A method for diagnosing deep peak load faults in thermal power units

Abstract

The present invention provides a method for diagnosing deep peak-shaving faults of thermal power units, which relates to the technical field of operation monitoring of thermal power units, and comprises: collecting various operation parameters of the thermal power units in the process of deep peak-shaving in real time, and classifying them according to the functional systems to which they belong; the functional systems include a steam system, a combustion system, a ventilation system and a mechanical transmission system; establishing operation status evaluation models based on different functional systems respectively; substituting the various operation parameters collected into the operation status evaluation model for calculation and analysis, and analyzing the coupling relationship between different evaluation results at the same time, so as to extract a comprehensive fault evaluation value; diagnosing the fault state based on the comprehensive fault evaluation value and each evaluation result, and providing a fault location suggestion; the present invention establishes a detailed operation status evaluation model of each system by comprehensively collecting and classifying the operation parameters of each functional system of the unit, so as to realize accurate diagnosis and location of the faults of the thermal power units under deep peak-shaving conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of thermal power unit operation monitoring, and in particular to a method for diagnosing deep peak regulation faults of thermal power units. Background Art

[0002] In the early days, thermal power units were mainly used as the main power source for power guarantee, and their design and operation focused on full-load power generation. With the increase in the demand for deep peak regulation, thermal power units have exposed many problems in the process of deep peak regulation. On the one hand, the operating parameters of the units under deep peak regulation conditions deviate from the traditional design conditions, resulting in increased equipment wear, reduced efficiency, and increased pollutant emissions. For example, boiler combustion is unstable during low-load operation, and incomplete combustion is prone to occur, increasing fuel consumption and pollutant emissions. The blades of the steam turbine are susceptible to erosion and water erosion under low flow conditions, affecting the efficiency and life of the steam turbine. On the other hand, most of the existing monitoring and diagnosis technologies for thermal power units are based on traditional operating condition designs, and it is difficult to accurately judge the operating status of the unit and timely discover potential faults under deep peak regulation conditions.

[0003] At present, some traditional fault diagnosis methods have limitations in deep peak load regulation. For example, some methods based on single parameter threshold judgment are prone to misjudgment under complex deep peak load regulation conditions. Because multiple parameters are interrelated and change in a complex manner during deep peak load regulation, a single threshold cannot fully reflect the true state of the unit. In addition, some existing fault diagnosis systems lack in-depth analysis of different subsystems (such as steam systems, combustion systems, etc.), and can only obtain the overall fault judgment results of the unit, which reduces the accuracy of fault diagnosis.

[0004] Therefore, there is an urgent need in the art for a method for diagnosing deep peak load failures of thermal power units to solve the above problems. Summary of the invention

[0005] The present invention provides a method for diagnosing deep peak-shaving faults of thermal power units. By comprehensively collecting and classifying the operating parameters of various functional systems of the unit, a detailed operating status evaluation model of each system is established, so as to accurately diagnose and locate the faults of the thermal power units under deep peak-shaving conditions, thereby solving the problem of inaccurate and incomplete fault diagnosis of thermal power units under deep peak-shaving conditions in the prior art.

[0006] The present invention provides a method for diagnosing deep peak load failure of a thermal power unit, comprising:

[0007] Step 1: collect various operating parameters of thermal power units during deep peak regulation in real time and classify them according to their functional systems; the functional systems include steam system, combustion system, ventilation system and mechanical transmission system;

[0008] Step 2: Establish operation status evaluation models based on different functional systems;

[0009] Step 3: Substituting the collected various operating parameters into the operating status evaluation model for calculation and analysis, and analyzing the coupling relationship between different evaluation results to extract a comprehensive fault evaluation value;

[0010] Step 4: diagnose the fault status based on the comprehensive fault evaluation value and each evaluation result, and provide fault location suggestions.

[0011] According to a method for diagnosing deep peak load regulation faults of a thermal power unit provided by the present invention, the process of real-time acquisition of various operating parameters of the thermal power unit during deep peak load regulation and classification according to the functional systems to which they belong comprises:

[0012] For the steam system, the collected operating parameters include steam density, steam flow rate, cross-sectional area of ​​the inlet pipe at the steam inlet, steam density, steam flow rate, cross-sectional area of ​​the pipe at the preset measuring point, theoretical heat released by fuel combustion, steam inlet temperature, pressure, steam outlet temperature, pressure, and steam mass flow rate;

[0013] For the combustion system, the collected operating parameters include the type of fuel raw material, the fuel flow rate and air flow rate entering the combustion chamber, the temperatures of three preset measuring points in the combustion chamber, and the current flame image;

[0014] For the ventilation system, the collected operating parameters include the air pressure at the fan, the air flow, the actual input power of the fan and the rated efficiency of the fan, the length and diameter of the ventilation duct, the air density and flow rate in the ventilation duct, the inlet and outlet pressure difference of the ventilation duct and the friction coefficient of the ventilation duct;

[0015] For mechanical transmission systems, the collected operating parameters include the rotor reference frequency and reference amplitude during normal operation, the current rotor vibration frequency, amplitude and phase, and the phase difference between two preset measuring points of the current rotor.

[0016] According to a method for diagnosing deep peak load regulation faults of a thermal power unit provided by the present invention, the operation status evaluation models established based on different functional systems respectively include: a steam system operation status evaluation model, a combustion system operation status evaluation model, a ventilation system operation status evaluation model, and a mechanical transmission system operation status evaluation model;

[0017] The steam system operation status assessment model is:

[0018]

[0019] Among them, F sf is the rationality evaluation value of steam flow, ρ1 is the steam density at the steam inlet, v1 is the steam velocity at the steam inlet, A1 is the cross-sectional area of ​​the inlet pipe, ρact is the steam density at the preset measuring point, v act is the steam velocity at the measuring point, A act is the cross-sectional area of ​​the pipe at the measuring point;

[0020] Among them, E s is the steam energy conversion efficiency evaluation value, The theoretical heat released by fuel combustion is calculated based on the known theoretical calorific value of the fuel and the fuel mass flow rate; m s is the mass flow rate of steam, h(T in , P in ) is based on the steam inlet temperature T in 、Pressure P in Determine the enthalpy, h(T out , P out ) is based on the steam outlet temperature T out 、Pressure P out Determined enthalpy values; the enthalpy values ​​are all determined by looking up in the standard enthalpy value table.

[0021] According to a method for diagnosing deep peak load regulation faults of a thermal power unit provided by the present invention, the combustion system operation status evaluation model is:

[0022]

[0023] Among them, C comb is the combustion completeness evaluation value, x and y are the number of carbon atoms and hydrogen atoms in the fuel raw materials, that is, the fuel C x H y ; is the fuel flow rate entering the combustion chamber, is the air flow rate entering the combustion chamber; I comb is a combustion flame index determined based on the current flame image; the combustion flame index I comb Based on the analysis of the hue, saturation and brightness characteristics of the flame image, the combustion flame index I is determined by normalization and summary calculation. comb Value, and I comb The value is between 0 and 1, the closer to 1, the higher the degree of complete combustion, and the closer to 0, the higher the degree of incomplete combustion;

[0024] V comb is the temperature uniformity evaluation value in the combustion chamber; σ temp is the temperature standard deviation, and in are the temperatures of the three preset measuring points in the combustion chamber, is the average temperature of the measuring point,

[0025] According to a method for diagnosing deep peak load regulation faults of a thermal power unit provided by the present invention, the ventilation system operation status evaluation model is:

[0026]

[0027] Among them, E fan is the evaluation value of fan working efficiency, is the air pressure at the fan, is the air flow at the fan, is the actual input power of the fan, is the rated efficiency of the fan;

[0028] P pipe is the ventilation duct resistance evaluation value, ΔP act is the pressure difference between the inlet and outlet of the ventilation duct, f is the friction coefficient of the ventilation duct, L is the length of the ventilation duct, D is the diameter of the ventilation duct, ρ act is the air density in the ventilation duct, V act is the air velocity in the ventilation duct.

[0029] According to a method for diagnosing deep peak load regulation faults of a thermal power unit provided by the present invention, the operating state evaluation model of the mechanical transmission system is:

[0030]

[0031] Among them, V rotor is the rotor vibration state evaluation value, f rated is the rotor reference frequency, f vib is the current rotor vibration frequency, A rated is the rotor reference amplitude, A vib is the current rotor amplitude, is the current rotor phase conversion value, the phase conversion value is a value that maps the phase angle to a value between 0 and 1; k1, k2, k3 are vibration weight coefficients, and k1+k2+k3=1, which is determined based on fault simulation experiments;

[0032] A shaft is the shaft alignment status assessment value, The phase difference between the two measuring points preset for the current rotor.

[0033] According to a method for diagnosing deep peak load regulation faults of a thermal power unit provided by the present invention, the process of analyzing the coupling relationship between different evaluation results to extract a comprehensive fault evaluation value comprises:

[0034] Based on the evaluation results of each model output, the steam system evaluation vector is established. Combustion System Assessment Vector Ventilation System Assessment Vector Mechanical transmission system evaluation vector

[0035] Constructing a comprehensive evaluation function

[0036]

[0037] Among them, ω1, ω2, ω3, and ω4 are comprehensive evaluation weights, which are used to reflect the coupling relationship between different evaluation results, and ω1+ω2+ω3+ω4=1, which is determined by fitting based on historical data;

[0038] Output comprehensive fault evaluation value The larger the value is, the more stable the operation of the unit is during the peak load regulation process.

[0039] According to a method for diagnosing deep peak load regulation faults of a thermal power unit provided by the present invention, the method of diagnosing the fault state based on the comprehensive fault evaluation value and each evaluation result and providing fault location suggestions includes:

[0040] Preset the comprehensive fault threshold value, and determine the fault status of the current unit during the peak load regulation process by comparing the comprehensive fault assessment value with the comprehensive fault threshold value;

[0041] The obtained fault status and each evaluation result are visualized on the terminal device as a fault location suggestion for the administrator.

[0042] Compared with the prior art, the beneficial effects of this application are:

[0043] This application establishes a detailed operating status evaluation model for each system by comprehensively collecting and classifying the operating parameters of each functional system (steam system, combustion system, ventilation system, mechanical transmission system) of the thermal power unit. Compared with the existing methods based on single parameter threshold judgment or lack of in-depth analysis of subsystems, it can diagnose the fault type more accurately and provide managers with the specific subsystem and location where the fault occurs;

[0044] By constructing multiple evaluation values ​​to comprehensively measure the operating status of each subsystem, the performance of the unit is fully reflected from different angles. By fully considering the characteristics of the unit operating parameters deviating from the traditional design conditions under deep peak load conditions, the problem of high misjudgment rate and difficulty in accurately judging the unit status under such conditions in the existing technology is solved.

[0045] Fault diagnosis and comprehensive status assessment can help to promptly identify potential fault hazards and take targeted measures to reduce equipment wear, improve efficiency, and reduce pollutant emissions, thereby ensuring the safe and stable operation of the unit during deep peak regulation, extending the service life of the equipment, and improving the economic efficiency of the unit operation.

[0046] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0047] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0049] Figure 1 The present invention provides a flowchart of a method for diagnosing deep peak load failures of a thermal power unit. DETAILED DESCRIPTION

[0050] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0051] Embodiment 1:

[0052] The embodiment of the present invention provides a method for diagnosing deep peak load failure of a thermal power unit. Figure 1 ,include:

[0053] Step 1: collect various operating parameters of thermal power units during deep peak regulation in real time and classify them according to their functional systems; the functional systems include steam system, combustion system, ventilation system and mechanical transmission system;

[0054] Step 2: Establish operation status evaluation models based on different functional systems;

[0055] Step 3: Substitute the collected operating parameters into the operating status assessment model for calculation and analysis, and analyze the coupling relationship between different assessment results to extract the comprehensive fault assessment value;

[0056] Step 4: diagnose the fault status based on the comprehensive fault evaluation value and each evaluation result, and provide fault location suggestions.

[0057] The principles and beneficial effects of this embodiment are as follows: various operating parameters of the thermal power unit during the deep peak regulation process are collected in real time, and are classified according to functional systems, so that the parameter ranges of different systems are clarified, providing a basis for subsequent analysis; operating status evaluation models are established for different functional systems respectively, so as to evaluate the operating status of each system in a more targeted manner; the collected parameters are substituted into the model for calculation and analysis, and the coupling relationship between different evaluation results is considered, so as to extract a comprehensive fault evaluation value, which comprehensively reflects the overall operating status of the thermal power unit; fault diagnosis is performed based on the comprehensive fault evaluation value and each evaluation result, and fault location suggestions are provided, so as to achieve accurate judgment and rapid location of the fault.

[0058] In order to further optimize the above embodiment, the process of collecting various operating parameters of the thermal power unit in the deep peak regulation process in real time and classifying them according to the functional system to which they belong includes:

[0059] For steam systems, the collected operating parameters include steam density, steam flow rate, cross-sectional area of ​​the inlet pipe at the steam inlet, steam density, steam flow rate, cross-sectional area of ​​the pipe at the preset measuring point, theoretical heat released by fuel combustion, steam inlet temperature, pressure, steam outlet temperature, pressure, and steam mass flow rate;

[0060] For the combustion system, the collected operating parameters include the type of fuel raw materials, the fuel flow rate and air flow rate entering the combustion chamber, the temperature of three preset measuring points in the combustion chamber, and the current flame image;

[0061] For ventilation systems, the collected operating parameters include air pressure, air flow, actual input power and rated efficiency of the fan at the fan, length and diameter of the ventilation duct, air density and flow rate in the ventilation duct, pressure difference between the inlet and outlet of the ventilation duct, and friction coefficient of the ventilation duct;

[0062] For mechanical transmission systems, the collected operating parameters include the rotor reference frequency and reference amplitude during normal operation, the current rotor vibration frequency, amplitude and phase, and the phase difference between two preset measuring points of the current rotor.

[0063] It should be noted that currently flame images are captured using specialized industrial cameras. The cameras should have appropriate resolution (e.g. 1024×768 pixels or higher), frame rate (generally no less than 25 frames per second), and a spectral response range that can accurately capture the flame color. The camera should be installed in a position that can clearly capture the entire flame area and avoid interference from external light; for example, install the camera near the observation port of the combustion furnace, protect the camera lens with a high-temperature resistant protective cover, and ensure that there are no obstacles between the lens and the flame that block the line of sight;

[0064] The principles for collecting other parameters are existing technical means and will not be elaborated on in detail.

[0065] In order to further optimize the above embodiment, the operation status evaluation models established based on different functional systems include: a steam system operation status evaluation model, a combustion system operation status evaluation model, a ventilation system operation status evaluation model, and a mechanical transmission system operation status evaluation model;

[0066] The steam system operation status assessment model is:

[0067]

[0068] Among them, F sf is the rationality evaluation value of steam flow, ρ1 is the steam density at the steam inlet, v1 is the steam velocity at the steam inlet, A1 is the cross-sectional area of ​​the inlet pipe, ρ act is the steam density at the preset measuring point, v act is the steam velocity at the measuring point, A act is the cross-sectional area of ​​the pipe at the measuring point;

[0069] Among them, E s is the steam energy conversion efficiency evaluation value, The theoretical heat released by fuel combustion is calculated based on the known theoretical calorific value of the fuel and the fuel mass flow rate; m s is the mass flow rate of steam, h(T in , P in ) is based on the steam inlet temperature T in 、Pressure P in Determine the enthalpy, h(T out , P out ) is based on the steam outlet temperature T out 、Pressure P out Determine the enthalpy value; the enthalpy value is determined by looking up the standard enthalpy value table.

[0070] It should be noted that the steam flow rationality assessment value reflects the closeness between the actual measured steam flow and the theoretical steam flow calculated based on the steam inlet parameters, and is used to determine whether the flow in the steam system is within a reasonable range. The greater the deviation, the more likely it is that the steam flow is abnormal.

[0071] The steam energy conversion efficiency assessment value reflects the proportional relationship between the actual heat absorbed by steam and the theoretical heat released by fuel combustion. It is used to evaluate the efficiency of energy conversion from fuel to steam in the steam system. A low value may mean a large energy loss or a problem in the conversion process.

[0072] In order to further optimize the above embodiment, the combustion system operation status evaluation model is:

[0073]

[0074] Among them, C comb is the combustion completeness evaluation value, x and y are the number of carbon atoms and hydrogen atoms in the fuel raw materials, that is, the fuel C x H y ; is the fuel flow rate entering the combustion chamber, is the air flow rate entering the combustion chamber; I comb is the combustion flame index determined based on the current flame image; combustion flame index I comb Based on the analysis of the hue, saturation and brightness characteristics of the flame image, the combustion flame index I is determined by normalization and summary calculation. comb Value, and I comb The value is between 0 and 1, the closer to 1, the higher the degree of complete combustion, and the closer to 0, the higher the degree of incomplete combustion;

[0075] V comb is the evaluation value of temperature uniformity in the combustion chamber; σ temp is the temperature standard deviation, and in are the temperatures of the three preset measuring points in the combustion chamber, is the average temperature of the measuring point,

[0076] It should be noted that the combustion completeness evaluation value combines the fuel-air ratio and flame combustion characteristics, and is used to measure the completeness of fuel combustion in the combustion chamber. A value close to 1 indicates high combustion completeness, and a value close to 0 indicates high incomplete combustion.

[0077] The temperature uniformity assessment value in the combustion chamber reflects the uniformity of the temperature distribution in the combustion chamber by calculating the inverse of the standard deviation of the temperature of the preset measuring points in the combustion chamber. The larger the value, the more uniform the temperature, and the smaller the value, the higher the degree of temperature non-uniformity, which may affect the combustion efficiency and equipment safety.

[0078] For combustion flame index I comb , the collected flame image in RGB (red, green, blue) color space is converted into a color space more suitable for color analysis, such as HSV (hue, saturation, brightness) color space; in RGB color space, the change of flame color may be affected by factors such as light intensity, while HSV color space separates color information and brightness information, which is more conducive to accurately analyzing flame color characteristics; then feature analysis is performed, including:

[0079] Hue feature statistics: In HSV images, the hue value can reflect the color characteristics of the flame; for a fully burned flame, its hue is mainly concentrated in the orange to yellow range (about 30 degrees to 60 degrees); count the number of pixels with different hue values ​​in the flame image, and calculate the proportion of pixels in the orange to yellow hue range to the total number of pixels;

[0080] Saturation feature analysis: The saturation of a completely burned flame is relatively high, because the high temperature and strong chemical reaction generated by the combustion will make the flame color more vivid; calculate the average saturation of all pixels in the flame image, as well as the standard deviation of the saturation; if the average saturation is low and the standard deviation is large, it may indicate that the flame color is uneven and the combustion is incomplete;

[0081] Brightness feature evaluation: The brightness of a flame is related to the intensity of combustion and the fuel supply. During normal combustion, the brightness of the flame center is high and gradually decreases at the edge. Calculate the maximum, minimum, and average brightness in the flame image, as well as the gradient change of the brightness (for example, by calculating the grayscale gradient of the image). If the overall brightness of the flame is low or the brightness distribution is abnormal (for example, the brightness of the center area is low and the brightness of the edge area is high), it may indicate a problem with the combustion.

[0082] Combining the above color features, the combustion completeness index is constructed. First, the hue ratio is normalized, and then the features are fused in a weighted manner, so that I comb The value of is between 0 and 1, where a value close to 1 indicates high combustion completeness and a value close to 0 indicates high combustion incompleteness.

[0083] In order to further optimize the above embodiment, the ventilation system operation status evaluation model is:

[0084]

[0085] Among them, E fan is the evaluation value of fan working efficiency, is the air pressure at the fan, is the air flow at the fan, is the actual input power of the fan, is the rated efficiency of the fan;

[0086] P pipe is the ventilation duct resistance evaluation value, ΔP act is the pressure difference between the inlet and outlet of the ventilation duct, f is the friction coefficient of the ventilation duct, L is the length of the ventilation duct, D is the diameter of the ventilation duct, ρ act is the air density in the ventilation duct, V act is the air velocity in the ventilation duct.

[0087] It should be noted that the fan working efficiency evaluation value represents the ratio of the product of the pressure and flow generated by the fan during actual operation to the actual input power relative to the rated efficiency of the fan. It is used to evaluate the working efficiency of the fan in the ventilation system. A large deviation from 1 may indicate a decrease in fan performance or abnormal operation.

[0088] The ventilation duct resistance assessment value is the ratio of the actual pressure difference between the inlet and outlet of the ventilation duct to the theoretical pressure difference calculated based on the duct parameters and air flow conditions. It is used to reflect the relationship between the actual resistance and theoretical resistance in the ventilation duct. A value greater than 1 may mean that the duct has problems such as blockage or deformation that increase resistance.

[0089] In order to further optimize the above embodiment, the mechanical transmission system operation status evaluation model is:

[0090]

[0091] Among them, V rotor is the rotor vibration state evaluation value, f rated is the rotor reference frequency, f vib is the current rotor vibration frequency, A rated is the rotor reference amplitude, A vib is the current rotor amplitude, is the current rotor phase conversion value, phase conversion value is a value that maps the phase angle to a value between 0 and 1; k1, k2, k3 are vibration weight coefficients, and k1+k2+k3=1, which is determined based on fault simulation experiments;

[0092] A shaft is the shaft alignment status assessment value, The phase difference between the two measuring points preset for the current rotor.

[0093] It should be noted that the rotor vibration state evaluation value comprehensively considers the current vibration frequency and amplitude of the rotor, the ratio of the normal reference value, and the phase conversion value, and is obtained by weighted summation. It is used to evaluate the vibration state of the rotor in the mechanical transmission system. Abnormal values ​​may indicate that the rotor is unbalanced, misaligned, or has other mechanical faults.

[0094] The shaft alignment status evaluation value is calculated based on the phase difference between two preset measuring points of the rotor, and is used to reflect the alignment of the shaft in the mechanical transmission system. A value close to 1 indicates that the shaft alignment is good, and a value close to 0 indicates that the degree of misalignment of the shaft is higher.

[0095] The conversion of the phase angle of rotor vibration into a numerical value is based on normalizing and mapping the angle within a reasonable numerical range so that it can participate in the evaluation value calculation at the same scale as other parameters such as frequency and amplitude. The 360-degree phase angle range from 0 to 0 degrees can be linearly mapped to a numerical range between 0 and 1, so that the phase information can reflect the characteristics of the rotor vibration state in a relatively quantitative manner, thereby comprehensively considering the influence of the phase factor when evaluating the overall vibration of the rotor;

[0096] The vibration weight coefficient can be obtained by collecting and analyzing a large amount of actual unit operation data, observing the differences in the degree of influence of frequency, amplitude and phase changes on the rotor vibration state under different fault conditions, and determining the weight coefficient based on these statistical results. Or, a fault simulation experiment can be conducted in a laboratory environment or during the shutdown and overhaul of the actual unit, artificially creating common fault conditions such as shaft misalignment and imbalance, measuring the frequency, amplitude and phase changes of the rotor vibration under different fault levels, and recording the corresponding vibration state evaluation values. Then, by adjusting the values ​​of k1, k2, and k3, the evaluation value can accurately reflect the actual fault state, thereby determining the appropriate weight coefficient.

[0097] In order to further optimize the above embodiment, the process of analyzing the coupling relationship between different evaluation results to extract the comprehensive fault evaluation value includes:

[0098] Based on the evaluation results of each model output, the steam system evaluation vector is established. Combustion System Assessment Vector Ventilation System Assessment Vector Mechanical transmission system evaluation vector

[0099] Constructing a comprehensive evaluation function

[0100]

[0101] Among them, ω1, ω2, ω3, and ω4 are comprehensive evaluation weights, which are used to reflect the coupling relationship between different evaluation results, and ω1+ω2+ω3+ω4=1, which is determined by fitting based on historical data;

[0102] Output comprehensive fault evaluation value The larger the value is, the more stable the operation of the unit is during the peak load regulation process.

[0103] It should be noted that the comprehensive evaluation weight reflects the coupling relationship between different evaluation results, and its value can be determined by: collecting historical data of long-term operation of thermal power units under different depth peak-shaving conditions, including the operating parameters of each subsystem (steam system, combustion system, ventilation system, mechanical transmission system) and the corresponding actual operating status of the unit (normal operation, various fault conditions, etc.); for different operating conditions, analyzing the correlation between the evaluation results of each subsystem (such as the rationality evaluation value of the steam flow of the steam system, the combustion completeness evaluation value of the combustion system, etc.) and the degree of influence on the overall status of the unit; for example, when a unit fails and it is determined that it is caused by the combined action of the steam system and the combustion system, statistics are collected in this case. The changing rules of the steam system evaluation value and the combustion system evaluation value and their relationship with the severity of the fault are analyzed; based on the statistical results, the contribution ratio of each subsystem evaluation result to the overall fault judgment under different operating conditions is calculated, and this is used as the basis for determining the weight coefficient; for example, if in a certain type of fault, the impact of the change in the steam system evaluation value on the fault judgment accounts for 40%, the combustion system accounts for 30%, the ventilation system accounts for 20%, and the mechanical transmission system accounts for 10%, then the weight coefficients are preliminarily determined to be 0.4, 0.3, 0.2, and 0.1; then, through the analysis and verification of multiple different fault cases, these weight coefficients are optimized and adjusted so that they can more accurately reflect the coupling relationship of each subsystem in the overall operation of the unit;

[0104] Alternatively, in the laboratory or during the actual unit shutdown and maintenance, conduct fault simulation experiments under various deep peak-shaving conditions; artificially set up faults of different types and degrees, such as steam system pipeline leakage, combustion system injector nozzle blockage, ventilation system fan failure, mechanical transmission system shaft misalignment, etc.;

[0105] During the fault simulation process, the operating parameters of each subsystem are accurately measured, the corresponding evaluation values ​​are calculated, and the actual response and fault performance of the unit are recorded;

[0106] By adjusting the weight coefficient, the calculated comprehensive fault assessment value is compared and verified with the actual fault situation; the weight coefficient is continuously optimized so that the comprehensive evaluation function can accurately predict and diagnose the simulated fault, ensuring that the weight coefficient can truly reflect the coupling relationship between each subsystem during the fault occurrence and propagation process; for example, when simulating a steam system pipeline leakage fault, observe whether the comprehensive fault assessment value under different weight coefficient combinations can accurately indicate the fault type and severity, and modify the weight coefficient according to the verification results until a satisfactory diagnostic effect is achieved.

[0107] In order to further optimize the above embodiment, the fault status is diagnosed based on the comprehensive fault evaluation value and each evaluation result, and the fault location suggestion is provided, including:

[0108] Preset the comprehensive fault threshold value, and determine the fault status of the current unit during the peak load regulation process by comparing the comprehensive fault assessment value with the comprehensive fault threshold value;

[0109] The obtained fault status and each evaluation result are visualized on the terminal device as a fault location suggestion for the administrator.

[0110] It should be noted that the comprehensive fault threshold needs to be determined through fault simulation experiments under various deep peak-shaving conditions in the laboratory or during the actual unit shutdown and maintenance, and different types and degrees of faults need to be artificially set, such as various steam system faults (abnormal flow, low energy conversion efficiency, pipeline leakage, etc.), combustion system faults (incomplete combustion, unstable flame, etc.), ventilation system faults (fan failure, pipeline blockage, etc.) and mechanical transmission system faults (shaft misalignment, rotor imbalance, etc.).

[0111] During the fault simulation process, the operating parameters of each subsystem are accurately measured, the corresponding evaluation values ​​and comprehensive fault evaluation values ​​are calculated, and the actual operating performance of the unit under different fault degrees is recorded.

[0112] According to the results of the fault simulation experiment, the changing rules of the comprehensive fault assessment value during the occurrence and development of different faults are determined. For example, as the leakage degree of the steam system pipeline increases, the comprehensive fault assessment value gradually decreases. When the leakage reaches a certain level, the assessment value will be lower than a certain value. According to these rules, combined with the fault degree that the unit can tolerate and the safe operation requirements, the corresponding thresholds are set. For example, when the leakage degree reaches a level that may affect the safe operation of the unit but has not yet caused serious consequences, the comprehensive fault assessment value can be used as the warning threshold of the fault; when the leakage is so serious that the unit must be shut down for maintenance, the assessment value can be used as the fault shutdown threshold.

[0113] Comprehensively consider and coordinate the thresholds obtained from various fault simulation experiments to avoid conflicts between different fault thresholds and form a complete and reasonable comprehensive fault threshold system;

[0114] When providing fault location suggestions, interactive functions can be added to the visual interface to facilitate administrators to further analyze the fault situation. For example, administrators can click on graphic elements (such as bar graphs, trend graphs, etc.) to view detailed data information, including historical curves of data, statistical analysis results, etc. For suspected fault points, administrators can obtain relevant help information and processing suggestions by hovering or clicking the mouse. These suggestions can be generated based on a pre-set expert knowledge base or fault handling experience rules. In addition, data filtering and comparison functions can be set. Administrators can filter data according to time range, system type and other conditions, and compare the differences in operating status of different time periods or different units, which will help to discover potential problems and trends. For example, administrators can compare the changes in the evaluation values ​​of each system of the same unit under different depths of peak load regulation, analyze the impact of load changes on unit operation, and take measures in advance to prevent faults.

[0115] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for diagnosing deep peak load failure of a thermal power unit, characterized in that: include: Step 1: collect various operating parameters of thermal power units during deep peak regulation in real time and classify them according to their functional systems; the functional systems include steam system, combustion system, ventilation system and mechanical transmission system; Step 2: Establish operation status evaluation models based on different functional systems; Step 3: Substituting the collected various operating parameters into the operating status evaluation model for calculation and analysis, and analyzing the coupling relationship between different evaluation results to extract a comprehensive fault evaluation value; Step 4: diagnose the fault status based on the comprehensive fault evaluation value and each evaluation result, and provide fault location suggestions.

2. A method for diagnosing deep peak load failure of a thermal power unit according to claim 1, characterized in that: The process of real-time collection of various operating parameters of thermal power units during deep peak regulation and classification according to their respective functional systems includes: For the steam system, the collected operating parameters include steam density, steam flow rate, cross-sectional area of ​​the inlet pipe at the steam inlet, steam density, steam flow rate, cross-sectional area of ​​the pipe at the preset measuring point, theoretical heat released by fuel combustion, steam inlet temperature, pressure, steam outlet temperature, pressure, and steam mass flow rate; For the combustion system, the collected operating parameters include the type of fuel raw material, the fuel flow rate and air flow rate entering the combustion chamber, the temperatures of three preset measuring points in the combustion chamber, and the current flame image; For the ventilation system, the collected operating parameters include the air pressure at the fan, the air flow, the actual input power of the fan and the rated efficiency of the fan, the length and diameter of the ventilation duct, the air density and flow rate in the ventilation duct, the inlet and outlet pressure difference of the ventilation duct and the friction coefficient of the ventilation duct; For mechanical transmission systems, the collected operating parameters include the rotor reference frequency and reference amplitude during normal operation, the current rotor vibration frequency, amplitude and phase, and the phase difference between two preset measuring points of the current rotor.

3. A method for diagnosing deep peak load failure of a thermal power unit according to claim 2, characterized in that: The operation status assessment models established based on different functional systems include: a steam system operation status assessment model, a combustion system operation status assessment model, a ventilation system operation status assessment model, and a mechanical transmission system operation status assessment model; The steam system operation status assessment model is: Among them, F sf is the rationality evaluation value of steam flow, ρ1 is the steam density at the steam inlet, v1 is the steam velocity at the steam inlet, A1 is the cross-sectional area of ​​the inlet pipe, ρac t is the steam density at the preset measuring point, v act is the steam velocity at the measuring point, A act is the cross-sectional area of ​​the pipe at the measuring point; Among them, E s is the steam energy conversion efficiency evaluation value, The theoretical heat released by fuel combustion is calculated based on the known theoretical calorific value of the fuel and the fuel mass flow rate; m s is the mass flow rate of steam, h(T in , P in ) is based on the steam inlet temperature T in 、Pressure P in Determine the enthalpy, h(T out , P out ) is based on the steam outlet temperature T out 、Pressure P out Determined enthalpy values; the enthalpy values ​​are all determined by looking up in the standard enthalpy value table.

4. A method for diagnosing deep peak load failure of a thermal power unit according to claim 3, characterized in that: The combustion system operation status evaluation model is: Among them, C comb is the combustion completeness evaluation value, x and y are the number of carbon atoms and hydrogen atoms in the fuel raw materials, that is, the fuel C x H y ; is the fuel flow rate entering the combustion chamber, is the air flow rate entering the combustion chamber; I comb is a combustion flame index determined based on the current flame image; the combustion flame index I comb Based on the analysis of the hue, saturation and brightness characteristics of the flame image, the combustion flame index I is determined by normalization and summary calculation. comb Value, and I comb The value is between 0 and 1, the closer to 1, the higher the degree of complete combustion, and the closer to 0, the higher the degree of incomplete combustion; V comb is the evaluation value of temperature uniformity in the combustion chamber; σ temp is the temperature standard deviation, and in are the temperatures of the three preset measuring points in the combustion chamber, is the average temperature of the measuring point, 5. A method for diagnosing deep peak load failure of a thermal power unit according to claim 4, characterized in that: The ventilation system operation status assessment model is: Among them, E fan is the evaluation value of fan working efficiency, is the air pressure at the fan, is the air flow at the fan, is the actual input power of the fan, is the rated efficiency of the fan; P pipe is the ventilation duct resistance evaluation value, ΔP act is the pressure difference between the inlet and outlet of the ventilation duct, f is the friction coefficient of the ventilation duct, L is the length of the ventilation duct, D is the diameter of the ventilation duct, ρ act is the air density in the ventilation duct, V act is the air velocity in the ventilation duct.

6. A method for diagnosing deep peak load failure of a thermal power unit according to claim 5, characterized in that: The mechanical transmission system operation status assessment model is: Among them, V rotor is the rotor vibration state evaluation value, f rated is the rotor reference frequency, f vib is the current rotor vibration frequency, A rated is the rotor reference amplitude, A vib is the current rotor amplitude, is the current rotor phase conversion value, the phase conversion value is a value that maps the phase angle to a value between 0 and 1; k1, k2, k3 are vibration weight coefficients, and k1+k2+k3=1, which is determined based on fault simulation experiments; A shaft is the shaft alignment status assessment value, The phase difference between the two measuring points preset for the current rotor.

7. A method for diagnosing deep peak load failure of a thermal power unit according to claim 6, characterized in that: The process of analyzing the coupling relationship between different evaluation results to extract the comprehensive fault evaluation value includes: Based on the evaluation results of each model output, the steam system evaluation vector is established. Combustion System Assessment Vector Ventilation System Assessment Vector Mechanical transmission system evaluation vector Constructing a comprehensive evaluation function Among them, ω1, ω2, ω3, and ω4 are comprehensive evaluation weights, which are used to reflect the coupling relationship between different evaluation results, and ω1+ω2+ω3+ω4=1, which is determined by fitting based on historical data; Output comprehensive fault evaluation value The larger the value is, the more stable the operation of the unit is during the peak load regulation process.

8. A method for diagnosing deep peak load failure of a thermal power unit according to claim 7, characterized in that: The diagnosing the fault status based on the comprehensive fault evaluation value and each evaluation result and providing fault location suggestions include: Preset the comprehensive fault threshold value, and determine the fault status of the current unit during the peak load regulation process by comparing the comprehensive fault assessment value with the comprehensive fault threshold value; The obtained fault status and each evaluation result are visualized on the terminal device as a fault location suggestion for the administrator.

Images