tube bundle of the regenerator is fouled, has gas accumulation, or has experienced heat exchange area loss.

[0053] The saturation temperature corresponding to the extraction steam pressure is obtained as follows: Since there is a pressure loss along the pipeline when the extraction steam flows from the extraction port to the shell side of the regenerator heater, based on industry experience, the pipeline pressure loss rate is set to 0.03, and the corresponding pressure loss is recorded as 0.03 times the extraction steam pressure. The pressure loss is then subtracted from the extraction steam pressure to obtain the heater shell side pressure. Then, based on the industrial standards for the thermal properties of water and water vapor, and on... The saturation temperature is solved using the basic equation of the saturation line in the industrial standard. The specific solution process is based on existing technology and will not be elaborated here.

[0054] The calculation process for boiler flue gas temperature is as follows: the flue gas temperature is measured using thermocouples installed on the outlet flue of the boiler's air preheater, and this value is taken as the flue gas temperature. When ash or coking occurs on the boiler's heating surfaces, the thermal resistance on the flue gas side increases, the heat exchange efficiency decreases, and the flue gas temperature will rise accordingly. Therefore, changes in flue gas temperature characterize the ash and coking status of the boiler's tail-end heating surfaces and the degree of degradation in heat exchange performance.

[0055] After obtaining the turbine's flow area, heater terminal temperature difference, and boiler flue gas temperature, the standard deviations of the independent variables in the data subset are calculated. For each historical data point in the data subset, the differences between the historical and real-time data for the three independent variables are calculated, resulting in three corresponding difference values. Each difference is then divided by the standard deviation of the corresponding independent variable to obtain three standardized differences. The sum of squares of the three standardized differences is then taken as the weighted Euclidean distance. The smaller the weighted Euclidean distance, the smaller the difference between the operating conditions of the corresponding historical data point and the current operating conditions, and the greater the corresponding weight in the subsequent weighted regression fitting.

[0056] After obtaining the weighted Euclidean distance, the weight of each historical data point is determined by the following formula:

[0057] ;

[0058] in, Let i be the weight of the i-th historical data point; τ is the weighted Euclidean distance of the i-th historical data point; τ is the bandwidth parameter; i = 1, 2, 3, ..., n; n is the number of historical data points in the data subset.

[0059] The bandwidth parameter is determined as follows: For any two historical data points in the data subset, extract their respective three independent variables, subtract the same independent variables pairwise to obtain three differences, and take the square root of the sum of the squares of the three differences to obtain the original Euclidean distance between the two historical data points; based on engineering practice experience, 1.5 times the arithmetic mean of all original Euclidean distances is taken as the bandwidth parameter.

[0060] Next, linear regression was performed on each dependent variable to obtain the regression equation:

[0061] ;

[0062] Where y represents the dependent variable, namely the turbine's flow area, the heater terminal temperature difference, or the boiler exhaust temperature; These represent the three independent variables: unit load, calorific value of coal fed into the furnace, and ambient temperature. For the intercept term, , , These are the regression coefficients corresponding to the three independent variables.

[0063] The weighted sum of squared residuals is determined by minimizing the weighted sum of squared residuals. The expression for the weighted sum of squared residuals is:

[0064] ;

[0065] Where J represents the weighted sum of squared residuals; Represents the dependent variable for the i-th data point; Let represent the three independent variables for each data point i. The weighted sum of squared residuals is minimized by weighted least squares method, the specific solution process of which is existing technology and will not be elaborated here.

[0066] The above weighted regression fitting process was performed independently on the three dependent variables: the flow area of ​​each stage of the steam turbine, the terminal temperature difference of each regenerator, and the boiler flue gas temperature, to obtain their respective regression equations. The regression equations describe the relationship between the predicted values ​​of the dependent variables and the changes in the independent variables, and are used as a reference baseline.

[0067] Then, real-time data of unit load, calorific value of coal fed into the furnace, and ambient temperature are substituted into the reference baseline, and reference values ​​of turbine flow area, heater terminal temperature difference, and boiler flue gas temperature in the reference baseline are read.

[0068] Finally, the real-time data of turbine flow area, heater terminal temperature difference, and boiler flue gas temperature are subtracted from the corresponding reference values, and the resulting differences are divided by the corresponding reference values ​​to obtain residual values. The residual values ​​are arranged in chronological order to form the corresponding residual sequences, namely the flow area residual sequence, the terminal temperature residual sequence, and the flue gas temperature residual sequence.

[0069] Please see Figure 3 As shown, in step S2, the difference between the input enthalpy and the output enthalpy is calculated based on the temperature, pressure and flow rate of the working fluid at the inlet and outlet of each device; the enthalpy deviation is obtained by correcting the difference through the residual sequence.

[0070] For each stage of the steam turbine, the inlet working medium is the inlet steam of the corresponding stage. The temperature and pressure of the inlet working medium are measured by temperature and pressure sensors arranged on the steam pipe at the inlet of the stage. The corresponding inlet working medium flow rate is the steam flow rate of each stage obtained in step S1. Subtract the sum of the extraction steam flow rates from the extraction steam ports of each stage after the corresponding stage from the inlet working medium flow rate, and then subtract the leakage flow rate to obtain the outlet working medium flow rate.

[0071] The outlet working medium is the exhaust steam of the corresponding stage group. The temperature and pressure of the outlet working medium are measured by temperature and pressure sensors located on the steam pipe or cylinder wall at the stage group outlet. The residual value is extracted from the flow area residual sequence. The extraction steam flow rate from each extraction port is the extraction steam flow rate corresponding to each regenerative heater, which is calculated through step S1. The leakage flow rate is taken as the design leakage rate provided by the turbine manufacturer.

[0072] For the regenerative heater, the inlet working fluid includes feedwater and extraction steam. The feedwater pressure and temperature are measured by pressure and temperature sensors installed on the feedwater inlet pipe of the regenerative heater, respectively. The corresponding inlet working fluid flow rates are feedwater flow rate and extraction steam flow rate. The feedwater flow rate, extraction steam temperature, extraction steam pressure, and extraction steam flow rate all use the corresponding parameter values ​​obtained in step S1. The outlet working fluid is the outlet feedwater of the regenerative heater. The temperature and pressure of the outlet working fluid are measured by temperature and pressure sensors installed on the outlet feedwater pipe of the regenerative heater, respectively. The residual value is extracted from the terminal difference residual sequence. Under the condition of ignoring pipeline leakage, according to the law of conservation of mass, the outlet working fluid flow rate is approximately taken as the inlet working fluid flow rate.

[0073] Common types of boiler heating surfaces include water-cooled walls, superheaters, reheaters, and economizers. This embodiment uses the four types of heating surfaces commonly found in coal-fired boilers as examples for illustration:

[0074] Firstly, the inlet working fluid of the economizer is feedwater, and the temperature and pressure of the inlet working fluid are measured by temperature sensors and pressure sensors installed on the feedwater pipe at the economizer inlet, respectively; the inlet working fluid flow rate is read from the feedwater flow measurement point of the distributed control system; the outlet working fluid is heated feedwater, and the temperature and pressure of the outlet working fluid are measured by temperature sensors and pressure sensors installed on the economizer outlet pipe, respectively.

[0075] Secondly, the inlet working medium of the water-cooled wall is water, and its temperature and pressure are measured by temperature and pressure sensors installed on the inlet header of the water-cooled wall, respectively. The inlet working medium flow rate is the product of the main steam flow rate and the circulation ratio. The circulation ratio is taken as the design value in the boiler technical manual. The outlet working medium is a steam-water mixture, and its temperature and pressure are measured by temperature and pressure sensors installed in the outlet header of the water-cooled wall or in the steam drum, respectively.

[0076] Third, the inlet working fluid of the superheater is saturated steam, and the temperature and pressure of the inlet working fluid are measured by temperature sensors and pressure sensors respectively arranged on the steam pipe at the inlet of the superheater; the inlet working fluid flow rate is approximately taken as the main steam flow rate calculated in step S1; the outlet working fluid is superheated steam, and the temperature and pressure of the outlet working fluid are measured by temperature sensors and pressure sensors respectively installed on the steam pipe at the outlet of the superheater.

[0077] Fourth, the inlet working fluid of the reheater is cold reheat steam. The temperature and pressure of the inlet working fluid are measured by temperature and pressure sensors installed on the reheater inlet steam pipe, respectively. The inlet working fluid flow rate is obtained by subtracting the extraction steam flow rate corresponding to each regenerating heater and the leakage from the shaft seal and valve stem of the high-pressure cylinder from the main steam flow rate, and then adding the reheater desuperheating water flow rate. The extraction steam flow rate corresponding to each regenerating heater is calculated in step S1; the leakage rate is the design value provided by the turbine manufacturer; the reheater desuperheating water flow rate is directly read from the distributed control system; the outlet working fluid is hot reheat steam. The temperature and pressure of the outlet working fluid are measured by temperature and pressure sensors installed on the reheater outlet steam pipe, respectively.

[0078] The heating surfaces of the above four types of boilers are all relatively closed thermal systems. Under the condition of ignoring minor equipment leakage and water spray desuperheating, based on the law of conservation of mass, the outlet working fluid flow rate is approximately taken as the inlet working fluid flow rate, and the residual value is extracted from the flue gas temperature residual sequence.

[0079] After determining the temperature, pressure, and flow rate of the working fluid at the inlet and outlet of each piece of equipment, according to the first law of thermodynamics, the input and output enthalpies of various thermal equipment in the unit depend only on the temperature, pressure, and mass flow rate of the working fluid. The specific calculation method is independent of the equipment type. Therefore, the calculation process for the input and output enthalpies of each turbine unit, the regenerator, and the boiler heating surface is the same.

[0080] The input enthalpy calculation process is as follows: The temperature and pressure of the inlet working fluid are input into the industrial standard function library of water and steam thermodynamic properties built into the distributed control system. The function library outputs the corresponding specific enthalpy value as the specific enthalpy of the inlet working fluid. The specific enthalpy of the inlet working fluid is multiplied by the flow rate of the inlet working fluid to obtain the input enthalpy.

[0081] It should be noted that for a regenerative heater, the inlet enthalpy of the working fluid on the feedwater side is obtained from the feedwater temperature and feedwater pressure. Multiplying the inlet enthalpy of the working fluid on the feedwater side by the feedwater flow rate yields the input enthalpy of the feedwater side. Similarly, the inlet enthalpy of the working fluid on the extraction steam side is obtained from the extraction steam temperature and extraction steam pressure. Multiplying the inlet enthalpy of the working fluid on the extraction steam side by the extraction steam flow rate yields the input enthalpy of the extraction steam side. The input enthalpy is the sum of the input enthalpy of the feedwater side and the input enthalpy of the extraction steam side.

[0082] The output enthalpy calculation process is as follows: read the temperature and pressure of the working fluid at the outlet of the corresponding equipment from the distributed control system, input the temperature and pressure of the working fluid at the outlet into the function library mentioned above, and output the specific enthalpy of the working fluid at the outlet; multiply the specific enthalpy of the working fluid at the outlet by the flow rate of the working fluid at the outlet to obtain the output enthalpy.

[0083] Then, residual values ​​at the same sampling time are extracted from the flow area residual sequence, end difference residual sequence, or flue gas temperature residual sequence. The extracted residual value is multiplied by the inlet working fluid flow rate, and then multiplied by the inlet working fluid specific enthalpy to obtain the deviation correction. It should be noted that if the residual value at a certain sampling time is missing, the corresponding sampling time will not participate in the enthalpy deviation calculation, and no corresponding enthalpy deviation will be generated.

[0084] Finally, the input enthalpy is subtracted from the output enthalpy to obtain the initial enthalpy difference of the corresponding device; the deviation correction is subtracted from the initial enthalpy difference to obtain the enthalpy deviation of the corresponding device.

[0085] Step S3: Along the disturbance transmission direction determined based on the working fluid flow direction, subtract the component transmitted from upstream to downstream from the enthalpy deviation to obtain the net enthalpy deviation.

[0086] For the thermal power unit's thermal system, the working fluid flows from upstream equipment to downstream equipment along the medium flow direction. The enthalpy deviation of any equipment will be transmitted downstream along with the working fluid flow. Therefore, the flow direction of the working fluid in the thermal system is taken as the disturbance transmission direction.

[0087] Next, the devices are arranged according to the direction of disturbance transmission to determine the direct upstream device for each device. The direct upstream device is the device located one level before the corresponding device in the direction of disturbance transmission. For example, in a regenerative system, if the feedwater flows sequentially through high-pressure heater No. 3, high-pressure heater No. 2, and high-pressure heater No. 1, then the direct upstream device of high-pressure heater No. 2 is high-pressure heater No. 3, and the direct upstream device of high-pressure heater No. 1 is high-pressure heater No. 2.

[0088] After determining the direct upstream device of each device, calculate the enthalpy deviation of each device sequentially along the disturbance transmission direction, and record the device currently performing the enthalpy deviation calculation as the current device.

[0089] Each piece of equipment is connected to its immediate upstream equipment via pipelines. Specifically, the turbine stages and the turbine and reheater are connected via steam pipelines, the regenerators are connected via feedwater pipelines, and the boiler heating surfaces are connected via connecting pipes. To ensure calculation accuracy, after determining the immediate upstream equipment for each piece of equipment, it is necessary to determine the attenuation caused by pipeline losses during the transmission of enthalpy deviation to the current equipment.

[0090] The specific determination process is as follows: considering that the heat loss of the water supply pipe is small, it can be ignored; the length of the connecting pipe between the boiler heating surfaces is short and located within the boiler body, so its heat loss can also be ignored; there is a large temperature difference between the working fluid transported by the steam pipe and the ambient temperature, so the heat loss cannot be ignored.

[0091] Steam pipelines are usually covered with insulation to reduce heat loss. The heat loss of the pipeline is calculated based on the thickness of the insulation layer, the thermal conductivity of the insulation material, and the difference between the temperature of the working fluid in the pipeline and the ambient temperature.

[0092] First, the heat loss per unit length of the pipe is calculated based on the heat conduction formula of the cylindrical wall:

[0093] ;

[0094] Where q is the heat loss per unit length of the pipe, in W / m; π is pi, specifically taken as 3.14;

[0095] The temperature of the working fluid inside the pipeline is expressed in °C and is measured by a temperature sensor installed at the inlet of the steam pipeline. The ambient temperature is measured in °C and is determined by ambient temperature measuring points in the area where the steam pipeline is located. The inner radius of the pipe, in meters, is obtained from the design manual provided by the equipment manufacturer. The outer radius of the insulation layer is the inner radius of the pipe plus the thickness of the insulation layer, in meters (m). This value can be obtained from the design manual provided by the equipment manufacturer. The thermal conductivity of the insulation material is expressed in W / (m·K), which can be found in the product manual provided by the insulation material manufacturer.

[0096] Next, the corresponding pipe length is read from the design drawings. For equipment connected by steam pipes, the length of the steam pipe is read. The heat loss per unit length of pipe is multiplied by the length of the steam pipe to obtain the heat loss of the corresponding steam pipe, which is recorded as the pipe heat loss of the corresponding equipment.

[0097] If the current equipment is connected to its direct upstream equipment through multiple steam pipes, the heat loss of each steam pipe is calculated separately, and the sum of the heat loss of each steam pipe is taken as the pipeline heat loss of the corresponding equipment.

[0098] After obtaining the heat loss of the pipeline, for equipment connected by steam pipelines, the volumetric flow rate of the working fluid in the pipeline is read from the distributed control system, and the volumetric flow rate is divided by the cross-sectional area of ​​the pipeline to obtain the average flow velocity of the working fluid in the pipeline; then the length of the steam pipeline is divided by the average flow velocity of the working fluid in the pipeline to obtain the transmission delay time; wherein, the cross-sectional area of ​​the pipeline is calculated based on the inner diameter of the pipeline obtained from the design drawings, and the specific calculation process is existing technology and will not be described in detail here.

[0099] Then, using the current sampling time as the endpoint, the transmission delay time is traced back to determine the corresponding sampling time, which is taken as the historical time. The enthalpy deviation of the direct upstream device of the current device at the historical time is extracted and recorded as the upstream delay deviation; if there is no corresponding enthalpy deviation at the traced historical time, the enthalpy deviation of the sampling time with the smallest time difference from the historical time is used as a substitute, and the above calculation is performed. The pipeline heat dissipation loss is subtracted from the upstream delay deviation to obtain the variation component; the variation component is subtracted from the enthalpy deviation of the current device to obtain the net enthalpy deviation.

[0100] For equipment connected via water supply pipelines, the working fluid transmission delay still exists. The transmission delay time and upstream delay deviation need to be determined using the aforementioned method. The net enthalpy deviation is obtained by subtracting the upstream delay deviation from the current equipment's enthalpy deviation.

[0101] For the connecting pipes between the boiler heating surfaces, since they are short and have little delay, heat loss and transmission delay are negligible. The net enthalpy deviation is calculated by directly using the enthalpy deviation of the direct upstream device at the current sampling time as the variation component.

[0102] It should be added that when a device is a medium inlet device, that is, there is no direct upstream device, the corresponding net enthalpy deviation is directly taken as its enthalpy deviation.

[0103] Step S4: Based on the inlet working fluid pressure and the inlet and outlet working fluid flow rates, the net enthalpy deviation is divided into exogenous enthalpy deviation and endogenous enthalpy deviation.

[0104] In actual operation of thermal power units, the net enthalpy deviation of the equipment originates from two different types of disturbances: one is the enthalpy deviation caused by changes in the external boundary conditions of the equipment, i.e., exogenous enthalpy deviation; the other is the enthalpy deviation caused by the degradation of the equipment's own performance or changes in its state, i.e., endogenous enthalpy deviation. This step distinguishes between the aforementioned exogenous and endogenous enthalpy deviations by comparing the direction of change of the inlet working fluid pressure deviation with that of the net enthalpy deviation, thereby improving the accuracy of subsequent assessments.

[0105] Because the real-time pressure of the inlet working medium is affected by operating conditions such as unit load, calorific value of coal fed into the furnace, and ambient temperature, the physical meaning of the same pressure value is different under full load and half load conditions. Therefore, it is impossible to determine whether the inlet working medium pressure has deviated from the normal state by using the real-time pressure of the inlet working medium.

[0106] Therefore, the same weighted regression method as in step S1 is adopted, with unit load, calorific value of coal fed into the furnace and ambient temperature as independent variables and inlet working fluid pressure of each equipment as dependent variable. The historical data under the healthy operating conditions of the unit are fitted, and the comparison between the fitted equation results and the real-time values ​​is used as the basis for judging the change of inlet working fluid pressure with operating conditions.

[0107] Specifically, during each execution of step S4, the unit load, calorific value of the coal fed into the furnace, and ambient temperature at the current sampling time are substituted into the corresponding fitting equation to obtain the pressure reference value of the inlet working fluid under the current operating conditions; the pressure reference value is subtracted from the real-time obtained inlet working fluid pressure to obtain the deviation; a positive deviation value indicates that the inlet working fluid pressure is higher than the reference level, and a negative deviation value indicates that the inlet working fluid pressure is lower than the reference level.

[0108] Next, the deviation and net enthalpy deviation are arranged in chronological order of sampling time to obtain the deviation sequence and the deviation sequence, respectively. Each element in the deviation sequence represents the deviation at the corresponding sampling time, and each element in the deviation sequence represents the net enthalpy deviation at the corresponding sampling time. The deviation sequence and the deviation sequence are aligned on the time axis, with the same index position corresponding to the same sampling time.

[0109] Then, for each deviation other than the first deviation in the deviation sequence, calculate the difference between each deviation and the previous adjacent deviation, and record it as the adjacent difference.

[0110] If the difference between adjacent values ​​is greater than zero, the deviation is determined to be increasing at the corresponding sampling time; if the difference between adjacent values ​​is less than zero, the deviation is determined to be decreasing at the corresponding sampling time; if the difference between adjacent values ​​is equal to zero, the deviation is determined to be flat at the corresponding sampling time.

[0111] Following the same method described above, the direction of change of each net enthalpy deviation in the deviation sequence is determined at each sampling time. It should be noted that the first deviation in the deviation sequence, and the first net enthalpy deviation in the deviation sequence, are not included in the determination of the direction of change because there are no preceding adjacent deviations or net enthalpy deviations for comparison. If the deviation or net enthalpy deviation at a certain sampling time is missing, the corresponding sampling time is not included in the determination of the direction of change.

[0112] At the same sampling time, if the direction of change of the deviation is the same as the direction of change of the net enthalpy deviation, it indicates that the change of the net enthalpy deviation is synchronous with the change of the inlet working fluid pressure, that is, the change of the net enthalpy deviation is driven by the external boundary conditions, and the net enthalpy deviation at the corresponding sampling time is marked as exogenous enthalpy deviation; if the direction of change of the deviation is different from the direction of change of the net enthalpy deviation, it indicates that the change of the net enthalpy deviation is not driven by the change of the external boundary conditions, and the net enthalpy deviation at the corresponding sampling time is marked as endogenous enthalpy deviation.

[0113] Then, all net enthalpy deviations marked as exogenous enthalpy deviations are removed from the deviation sequence, and the remaining net enthalpy deviations constitute the endogenous enthalpy deviation sequence. When a sampling moment is not involved in determining the direction of change, the corresponding net enthalpy deviation is neither marked as an exogenous enthalpy deviation nor as an endogenous enthalpy deviation.

[0114] Please see Figure 4 As shown, in step S5, the abnormal equipment and evaluation cycle are determined based on the amplitude and rate of change of the exogenous enthalpy deviation; the efficiency decay value of each equipment is determined based on the cumulative amount of the endogenous enthalpy deviation.

[0115] First, a first observation window is set. The setting process is as follows: For the steam turbine, the duration of the first observation window is a preset multiple of the sum of the rotor time constant and the reheater time constant; for the regenerating heater, the duration of the first observation window is a preset multiple of the regenerating heater's thermal inertia time constant; for the boiler heating surface, the duration of the first observation window is a preset multiple of the heat transfer process time constant of the heating surface. The above time constants are obtained from the manufacturer's technical manual or determined through on-site step response tests. The specific test process adopts existing technology and will not be elaborated here. The preset multiple is specifically set to 5 times to balance statistical stability and response timeliness.

[0116] Then, the first observation window of the aforementioned duration is intercepted with the current sampling time as the endpoint, and the endogenous enthalpy deviation is integrated over time within the first observation window to obtain the cumulative amount of the endogenous enthalpy deviation.

[0117] Next, using the same method as in step S1, historical data of the corresponding equipment during its healthy operating period are selected. Taking each sampling time in the selected historical data as the endpoint, the first observation window is extracted backward. Within each first observation window, the endogenous enthalpy deviation is integrated over time to obtain the corresponding cumulative quantity. At the same time, the product of the working fluid flow rate and the difference in the specific enthalpy of the inlet and outlet working fluids is integrated over time to obtain the corresponding integral value. The arithmetic mean of multiple cumulative quantities is taken as the cumulative quantity benchmark value, and the arithmetic mean of multiple integral values ​​is taken as the theoretical output value.

[0118] Subsequently, the cumulative amount of the intrinsic enthalpy deviation is subtracted from the cumulative baseline value to obtain the attenuation characterization quantity; the attenuation characterization quantity represents the additional loss due to the equipment's own performance degradation. Dividing the attenuation characterization quantity by the theoretical output value yields the efficiency attenuation value; the efficiency attenuation value represents the proportion of equipment efficiency reduction relative to the healthy operating state.

[0119] In addition to planned maintenance in accordance with the maintenance guidelines for coal-fired power plants or the maintenance cycle recommended by the equipment manufacturers, thermal power units may also undergo unplanned maintenance due to abnormal equipment failures. The efficiency degradation value one week before the unplanned maintenance represents the actual degree of deterioration of the corresponding equipment when maintenance is required due to abnormal failures. Therefore, a preset degradation value can be set accordingly.

[0120] The specific setting process is as follows: retrieve the historical unplanned maintenance records of each device, and calculate the efficiency decay value corresponding to each first observation window within the week prior to each unplanned maintenance; for each maintenance, take the arithmetic mean of the efficiency decay values ​​of all first observation windows within the week prior to the maintenance as the decay reference value for this maintenance; take the arithmetic mean of the decay reference values ​​for each maintenance as the preset decay value for the corresponding device. When there are no historical unplanned maintenance records for the corresponding device or the duration before the historical unplanned maintenance records is less than one week, the industry-recognized experience value obtained by consulting power industry reference books will be used as the preset decay value. If the experience value is given in the form of a parameter range, the median value of the parameter range will be taken as the preset decay value.

[0121] When the efficiency decay value is greater than the preset decay value, it indicates that the decay ratio of the corresponding device exceeds the limit range, that is, quantifiable performance degradation has occurred. Therefore, the corresponding device is marked as abnormal device, and the evaluation period is set to the first period.

[0122] Considering that when a device experiences an exogenous enthalpy deviation due to an external disturbance, this deviation will propagate downstream along the disturbance propagation direction with the working fluid flow, forming a disturbance propagation chain from the disturbance source device to the downstream affected device, when the efficiency decay value is less than or equal to a preset decay value, the device with the largest exogenous enthalpy deviation at the current sampling time is extracted as the downstream device of the disturbance propagation chain and recorded as the tracing starting point.

[0123] Starting from the tracing point, tracing is performed in reverse along the direction of disturbance propagation, sequentially obtaining the exogenous enthalpy deviation of each device. When the absolute value of the exogenous enthalpy deviation corresponding to the tracing device is less than the termination limit, it indicates that the exogenous enthalpy deviation of the corresponding device has fallen into the operating fluctuation range, and its disturbance to downstream devices is small and can be ignored, so tracing is stopped. The device at which tracing stops is recorded as the tracing stop point. The device whose absolute value of the last level of exogenous enthalpy deviation before the tracing stop point is greater than or equal to the termination limit is the external disturbance source of the disturbance propagation chain, and is recorded as the tracing end point.

[0124] The termination limit is determined as follows: using the same method as in step S1, historical data of the corresponding device during the healthy operating period is selected, and each sampling time in the selected historical data is taken as the endpoint. The first observation window is then extracted forward, and the corresponding exogenous enthalpy deviation value is calculated within each first observation window. All exogenous enthalpy deviation values ​​are used to form a sample sequence, and the standard deviation of the sample sequence is calculated as the termination limit value of the corresponding device.

[0125] Once the starting point and ending point of the traceability are determined, the traceability path is formed by the starting point, the ending point, and all the equipment in between.

[0126] If, in addition to the devices covered by the tracing path, there are still devices whose absolute value of exogenous enthalpy deviation is greater than or equal to the termination limit, a new tracing starting point is extracted, and the tracing is repeated; if there are no devices whose absolute value of exogenous enthalpy deviation is greater than or equal to the termination limit, the tracing ends.

[0127] After the tracing process ends, all tracing endpoints are marked as abnormal devices; the remaining devices are marked as normal devices. Then, the corresponding evaluation cycle is determined.

[0128] The specific process for determining the evaluation cycle is as follows: For non-abnormal equipment, the evaluation cycle is set as the second cycle; for abnormal equipment, the second observation window is intercepted forward from the current sampling time. The duration of the second observation window is one-fifth of the duration of the first observation window, so as to obtain the changing trend of exogenous enthalpy deviation in a timely manner, while avoiding the influence of fluctuations that may lead to misjudgment.

[0129] Starting from the second sampling time in the second observation window, the difference between the exogenous enthalpy deviation at each sampling time and the exogenous enthalpy deviation at the previous adjacent sampling time is calculated and recorded as the deviation difference. If the deviation difference is greater than zero, the trend is determined to be increasing; if the deviation difference is less than zero, the trend is determined to be decreasing; if the difference is equal to zero, the trend is determined to be flat.

[0130] Then, count the number of times the trend of change is increasing and the number of times the trend of change is decreasing, and record them as the number of increases and the number of decreases; record the total number of all deviation differences within the second observation window as the total number of differences.

[0131] If the number of increases is greater than or equal to the preset proportion of the total difference, it is determined that the exogenous enthalpy deviation of the corresponding traceability starting point shows a monotonically increasing trend in the second observation window, indicating that the external disturbance is continuously intensifying and the equipment operating environment is deteriorating. The evaluation period is set to the first period.

[0132] If the number of reductions is greater than or equal to the preset proportion of the total difference, it is determined that the exogenous enthalpy deviation of the corresponding traceability starting point shows a monotonically decreasing trend in the second observation window, indicating that the external disturbance is being alleviated and the equipment operating environment is improving. The evaluation cycle is then set to the third cycle.

[0133] If both the number of increases and decreases are less than the preset proportion of the total difference, then the evaluation period will be set to the second period.

[0134] To eliminate measurement noise or disturbances and ensure the statistical robustness of the judgment results, the preset ratio is set to two-thirds. In practical applications, the preset ratio can be adjusted according to the equipment type and actual operating conditions.

[0135] In the aforementioned assessment cycle, the second cycle is the maintenance cycle for daily operation monitoring of thermal power units, obtained from the power plant's daily operation management procedures, specifically 24 hours; the first cycle is the shortest, specifically one-third of the second cycle, used for intensive monitoring of the corresponding equipment to promptly detect anomalies; the third cycle is the longest, specifically three times the second cycle, used for low-frequency monitoring of equipment whose condition is improving, avoiding waste of computing resources. Through the differentiated settings of the above assessment cycles, a dynamic match between the assessment cycle and the actual condition of the equipment is achieved, realizing on-demand allocation of computing resources.

[0136] It should be added that, provided that the first cycle is shorter than the second cycle and the second cycle is shorter than the third cycle, the first, second, and third cycles can be adjusted according to the unit type and actual operating conditions.

[0137] The start time of the evaluation cycle is determined as the time of assessment. The exogenous enthalpy deviation corresponding to the start time of the evaluation cycle is taken as the exogenous enthalpy deviation of the corresponding evaluation cycle. When the exogenous enthalpy deviation of the abnormal device is less than the termination limit and the efficiency decay value is less than the preset decay value in several consecutive evaluation cycles, it indicates that the external disturbance has disappeared and the device's performance has returned to normal. The abnormal device mark is then removed, and the device is converted to a normal device. The corresponding evaluation cycle is set as the second cycle. Otherwise, the abnormal device mark and the corresponding evaluation cycle are maintained. The specific number of consecutive evaluation cycles is three to ensure timeliness and avoid misjudgment.

[0138] Step S6: Based on the assessment cycle, diagnose the failure modes of each device and abnormal devices, and generate a single device health score by combining the efficiency decay value. After summarizing at each level, generate a whole machine assessment report including the device maintenance level.

[0139] After obtaining the evaluation period, the efficiency decay value is continuously obtained according to the corresponding evaluation period. The efficiency decay value at the beginning of each evaluation period is used as the efficiency decay value for each evaluation period.

[0140] For abnormal equipment, it is necessary to further determine the failure mode: take the current evaluation period and the three evaluation periods with the smallest time difference with the current evaluation period as reference periods; arrange the four efficiency decay values ​​corresponding to the reference periods in chronological order to form an efficiency decay value sequence; calculate the difference between each efficiency decay value in the efficiency decay value sequence and the previous adjacent efficiency decay value to form a difference value sequence.

[0141] If all terms in the difference sequence are greater than zero, the fault mode is determined to be a deterioration-intensifying type, indicating that the equipment performance is continuously deteriorating; if all terms in the difference sequence are less than zero, the fault mode is determined to be a recovery-trend type, indicating that the equipment performance is gradually improving; otherwise, the fault mode is determined to be a fluctuating-stable type, indicating that the equipment performance has no clear directional change.

[0142] It should be added that if the corresponding device is marked as abnormal and has not yet undergone 4 evaluation cycles, the fault mode will be set to provisional until the evaluation cycle is greater than or equal to 4, at which point the fault mode will be re-determined. This is to avoid misjudgment due to insufficient data when determining the fault mode, which may be caused by short-term fluctuations.

[0143] Then, based on the efficiency decay value of the current evaluation period, calculate the individual health score of each device in the following manner, with the health score using a percentage system.

[0144] Specifically, when the efficiency decay value is zero, the corresponding single device health score is 100 points; when the efficiency decay value is greater than or equal to the preset decay value, the corresponding single device health score is 0 points; when the efficiency decay value is greater than 0 and less than the preset decay value, the ratio of the efficiency decay value to the preset decay value is calculated, and the ratio is subtracted from 1 and then multiplied by 100 to obtain the corresponding single device health score.

[0145] After obtaining the individual health scores of each device, the subsystem to which each device belongs is determined based on the thermal system diagram of the thermal power unit; the arithmetic mean of the individual health scores of multiple devices belonging to the same subsystem is calculated to obtain the health score of each subsystem; then, the arithmetic mean of the health scores of each subsystem is calculated to obtain the overall health score of the entire unit.

[0146] After obtaining the overall health score of the unit, it is also necessary to determine the equipment maintenance level: when the overall health score of the unit is higher than the first score limit and there are no abnormal equipment with the failure mode of deterioration aggravation, the equipment maintenance level is determined to be the first maintenance level, indicating that the overall condition of the unit is good, and it is recommended to carry out planned maintenance in accordance with the maintenance guidelines for coal-fired power plants or the maintenance cycle recommended by the equipment manufacturer.

[0147] When the overall health score of the machine is lower than the first score threshold but higher than the second score threshold, or when there is only one abnormal device with a failure mode of aggravated deterioration, the equipment maintenance level is determined to be the second maintenance level, and it is recommended to repair the abnormal device with aggravated deterioration.

[0148] When the overall health score of the machine is lower than the second score threshold, or when there are two or more abnormal devices with the fault type of worsening, the equipment maintenance level is determined to be the third maintenance level, and it is recommended to shut down the machine for maintenance.

[0149] The determination of the first and second scoring thresholds is as follows: Referring to step S1, historical data of the thermal power unit under healthy operating conditions is selected, and the minimum value of the overall unit health score is chosen as the first scoring threshold. From the historical unplanned maintenance records of the thermal power unit, historical data from the week preceding each unplanned maintenance is extracted and summarized. The maximum value of the overall unit health score is chosen from the summarized historical data as the second scoring threshold. When there is no selectable historical data, or the number of overall unit health scores corresponding to the historical data is less than three, based on engineering practice experience, the first scoring threshold is set to 70 points, and the second scoring threshold is set to 50 points.

[0150] Finally, to promptly determine whether maintenance needs to be arranged, a comprehensive unit assessment report is generated every 24 hours and pushed to the power plant operators or the condition-based maintenance management system. The comprehensive unit assessment report includes the overall health score of the unit, the maintenance level of the unit equipment, equipment name, equipment type, failure mode, efficiency degradation value, assessment cycle, health scores of each subsystem, health scores of individual equipment, and maintenance recommendations generated based on the overall equipment maintenance level and abnormal equipment failure modes.

[0151] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0152] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0153] In addition, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0154] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0155] Finally, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for assessing the operational health status of thermal power units, characterized in that, Includes the following steps: Based on unit load, calorific value of coal fed into the furnace and ambient temperature, a reference baseline is constructed within a sliding window for the turbine's flow area, heater terminal temperature difference and boiler flue gas temperature, and a residual sequence is obtained by combining real-time data. Calculate the difference between the input enthalpy and the output enthalpy based on the temperature, pressure and flow rate of the working fluid at the inlet and outlet of each device; The enthalpy deviation is obtained by correcting the difference using the residual sequence; Along the disturbance transmission direction determined by the working fluid flow direction, the component transmitted from upstream to downstream is subtracted from the enthalpy deviation to obtain the net enthalpy deviation; Based on the pressure of the imported working medium and the flow rates of the inlet and outlet working medium, the net enthalpy deviation is divided into exogenous enthalpy deviation and endogenous enthalpy deviation. The efficiency degradation value of each device is determined based on the cumulative amount of endogenous enthalpy deviation; the abnormal devices and evaluation cycle are determined based on the amplitude and rate of change of exogenous enthalpy deviation. Based on the assessment cycle, the fault modes of each device and abnormal devices are diagnosed, and the efficiency decay value is combined to generate a single device health score, which is then summarized level by level to generate a whole machine assessment report including the device maintenance level.

2. The method for assessing the operational health status of a thermal power unit as described in claim 1, characterized in that, The process of obtaining the residual sequence by combining real-time data is as follows: Several sampling times are extracted backward from the current sampling time to form a fitting period; the unit load within the fitting period is linearly fitted, and the slope obtained from the fitting is used as the real-time rate of change; the width of the sliding window is determined based on the real-time rate of change. Using unit load, calorific value of coal fed into the furnace, and ambient temperature as independent variables, and turbine flow area, heater terminal temperature difference, and boiler flue gas temperature as dependent variables, a weighted fit is performed on historical data containing independent and dependent variables within a sliding window to construct a reference baseline for flow area, heater terminal temperature difference, and boiler flue gas temperature. After substituting the real-time data of unit load, calorific value of coal fed into the furnace, and ambient temperature into the corresponding reference baseline, the reference values ​​of flow area, heater terminal temperature difference, and boiler flue gas temperature in the reference baseline are read. Subtract the corresponding reference values ​​from the real-time data of flow area, heater terminal temperature difference, and boiler flue gas temperature, and divide the resulting difference by the corresponding reference value to obtain the residual value. Arrange the residual values ​​in chronological order to form the corresponding residual sequences, namely the flow area residual sequence, terminal temperature difference residual sequence, and flue gas temperature residual sequence.

3. The method for assessing the operational health status of a thermal power unit as described in claim 2, characterized in that, The process of determining the width of the sliding window is as follows: Based on the rate of change of the unit load within a set historical period, a reference range for the rate of change is set; based on the rotor time constant and reheater time constant of the unit, the reference width is determined. When the real-time rate of change is less than the lower limit of the rate of change reference interval, the width of the sliding window is set to twice the reference width. When the real-time rate of change is greater than the upper limit of the rate of change reference interval, the width of the sliding window is set to half of the reference width; Otherwise, set the width of the sliding window to the reference width.

4. The method for assessing the operational health status of a thermal power unit as described in claim 2, characterized in that, The process of obtaining the enthalpy deviation is as follows: The specific enthalpy of the inlet working fluid is determined based on the temperature and pressure of the inlet working fluid for each device. The input enthalpy is obtained by multiplying the specific enthalpy of the inlet working fluid by the inlet working fluid flow rate. Similarly, the output enthalpy is obtained based on the temperature and pressure of the outlet working fluid for each device. Subtracting the output enthalpy from the input enthalpy yields the initial enthalpy difference for each device. Extract the flow area residual value at the corresponding sampling time from the flow area residual sequence; extract the end difference residual value at the corresponding sampling time from the end difference residual sequence; extract the exhaust temperature residual value at the corresponding sampling time from the exhaust temperature residual sequence. Multiply the residual value extracted from each device by the inlet working fluid flow rate, and then multiply by the inlet working fluid specific enthalpy to obtain the deviation correction amount; Subtract the deviation correction amount from the initial enthalpy difference to obtain the enthalpy deviation of each device.

5. The method for assessing the operational health status of a thermal power unit as described in claim 4, characterized in that, The process of obtaining the net enthalpy deviation is as follows: Using the flow direction of the working fluid in the thermodynamic system as the disturbance transmission direction, the equipment is arranged according to the disturbance transmission direction, and the direct upstream equipment of each equipment is determined. Obtain the pipeline length between each device and its direct upstream device, and calculate the heat loss of the pipeline by combining the difference between the working fluid temperature in the pipeline and the ambient temperature and the thickness of the pipeline insulation layer. Divide the pipeline length by the average flow velocity of the working fluid in the pipeline to obtain the transmission delay time; Taking the current sampling time as the endpoint, backtracking the transmission delay time, extracting the enthalpy deviation of the direct upstream device at the corresponding sampling time, and recording it as the upstream delay deviation; Subtracting the heat loss from the pipeline from the upstream delay deviation yields the change component; Subtract the change component from the enthalpy deviation to obtain the net enthalpy deviation of each device.

6. The method for assessing the operational health status of a thermal power unit as described in claim 1, characterized in that, The process of distinguishing between exogenous enthalpy deviation and endogenous enthalpy deviation is as follows: Obtain the reference pressure value of the inlet working medium for each device under the current operating conditions; subtract the reference pressure value from the inlet working medium pressure to obtain the deviation. The deviation and net enthalpy deviation are arranged in chronological order of sampling time to obtain the deviation sequence and the deviation sequence, respectively. By comparing the deviation and net enthalpy deviation of adjacent sampling times, the direction of change of the deviation and net enthalpy deviation at each sampling time is determined. The net enthalpy deviation that is in the same direction as the deviation amount is marked as the exogenous enthalpy deviation; After removing all exogenous enthalpy deviations from the deviation sequence, the remaining net enthalpy deviations are marked as endogenous enthalpy deviations.

7. The method for assessing the operational health status of a thermal power unit as described in claim 1, characterized in that, The process of determining the efficiency degradation value of each device is as follows: For each device, the first observation window is extracted backward from the current sampling time; within the first observation window, the endogenous enthalpy deviation is integrated over time to obtain the cumulative amount of the endogenous enthalpy deviation. Based on historical operational data, the cumulative baseline value and theoretical output value of each device within the first observation window are determined; Subtracting the cumulative reference value from the cumulative amount of the endogenous enthalpy deviation yields the attenuation characterization; dividing the attenuation characterization by the theoretical output value yields the efficiency attenuation value.

8. The method for assessing the operational health status of a thermal power unit as described in claim 7, characterized in that, The process for identifying faulty equipment is as follows: Devices whose efficiency decay value exceeds the preset decay value are marked as abnormal devices, and the evaluation period is set to the first period; for the remaining devices, the device with the largest exogenous enthalpy deviation at the current sampling time is extracted as the tracing starting point; The tracing process begins from the starting point and proceeds in the reverse direction of the disturbance propagation. Tracing stops when the absolute value of the exogenous enthalpy deviation is less than the termination limit. The device that stops tracing is recorded as the stop tracing point, and the device whose absolute value of the last stage exogenous enthalpy deviation before the stop tracing point is greater than or equal to the termination limit is recorded as the tracing endpoint. The traceability path consists of the traceability start point, the traceability end point, and all the equipment in between. In addition to the devices covered by the tracing path, if there are still devices whose absolute value of exogenous enthalpy deviation is greater than or equal to the termination limit, a new tracing starting point is extracted and the tracing is repeated; all tracing endpoints are marked as abnormal devices, and the remaining devices are marked as non-abnormal devices.

9. The method for assessing the operational health status of a thermal power unit as described in claim 8, characterized in that, The process of determining the evaluation cycle is as follows: For abnormal devices marked after tracing, a second observation window is extracted backward from the current sampling time; If the exogenous enthalpy deviation of the starting point shows a monotonically increasing trend within the second observation window, the evaluation period is set to the first period; if the exogenous enthalpy deviation of the starting point shows a monotonically decreasing trend within the second observation window, the evaluation period is set to the third period; otherwise, the evaluation period is set to the second period. For non-abnormal equipment, the evaluation cycle is set as the second cycle; among them, the first cycle is the shortest and the third cycle is the longest.

10. The method for assessing the operational health status of a thermal power unit as described in claim 8, characterized in that, The process of generating a complete machine evaluation report is as follows: For abnormal equipment, the failure mode is determined based on its efficiency degradation value over multiple consecutive evaluation periods; When the efficiency decay value is zero, the single device health score is full. When the efficiency decay value is greater than the corresponding preset decay value, the health score of a single device is zero; When the efficiency decay value is greater than zero and less than the corresponding preset decay value, a linear interpolation method is used to determine the health score of a single device. The health scores of all individual devices are summarized level by level to obtain the subsystem health score and the overall machine health score; The equipment maintenance level is determined based on the overall health score and failure mode of the machine, and an overall machine assessment report is generated.

Images