Identification and analysis system and method based on abnormal conditions of thermal power plant

Abstract

The invention discloses an identification analysis system and method based on abnormal conditions of a thermal power plant, and relates to the technical field of abnormal condition analysis of the thermal power plant. Whether early warning is carried out or not is judged by calculating the total entropy speed increase rate and comparing the total entropy speed increase rate with a threshold value, and the risk level is evaluated through a comprehensive formula after critical entropy change parameters are obtained; the method comprises the following steps: firstly, performing a coking rate abnormity type, a coal ash adhesion abnormity type or a compound type intervention operation according to grades, finally verifying a measure effect through an effectiveness formula, constructing a multi-source data fusion monitoring system, realizing accurate prediction and risk quantification of boiler coking by means of a thermodynamic entropy increase theory, solving the hysteresis quality of traditional single index monitoring, and improving the risk of boiler coking. The layered intervention mechanism based on the risk level improves the pertinence of anti-coking measures, avoids blind operation, forms a'monitoring-execution-optimization 'closed loop through efficiency evaluation, dynamically verifies the intervention effect, and effectively reduces the safety risk and economic loss caused by coking.

Description

Technical Field

[0001] The present invention relates to the technical field of abnormal condition analysis of thermal power plants, and in particular to an identification and analysis system and method based on abnormal conditions of thermal power plants. Background Art

[0002] Coking in thermal power plant boilers can easily lead to safety risks and economic losses. Traditional monitoring relies mostly on a single indicator, which is lagging, and anti-coking measures are not targeted enough and lack effectiveness evaluation. With the increasing demand for intelligent management and control of thermal power plants, there is an urgent need for a system that integrates multi-source data, accurately assesses risks and forms a closed-loop management and control system. A system and method for identifying and analyzing abnormal conditions in thermal power plants has emerged.

[0003] The existing identification and analysis systems and methods based on abnormal conditions of thermal power plants have the following technical problems: 1. The existing or traditional identification and analysis systems for abnormal conditions of thermal power plants often rely on a single or a few monitoring parameters to judge the risk of coking, and lack quantitative analysis of the essential characteristics of energy dissipation in the combustion process. For example, the traditional method only monitors the surface temperature of the coking layer through a temperature sensor, but does not combine parameters such as the ash thermal conductivity coefficient and the particle collision frequency to calculate the entropy growth rate, resulting in the inability to accurately identify the combustion energy dissipation anomaly caused by ash adhesion and coking. It often misses the situation of "the temperature has not increased significantly but the coking has continued to develop", and the accuracy and reliability of risk identification are low.

[0004] 2. Traditional abnormal condition identification and analysis systems for thermal power plants usually use fixed thresholds or simple empirical formulas for risk assessment, and lack scientific setting and dynamic calibration of core parameters such as the critical entropy growth rate and weight factors. For example, the critical entropy growth rate is roughly set based on historical data under a single operating condition, and the physical mechanism of coking phase change is not verified through thermodynamic experiments. As a result, the threshold cannot adapt to complex scenarios such as changes in fuel type and boiler load fluctuations. The allocation of weight factors mostly relies on subjective assignment based on expert experience, and the actual contribution of each indicator is not determined through quantitative methods such as fitting historical coking data or entropy weight method, making the comprehensive risk level assessment superficial.

[0005] 3. Existing abnormal condition identification and analysis systems for thermal power plants generally lack a closed-loop management mechanism of "intervention-assessment-optimization". Intervention operations are mostly preset fixed plans that are not dynamically adjusted according to the real-time risk level, and the effectiveness of the measures is not quantitatively evaluated. For example, traditional soot blowing strategies are executed according to a fixed cycle, and the same blowing frequency is used regardless of the coking risk. This will lead to insufficient blowing force under high-risk conditions and excessive blowing under low-risk conditions, causing wear of the heated surface. Operations such as fuel mixing or additive injection often lack tracking of key indicators such as "whether the total entropy growth rate has decreased" and "whether the coal ash adhesion has improved", making it impossible to verify the effectiveness of the measures. In addition, traditional systems have not established a side effect assessment model, and new problems may arise due to the blind implementation of anti-coking measures, such as excessive blending of low-adhesion fuels leading to reduced combustion stability, which makes coking prevention and control fall into an inefficient "experience-driven" cycle and difficult to adapt to the complex and changeable operating conditions of thermal power plants. Summary of the Invention

[0006] The purpose of the present invention is to provide a system and method for identifying and analyzing abnormal conditions in a thermal power plant, which solves the problems existing in the background technology.

[0007] In order to solve the above technical problems, the present invention adopts the following technical solutions: The present invention provides an identification and analysis system based on abnormal conditions of thermal power plants, including: a designated boiler coking prediction module, which is used to collect early warning data of the combustion process of a designated boiler corresponding to a designated thermal power plant within a set time period, and calculate the total entropy growth rate of the combustion process corresponding to the designated boiler within the set time period, and then determine whether to send an early warning signal.

[0008] The critical phase change prediction module is used to obtain the critical entropy change parameters of the combustion process of the specified boiler within a set time period when an early warning signal is received, and then calculate the comprehensive risk level corresponding to the received early warning signal.

[0009] The anti-stress measures execution module is used to execute preset intervention operations according to the comprehensive risk level corresponding to the early warning signal.

[0010] The effectiveness evaluation module is used to evaluate the effectiveness of executing the preset intervention operations.

[0011] In a second aspect, the present invention provides a method for identifying and analyzing abnormal conditions in a thermal power plant, comprising:

[0012] Step 1: Predict coking of designated boilers: Collect early warning data of the combustion process of the designated boiler of the designated thermal power plant within the set time period, and calculate the total entropy growth rate of the combustion process of the designated boiler within the set time period to determine whether to send an early warning signal.

[0013] Step 2: Critical phase change prediction: When an early warning signal is received, the critical entropy change parameters of the combustion process of the specified boiler within the set time period are obtained, and then the comprehensive risk level corresponding to the received early warning signal is calculated.

[0014] Step 3: Execution of anti-stress measures: Execute preset intervention operations based on the comprehensive risk level corresponding to the early warning signal.

[0015] Step 4: Effectiveness evaluation: Evaluate the effectiveness of implementing the preset intervention operations.

[0016] The beneficial effects of the present invention are: 1. The identification and analysis system and method based on abnormal conditions of thermal power plants provided by the embodiments of the present invention, through high-temperature resistant sensor networks, laser particle size analyzers and other multi-dimensional monitoring equipment, combined with three-dimensional modeling of boiler structure and optimized layout of monitoring points, are conducive to overcoming the limitations of traditional single-point monitoring and realizing three-dimensional perception of the temperature field distribution of the coking layer, particle movement trajectory, and ash physical properties. This multi-dimensional data collection method is conducive to early warning of coking hazards 3-5 days in advance, which has significant advantages over traditional single temperature threshold alarms.

[0017] 2. In the process of acquiring critical entropy change parameters and calculating risk levels, the embodiment of the present invention systematically and comprehensively integrates multiple key parameters such as the total entropy growth rate, the number of fly ash particles, and the boiler load rate. The critical entropy growth rate is determined through historical data fitting and thermodynamic experiments, and the state of fly ash particles is monitored using professional instruments. The boiler load information is obtained in real time from the power plant management platform. The comprehensive risk level assessment formula is used, combined with scientific weight distribution to calculate the risk level, and the fuzzy risk situation is converted into a clear and quantitative grade system. It comprehensively considers various influencing factors such as thermodynamic changes, particle physical properties, and operating conditions, providing a scientific and accurate risk basis for subsequent decision-making, making the risk assessment more comprehensive and objective.

[0018] 3. In the process of executing anti-coking measures, the system of the embodiment of the present invention accurately identifies the risk types of abnormal coking rate, abnormal coal ash adhesion or combined risk according to the comprehensive risk level by comparing the evaluation thresholds such as the entropy growth rate ratio and the proportion of fly ash molten particles. For different risk types, the system automatically matches and executes pre-set intervention operations, such as adjusting the combustion air distribution, enhancing the soot blowing frequency or coordinating multiple measures. The intelligent identification and precise policy implementation mechanism changes the traditional blind "one-size-fits-all" approach of anti-coking operations and realizes "measures according to risks", which not only greatly improves the pertinence and effectiveness of anti-coking measures, but also effectively reduces resource waste and potential equipment damage, and improves the economy and safety of thermal power plant operation.

[0019] 4. In the performance evaluation process, the embodiment of the present invention scientifically judges the effectiveness of the intervention operation by calculating the effectiveness evaluation value and the comprehensive side effect evaluation value. Once it is found that the executed intervention operation does not meet the effectiveness requirements, the optimization mechanism is immediately activated to adjust and improve the preset intervention strategy, which helps the system dynamically adjust the anti-coking measures according to the actual operation results. Through continuous feedback and optimization, the system's overall handling capability for abnormal conditions in thermal power plants is continuously improved, ensuring the long-term, stable and efficient operation of thermal power plants, and promoting the development of thermal power plant operation and maintenance management towards intelligence and refinement. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 This is a schematic diagram of the system structure connection of the present invention.

[0022] Figure 2 Schematic diagram of the implementation steps of the present invention. DETAILED DESCRIPTION

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0024] See also Figure 1 As shown, the present invention provides an identification and analysis system based on abnormal conditions of thermal power plants, which includes: a designated boiler coking prediction module, a critical phase change prediction module, an anti-coking measure execution module, an efficiency evaluation module and a database.

[0025] The designated boiler coking prediction module is connected to the critical phase change prediction module and the database respectively. The critical phase change prediction module is connected to the anti-coking measure execution module. The anti-coking measure execution module is connected to the efficiency evaluation module and the database respectively.

[0026] The designated boiler coking prediction module is used to collect early warning data of the combustion process of the designated boiler in the set time period of the designated thermal power plant, and calculate the total entropy growth rate of the combustion process of the designated boiler in the set time period to determine whether to send an early warning signal.

[0027] In a specific embodiment, the early warning data of the combustion process of a designated boiler in a designated thermal power plant within a set time period is collected. The specific process is as follows: the early warning data includes the ash layer temperature, particle collision frequency, average mass of ash particles and combustion energy release rate of the coking layer. The structure of the designated boiler is obtained from the corresponding design drawing of the designated boiler. Then, each monitoring point is set inside the designated boiler, and the corresponding distance between each monitoring point is recorded. The temperature value corresponding to each monitoring point is obtained by monitoring with a high-temperature resistant sensor, which is recorded as T i , i is the number corresponding to each monitoring point, i = 1, 2, ..., n, n is a positive integer, and then the calculation formula is: Get the temperature gradient ΔT corresponding to the direction of the i-th monitoring point and the i-1-th monitoring point i , d i It is expressed as the distance between the i-th monitoring point and the i-1-th monitoring point, T i-1 is the temperature value corresponding to the i-1th monitoring point.

[0028] The particle collision frequency f corresponding to each monitoring point is calculated by combining the dust concentration meter with the flue gas flow rate i , the particle samples of each monitoring point are collected by online fly ash sampler, and then the particle size distribution is measured by laser particle size analyzer, and then the average mass of ash particles is calculated by combining with ash density. The fuel flow, fuel calorific value, and combustion efficiency of a specified boiler within a set time period are obtained from the management platform of a specified thermal power plant, and the combustion energy release rate η is then calculated.

[0029] It should be noted that when setting monitoring points inside a designated boiler, its structural divisions should be clarified first according to the boiler design drawings, such as the furnace, water-cooled wall, superheater tube bundle and other key areas prone to coking. Combined with the historical locations of frequent coking and fluid dynamic characteristics, the monitoring points should be arranged according to the principle of "layered distribution and key coverage". For example, for a 600-megawatt pulverized coal boiler, the furnace water-cooled wall area is divided into a layer every 2 meters in the height direction, and 8 high-temperature resistant sensors are evenly arranged in the circumferential direction on each layer. In the dense superheater tube bundle area, the tube bundle spacing is used as the basis, and a monitoring point is set for every 3 tube bundles to ensure that the distance between adjacent points does not exceed 1.5 meters.

[0030] It should also be noted that the calculation of particle collision frequency is based on dust concentration and flue gas flow rate as core parameters. For example, when the dust concentration at a monitoring point is 10,000 particles / m3 and the flue gas flow rate is 10 m / s, the calculation is based on the principle that "collision frequency is positively correlated with the square of concentration and flow rate". The built-in calibration formula is used to multiply the square of concentration by the flow rate and then multiply it by the calibration coefficient, that is, 10,000. 2×10×2×10-11=2000 times / second, where 2000 times / second is the particle collision frequency. The built-in calibration formula is an empirical calculation module that is pre-fitted by a designated thermal power plant using experimental data, similar to the pre-set "weight-to-electrical signal conversion formula" in an electronic scale.

[0031] It should also be noted that particle samples at the monitoring point are collected by an online fly ash sampler, and the volume proportion of particles of different particle sizes in the sample is measured using a laser particle size analyzer. For example, particles with a diameter of less than 10 microns account for 30%, 10-50 microns account for 60%, and particles above 50 microns account for 10%. Assuming that the particles are approximately spheres, the volume of a single particle diameter is calculated according to the spherical volume formula, and then multiplied by the ash density to obtain the mass of a single particle. Finally, the mass of the particles in each particle size range is weighted averaged according to the volume proportion to obtain the average mass of the ash particles.

[0032] It should also be noted that the theoretical total energy of complete fuel combustion is the combustion flow rate multiplied by the combustion calorific value, but the actual combustion efficiency is not 100%. Therefore, the actual effective energy released needs to be multiplied by the combustion efficiency. The combustion energy release rate is the effective energy per unit time, expressed in megawatts. The calculation formula is: (fuel flow rate * fuel calorific value * combustion efficiency) / 3600. The denominator 3600 is used to convert hours to seconds to obtain megawatt-level power. For example, if the coal flow rate is 200 tons / hour, the calorific value is 25 megajoules / ton, and the combustion efficiency is 92%, then the combustion energy release rate is: (200×25×0.92) / 3600, which is approximately equal to 12.78 megawatts.

[0033] In a specific embodiment, the total entropy growth rate corresponding to the combustion process of a specified boiler within a set time period is calculated as follows: the entropy growth rate calculation formula is: The total entropy growth rate dv corresponding to the combustion process of the specified boiler within the set time period is obtained, where k and g represent the preset ash thermal conductivity and the empirical coefficient obtained by fitting historical data, respectively. S i It is represented as the heated area corresponding to the i-th monitoring point.

[0034] It should be noted that the preset ash thermal conductivity is based on laboratory measured data and coal quality analysis. First, ash samples under different working conditions are collected, such as coking layers and fly ash particles. The thermal conductivity of the ash samples is measured at simulated boiler temperature using equipment such as a laser thermal conductivity meter. The ash composition, the correspondence between the particle size distribution and the thermal conductivity are recorded to form an "ash characteristics-thermal conductivity" database. In actual application, according to the current boiler fuel type and ash test results, the corresponding thermal conductivity is matched from the database as the preset value. For example, the SiO2 content in the ash of a common bituminous coal used in a power plant is 50%, and the laboratory measured thermal conductivity at 800°C is 0.15 watts per meter Kelvin. This value is used as the preset ash thermal conductivity for subsequent calculations.

[0035] It should also be noted that the fitting of the empirical coefficient is based on the historical operating data of the boiler and regression analysis. First, real-time monitoring data for three months, such as the temperature, dust concentration and total entropy growth rate of each monitoring point, are collected to establish a mathematical model containing the empirical coefficient, such as the total entropy growth rate formula. Then, fitting methods such as the least squares method are used to adjust the coefficient value so that the sum of squares of the error between the model calculated value and the actual monitoring value is minimized, and finally the optimal empirical coefficient is determined. For example, assuming that the empirical coefficient in the formula is an unknown number, 100 groups of historical data are selected, and the temperature and dust concentration in each group of data are substituted into the formula. Through fitting calculation, it is found that when the empirical coefficient is 0.8, the average error between the total entropy growth rate predicted by the model and the actual value is the smallest, and this value is then used as the final empirical coefficient.

[0036] It should also be noted that the heated area corresponding to each monitoring point is directly obtained by statistical calculation based on the geometric dimensions measured on site corresponding to the specified boiler, such as the surface area of ​​the pipes and the number of heat exchange tube bundles.

[0037] In a specific embodiment, the determination of whether to send an early warning signal is as follows: a preset standard entropy growth rate threshold value in the combustion process of a specified boiler corresponding to a specified thermal power plant is queried from a database, and the total entropy growth rate dv in the combustion process of the specified boiler corresponding to the set time period is compared with the preset standard entropy growth rate threshold value dv′. If dv is greater than dv′, it indicates that the combustion energy dissipation caused by boiler coking is aggravated, and an early warning signal needs to be sent. If dv is less than or equal to dv′, it indicates that there is no need to send an early warning signal.

[0038] It should be noted that the preset standard entropy growth rate threshold is used as the basis for determining whether to send an early warning signal. The preset standard entropy growth rate threshold is obtained based on statistical analysis of historical data under normal operating conditions of the boiler or calculation of the thermodynamic safety limit. For example, by collecting multiple sets of total entropy growth rate data of a designated boiler in a power plant under a coking-free and stable combustion state, such as real-time monitoring values ​​for 30 consecutive days, the average value is calculated, such as 0.8 watts per Kelvin second, and a safety margin, such as +20%, is added. The final threshold is set to 0.96 watts per Kelvin second.

[0039] In the process of acquiring critical entropy change parameters and calculating risk levels, the embodiment of the present invention systematically and comprehensively integrates multiple key parameters such as the total entropy growth rate, the number of fly ash particles, and the boiler load rate. The critical entropy growth rate is determined through historical data fitting and thermodynamic experiments, and the state of fly ash particles is monitored using professional instruments. The boiler load information is obtained in real time from the power plant management platform. The comprehensive risk level assessment formula is used, combined with scientific weight distribution to calculate the risk level, and the fuzzy risk situation is converted into a clear and quantitative grade system. It comprehensively considers various influencing factors such as thermodynamic changes, particle physical properties, and operating conditions, providing a scientific and accurate risk basis for subsequent decision-making, making the risk assessment more comprehensive and objective.

[0040] The critical phase change prediction module is used to obtain the critical entropy change parameters of the combustion process of the specified boiler within a set time period when an early warning signal is received, and then calculate the comprehensive risk level corresponding to the received early warning signal.

[0041] In a specific embodiment, the critical entropy change parameters of the combustion process of a specified boiler are obtained within a set time period, and the specific process is as follows: the critical entropy change parameters include the total entropy growth rate, the critical entropy growth rate, the total number of fly ash particles, the number of molten fly ash particles and the boiler load rate within the set time period. The critical entropy growth rate corresponding to the specified boiler is determined in advance through historical coking data fitting and thermodynamic experiments. The total number of fly ash particles and the number of molten fly ash particles corresponding to each monitoring point of the specified boiler within the set time period are monitored by a fly ash online analyzer, and the boiler load rate corresponding to the specified boiler within the set time period is obtained from the designated thermal power plant management platform.

[0042] It should be noted that the specific process of obtaining the critical entropy growth rate is as follows: first, analyze the total entropy growth rate data of the specified boiler during historical coking, use statistical methods such as scatter plot threshold segmentation to identify the critical value at which coking is significantly aggravated, and at the same time simulate the boiler operating conditions in the laboratory, and record the entropy growth rate when ash begins to rapidly adhere to coke through controlled combustion experiments. Finally, combine the historical fitting results with the experimental data and introduce a safety margin to determine the critical entropy growth rate that both conforms to the actual operating laws and verifies the thermodynamic mechanism.

[0043] In a specific embodiment, the comprehensive risk level corresponding to the received warning signal is calculated as follows: the total entropy growth rate in the combustion process of the specified boiler corresponding to the set time period is divided by the critical entropy growth rate corresponding to the specified boiler to obtain the entropy growth rate ratio of the combustion process of the specified boiler, which is recorded as dv″ i , and then through the comprehensive risk level assessment formula:

[0044] Get the comprehensive risk level assessment value R corresponding to the received warning signal, where N′ i and N iThey represent the total number of fly ash particles and the number of molten fly ash particles at the i-th monitoring point of the specified boiler, respectively. F represents the boiler load rate corresponding to the specified boiler in the set time period. They are respectively expressed as the weight factor corresponding to the set entropy growth rate ratio, the weight factor corresponding to the proportion of fly ash molten particles, and the weight factor corresponding to the boiler load rate;

[0045] According to the comprehensive risk level assessment value R corresponding to the received warning signal, the comprehensive risk level assessment value is rounded up, and the result obtained is the comprehensive risk level corresponding to the received warning signal.

[0046] It should be noted that The values ​​of are greater than 0 and less than 1. The setting process is the same as the weight allocation process of the multi-index comprehensive evaluation system in the existing technology, such as the hierarchical analysis method and the entropy weight method. They all use expert experience assignment, historical data regression or entropy value calculation to quantitatively assign weights based on the degree of influence of each parameter on the coking risk, so they will not be elaborated here.

[0047] It should also be noted that when the R value is 2.2 or 2.8, after rounding up, the result is 3, which indicates that the comprehensive risk level corresponding to the received warning signal is 3.

[0048] The anti-stress measures execution module is used to execute preset intervention operations according to the comprehensive risk level corresponding to the early warning signal.

[0049] In a specific embodiment, the specific process of executing the preset intervention operation is as follows: the comprehensive risk level corresponding to the received warning signal is recorded as R', and the pre-set leading risk assessment thresholds corresponding to each comprehensive risk level are queried from the database. The leading risk assessment thresholds include each entropy growth rate ratio assessment threshold and each fly ash molten particle ratio assessment threshold. If If the entropy growth rate is greater than or equal to the evaluation threshold corresponding to the risk level R′, it is determined to be a coking rate abnormality risk, and then the intervention operation corresponding to the preset coking rate abnormality risk is performed.

[0050] like If the percentage of fly ash molten particles is greater than or equal to the assessment threshold of the risk level R′, it is determined to be an abnormal coal ash adhesion risk, and then the intervention operation corresponding to the preset abnormal coal ash adhesion risk is executed. The entropy growth rate corresponding to the risk level R′ is greater than or equal to the assessment threshold and If the fly ash molten particle ratio is greater than or equal to the assessment threshold corresponding to the risk level R′, it is determined to be a composite risk, and the pre-set intervention operation corresponding to the composite risk is executed.

[0051] It should be noted that the pre-set dominant risk assessment thresholds corresponding to each comprehensive risk level are used as the basis for evaluating which intervention operation to perform. The setting process of the dominant risk assessment thresholds corresponding to each comprehensive risk level is the same as the setting process of the standard entropy growth rate threshold, which will not be elaborated here.

[0052] It should also be noted that the risk of abnormal coking rate is centered on reducing the efficiency of particle collision and adhesion, such as increasing the purge frequency of boiler sootblowers, such as adjusting from once every 8 hours to once every 4 hours, optimizing burner air distribution parameters to reduce flue gas flow rate or adjusting temperature field distribution, such as reducing the proportion of secondary air in a certain area to inhibit local high-concentration particle aggregation.

[0053] Abnormal coal ash adhesion risk: The goal is to improve the physical and chemical properties of the ash, for example, by adjusting the ash melting point through fuel mixing, such as burning 10% low-adhesion lignite to reduce the overall coal ash viscosity, spraying anti-adhesion additives into the furnace, such as regularly injecting kaolin powder to change the surface tension of the ash particles.

[0054] Complex risks: Take comprehensive measures of "speed reduction + modification", such as simultaneously increasing the soot blowing frequency to cope with high coking rate and adjusting the particle size of the pulverizer outlet to reduce the proportion of fine particles that are easy to adhere, or combining fuel ratio optimization to reduce adhesion and burner swing angle adjustment to improve flow field uniformity, while strengthening online coking monitoring to dynamically verify the intervention effect, such as increasing the scanning frequency of infrared thermal imagers.

[0055] During the execution of anti-coking measures in the embodiment of the present invention, the system accurately identifies the risk types of abnormal coking rate, abnormal coal ash adhesion or combined risk according to the comprehensive risk level by comparing assessment thresholds such as the entropy growth rate ratio and the proportion of fly ash molten particles. For different risk types, the system automatically matches and executes pre-set intervention operations, such as adjusting combustion air distribution, enhancing soot blowing frequency or coordinated disposal of multiple measures. The intelligent identification and precise policy-making mechanism changes the traditional "one-size-fits-all" blind treatment method of anti-coking operations and realizes "measures according to risks", which not only greatly improves the pertinence and effectiveness of anti-coking measures, but also effectively reduces resource waste and potential equipment damage, and improves the economy and safety of thermal power plant operation.

[0056] The effectiveness evaluation module is used to evaluate the effectiveness of executing the preset intervention operations.

[0057] In a specific embodiment, the evaluation is performed to determine the effectiveness of the preset intervention operation, and the specific process is as follows: after the intervention operation corresponding to the preset complex risk is performed, the effectiveness evaluation value corresponding to the intervention operation corresponding to the preset complex risk is calculated, and the comprehensive side effect evaluation value corresponding to the intervention operation corresponding to the preset complex risk is obtained by weighted calculation.

[0058] When the effectiveness evaluation value is greater than or equal to the effectiveness threshold corresponding to the intervention operation corresponding to the preset complex risk and the comprehensive side effect evaluation value is less than the preset comprehensive side effect evaluation value, it indicates that the intervention operation corresponding to the preset complex risk meets the effectiveness requirements; otherwise, it indicates that the intervention operation corresponding to the preset complex risk does not meet the effectiveness requirements.

[0059] It should be noted that when the intervention actions corresponding to the pre-set composite risk do not meet the effectiveness requirements, the cause of the failure is traced and targeted adjustments are made based on real-time monitoring data. If the coking rate is insufficiently controlled, pulsed purging can be added to the original soot blowing frequency, such as changing from every four hours to every two hours and extending the single purging time, or an ultrasonic decoking device can be introduced to enhance particle dispersion. If the improvement in ash adhesion does not meet expectations, the fuel blend ratio can be optimized. For example, the blending ratio of low-adhesion lignite can be increased from 10% to 15%, while increasing real-time monitoring of key adhesion parameters such as ash melting point and surface tension. For example, after implementing the combined "soot blowing and coal blending" measures at a thermal power plant, the entropy growth rate did not decrease significantly. Analysis revealed that fine particle adhesion still dominated, so the mill outlet particle size adjustment was added and the purging pressure was simultaneously increased.

[0060] It should be noted that the specific process of obtaining the comprehensive side effect assessment value corresponding to the intervention operation corresponding to the preset composite risk through weighted calculation is as follows: assuming that the intervention operation of "increasing the soot blowing frequency" is performed on the specified boiler, the side effect parameters are set to the steam energy consumption increase rate weight of 40%, which means that the soot blowing steam volume after the operation increases by 5% compared with before, the soot blower wear rate weight of 30%, which means that the wear degree of mechanical parts increases by 2% compared with normal operation, and the flue gas heat loss increase rate weight of 30%, which means that the heat loss caused by soot blowing increases by 1.5% compared with before the intervention. After standardizing each parameter to 0.5, 0.2, and 0.15 according to the benchmark value, the comprehensive side effect assessment value is calculated by weight: 0.5×40%+0.2×30%+0.15×30%=0.305.

[0061] It should also be noted that the effectiveness threshold corresponding to the intervention operation corresponding to the preset complex risk is used as the basis for evaluating whether the intervention operation corresponding to the preset complex risk meets the effectiveness requirements. The setting process of the effectiveness threshold is the same as the setting process of the standard entropy growth rate threshold, which will not be elaborated here.

[0062] It should also be noted that the opposite means: when the effectiveness evaluation value is greater than or equal to the effectiveness threshold corresponding to the intervention operation corresponding to the preset complex risk and the comprehensive side effect evaluation value is greater than or equal to the preset comprehensive side effect evaluation value, it indicates that the intervention operation corresponding to the preset complex risk does not meet the effectiveness requirements; when the effectiveness evaluation value is less than the effectiveness threshold corresponding to the intervention operation corresponding to the preset complex risk and the comprehensive side effect evaluation value is less than the preset comprehensive side effect evaluation value, it indicates that the intervention operation corresponding to the preset complex risk does not meet the effectiveness requirements; when the effectiveness evaluation value is less than the effectiveness threshold corresponding to the intervention operation corresponding to the preset complex risk and the comprehensive side effect evaluation value is greater than or equal to the preset comprehensive side effect evaluation value, it indicates that the intervention operation corresponding to the preset complex risk does not meet the effectiveness requirements.

[0063] In a specific embodiment, the calculation of the effectiveness evaluation value corresponding to the intervention operation corresponding to the preset complex risk is performed in the following process: Based on the effectiveness calculation formula: Get the effectiveness evaluation value α corresponding to the intervention operation corresponding to the preset composite risk, where dv after It is expressed as the total entropy growth rate in the combustion process of a specified boiler after the intervention operation corresponding to the preset composite risk is executed.

[0064] It should be noted that when executing the intervention operation corresponding to the preset abnormal coking rate risk or the intervention operation corresponding to the preset abnormal coal ash adhesion risk, the calculation is also performed according to the effectiveness calculation formula.

[0065] In the performance evaluation process, the embodiment of the present invention scientifically judges the effectiveness of the intervention operation by calculating the effectiveness evaluation value and the comprehensive side effect evaluation value. Once it is found that the executed intervention operation does not meet the effectiveness requirements, the optimization mechanism is immediately activated to adjust and improve the preset intervention strategy, which helps the system to dynamically adjust the anti-coking measures according to the actual operation effect. Through continuous feedback and optimization, the system's overall handling ability for abnormal conditions in thermal power plants is continuously improved, ensuring the long-term, stable and efficient operation of thermal power plants, and promoting the development of thermal power plant operation and maintenance management towards intelligence and refinement.

[0066] The database is used to store the pre-set standard entropy growth rate thresholds for the combustion process of a specified boiler corresponding to a specified thermal power plant, and also stores the pre-set dominant risk assessment thresholds corresponding to each comprehensive risk level. The dominant risk assessment thresholds include each entropy growth rate ratio assessment threshold and each fly ash molten particle ratio assessment threshold.

[0067] See also Figure 2As shown, the identification and analysis method based on abnormal conditions of thermal power plants includes the following steps: Step 1, designated boiler coking prediction: collecting early warning data of the designated boiler combustion process corresponding to the designated thermal power plant within a set time period, and calculating the total entropy growth rate of the designated boiler combustion process corresponding to the set time period to determine whether to send an early warning signal.

[0068] Step 2: Critical phase change prediction: When an early warning signal is received, the critical entropy change parameters of the combustion process of the specified boiler within the set time period are obtained, and then the comprehensive risk level corresponding to the received early warning signal is calculated.

[0069] Step 3: Execution of anti-stress measures: Execute preset intervention operations based on the comprehensive risk level corresponding to the early warning signal.

[0070] Step 4: Effectiveness evaluation: Evaluate the effectiveness of implementing the preset intervention operations.

[0071] The embodiment of the present invention provides an identification and analysis system and method based on abnormal conditions of thermal power plants. By using multi-dimensional monitoring equipment such as a high-temperature resistant sensor network and a laser particle size analyzer, combined with three-dimensional modeling of the boiler structure and optimized layout of monitoring points, it is beneficial to overcome the limitations of traditional single-point monitoring and achieve three-dimensional perception of the temperature field distribution of the coking layer, the particle movement trajectory, and the physical properties of the ash. This multi-dimensional data collection method is conducive to warning of coking hazards 3-5 days in advance, which has significant advantages over the traditional single temperature threshold alarm.

[0072] The above content is merely an example and explanation of the concept of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined in this specification, they should all fall within the scope of protection of the present invention.

Claims

1. Based on the identification and analysis system of abnormal conditions in thermal power plants, the characteristics are: include: The designated boiler coking prediction module is used to collect early warning data of the combustion process of the designated boiler in the specified thermal power plant within the set time period. By calculating the total entropy growth rate of the combustion process of the designated boiler within the set time period, it is determined whether to send an early warning signal; The critical phase change prediction module is used to obtain the critical entropy change parameters of the combustion process of the specified boiler within a set time period when an early warning signal is received, and then calculate the comprehensive risk level corresponding to the received early warning signal; The anti-stress measures execution module is used to execute preset intervention operations according to the comprehensive risk level corresponding to the early warning signal; The effectiveness evaluation module is used to evaluate the effectiveness of executing the preset intervention operations.

2. The identification and analysis system based on abnormal conditions of thermal power plants according to claim 1, characterized in that: The specific process of collecting early warning data of the combustion process of a designated boiler in a designated thermal power plant within a set time period is as follows: The early warning data includes the temperature of the ash layer, the particle collision frequency, the average mass of the ash particles, and the combustion energy release rate. The specified boiler structure is obtained from the corresponding design drawing of the specified boiler. Then, each monitoring point is set inside the specified boiler, and the corresponding distance between each monitoring point is recorded. The temperature value corresponding to each monitoring point is obtained by monitoring with a high-temperature resistant sensor, which is recorded as T i , i is the number corresponding to each monitoring point, i = 1, 2, ..., n, n is a positive integer, and then the calculation formula is: Get the temperature gradient ΔT corresponding to the direction of the i-th monitoring point and the i-1-th monitoring point i , d i It is expressed as the distance between the i-th monitoring point and the i-1-th monitoring point, T i-1 is the temperature value corresponding to the i-1th monitoring point; The particle collision frequency f corresponding to each monitoring point is calculated by combining the dust concentration meter with the flue gas flow rate i , the particle samples of each monitoring point are collected by online fly ash sampler, and then the particle size distribution is measured by laser particle size analyzer, and then the average mass of ash particles is calculated by combining with ash density. The fuel flow, fuel calorific value, and combustion efficiency of a specified boiler within a set time period are obtained from the specified thermal power plant management platform, and the combustion energy release rate η is then calculated.

3. The identification and analysis system based on abnormal conditions of thermal power plants according to claim 2, characterized in that: The calculation is performed to determine the total entropy growth rate during the combustion process of a specified boiler within a set time period. The specific process is as follows: The entropy growth rate is calculated by the formula: The total entropy growth rate dv corresponding to the combustion process of the specified boiler within the set time period is obtained, where k and g represent the preset ash thermal conductivity and the empirical coefficient obtained by fitting historical data, respectively. S i It is represented as the heated area corresponding to the i-th monitoring point.

4. The identification and analysis system based on abnormal conditions of thermal power plants according to claim 3, characterized in that: The specific process of determining whether to send an early warning signal is as follows: The preset standard entropy growth rate threshold value of the combustion process of the specified boiler corresponding to the specified thermal power plant is queried from the database, and the total entropy growth rate dv of the combustion process of the corresponding specified boiler within the set time period is compared with the preset standard entropy growth rate threshold dv′. If dv is greater than dv′, it indicates that the combustion energy dissipation caused by boiler coking is aggravated and an early warning signal needs to be sent. If dv is less than or equal to dv′, it indicates that no early warning signal needs to be sent.

5. The identification and analysis system based on abnormal conditions of thermal power plants according to claim 4, characterized in that: The specific process of obtaining the critical entropy change parameter corresponding to the combustion process of a specified boiler within a set time period is as follows: The critical entropy change parameters include the total entropy growth rate, critical entropy growth rate, total fly ash particle number, fly ash molten particle number and boiler load rate within a set time period. The critical entropy growth rate corresponding to the specified boiler is determined in advance through historical coking data fitting and thermodynamic experiments. The total fly ash particle number and fly ash molten particle number of the specified boiler corresponding to each monitoring point within the set time period are monitored by a fly ash online analyzer, and the boiler load rate corresponding to the specified boiler within the set time period is obtained from the management platform of the specified thermal power plant.

6. The identification and analysis system based on abnormal conditions of thermal power plants according to claim 5, characterized in that: The specific process of calculating the comprehensive risk level corresponding to the received warning signal is as follows: The total entropy growth rate during the combustion process of the specified boiler within the set time period is divided by the critical entropy growth rate corresponding to the specified boiler to obtain the entropy growth rate ratio during the combustion process of the specified boiler, which is recorded as dv″ i , and then through the comprehensive risk level assessment formula: Get the comprehensive risk level assessment value R corresponding to the received warning signal, where N i ′ and N i They represent the total number of fly ash particles and the number of molten fly ash particles at the i-th monitoring point of the specified boiler, respectively. F represents the boiler load rate corresponding to the specified boiler in the set time period. They are respectively expressed as the weight factor corresponding to the set entropy growth rate ratio, the weight factor corresponding to the proportion of fly ash molten particles, and the weight factor corresponding to the boiler load rate; According to the comprehensive risk level assessment value R corresponding to the received warning signal, the comprehensive risk level assessment value is rounded up, and the result obtained is the comprehensive risk level corresponding to the received warning signal.

7. The identification and analysis system based on abnormal conditions of thermal power plants according to claim 6, characterized in that: The specific process of executing the preset intervention operation is as follows: The comprehensive risk level corresponding to the received warning signal is recorded as R', and the pre-set leading risk assessment thresholds corresponding to each comprehensive risk level are queried from the database. The leading risk assessment thresholds include the entropy growth rate ratio assessment thresholds and the fly ash molten particle ratio assessment thresholds. If If the entropy growth rate is greater than or equal to the assessment threshold corresponding to the risk level R′, it is determined to be a coking rate abnormality risk, and the preset intervention operation corresponding to the coking rate abnormality risk is executed; like If the percentage of fly ash molten particles is greater than or equal to the assessment threshold of the risk level R′, it is determined to be an abnormal coal ash adhesion risk, and then the intervention operation corresponding to the preset abnormal coal ash adhesion risk is executed. The entropy growth rate corresponding to the risk level R′ is greater than or equal to the assessment threshold and If the fly ash molten particle ratio is greater than or equal to the assessment threshold corresponding to the risk level R′, it is determined to be a composite risk, and the pre-set intervention operation corresponding to the composite risk is executed.

8. The identification and analysis system based on abnormal conditions of thermal power plants according to claim 7, characterized in that: The evaluation is performed to determine the effectiveness of the preset intervention operation. The specific process is as follows: After the intervention operation corresponding to the preset complex risk is executed, the effectiveness evaluation value corresponding to the intervention operation corresponding to the preset complex risk is calculated, and the comprehensive side effect evaluation value corresponding to the intervention operation corresponding to the preset complex risk is obtained by weighted calculation; When the effectiveness evaluation value is greater than or equal to the effectiveness threshold corresponding to the intervention operation corresponding to the preset complex risk and the comprehensive side effect evaluation value is less than the preset comprehensive side effect evaluation value, it indicates that the intervention operation corresponding to the preset complex risk meets the effectiveness requirements; otherwise, it indicates that the intervention operation corresponding to the preset complex risk does not meet the effectiveness requirements.

9. The identification and analysis system based on abnormal conditions of thermal power plants according to claim 8, characterized in that: The calculation of the effectiveness evaluation value of the intervention operation corresponding to the preset complex risk is performed in the following specific process: Based on the effectiveness calculation formula: Get the effectiveness evaluation value α corresponding to the intervention operation corresponding to the preset composite risk, where dv after It is expressed as the total entropy growth rate in the combustion process of a specified boiler after the intervention operation corresponding to the preset composite risk is executed.

10. A method for identifying and analyzing abnormal conditions in a thermal power plant, which implements the system for identifying and analyzing abnormal conditions in a thermal power plant according to any one of claims 1 to 9, characterized in that: The steps include: Step 1: Predicting coking in a designated boiler: Collecting early warning data from the combustion process of a designated boiler in a set time period at a designated thermal power plant. Calculating the total entropy growth rate during the combustion process of the designated boiler in the set time period to determine whether to send an early warning signal. Step 2: Critical phase change prediction: When an early warning signal is received, the critical entropy change parameter of the combustion process of the specified boiler within the set time period is obtained, and then the comprehensive risk level corresponding to the received early warning signal is calculated; Step 3: Execute anti-stress measures: Execute the preset intervention operations according to the comprehensive risk level corresponding to the early warning signal; Step 4: Effectiveness evaluation: Evaluate the effectiveness of implementing the preset intervention operations.

Images