Intelligent power plant anomaly analysis system and method based on electric power Internet of Things

Abstract

The invention discloses an intelligent power plant anomaly analysis system and method based on the electric power Internet of Things, and relates to the technical field of power plants, and the system comprises four modules: a microscopic dynamic monitoring module monitors whether the pulverized coal combustion dynamic state of each monitoring point is unbalanced or not through configuring microscopic hardware in each combustion chamber of a target power plant; when the control strategy analysis module detects combustion dynamic unbalance, the control strategy of the corresponding combustion chamber is analyzed in a targeted mode; the creep damage evaluation value analysis module is used for setting a plurality of evaluation time points when the combustion chamber runs, and quantitatively analyzing the creep damage evaluation value of each part; and the hidden damage risk assessment module accurately judges the hidden damage risk grade of each combustion chamber component according to the assessment value of each time point. The system depends on the electric power internet of things technology, comprehensive monitoring and risk assessment of the combustion state of the combustion chamber of the power plant and equipment damage are achieved, and powerful support is provided for abnormity analysis and safe operation of the intelligent power plant.

Description

Technical Field

[0001] The present invention relates to the technical field of power plants, and in particular to a smart power plant abnormality analysis system and method based on the power Internet of Things. Background Art

[0002] With the development of the power industry, traditional power plants face numerous challenges, such as improving production efficiency, reducing costs, ensuring safe production, and achieving energy conservation and emission reduction. The concept of the smart power plant has emerged. Its goal is to leverage advanced information technologies, such as the Internet of Things (IoT), big data, and artificial intelligence (AI), to comprehensively perceive the power plant's production processes, optimize decision-making, and implement intelligent control to enhance the plant's overall performance and competitiveness. Consequently, a smart power plant anomaly analysis system and method based on the power IoT is needed.

[0003] The prior art, such as the invention application patent with publication number CN117553315A, discloses an intelligent boiler combustion monitoring system, which detects the coal powder and fuel oil parameters in the micro-oil ignition combustion process through a combustion medium detection module; monitors the operating parameters of the primary combustion chamber, secondary combustion chamber, fuel sprayer and ignition device, including inlet air volume, coal powder concentration, injection time and ignition action, through an operation process detection module; determines the compliance degree of the inlet air volume and coal powder concentration of the primary combustion chamber according to the air volume standard through an operation analysis module, calculates the ideal inlet air volume and coal powder concentration of the secondary combustion chamber, and analyzes the ideal ignition time and ideal injection time; controls the operation of the air supply device, fuel sprayer and ignition device according to the analysis results through an operation control module; displays the analysis results and control process through a display management module; the present invention realizes monitoring and control of the micro-oil ignition coal powder combustion system through an intelligent monitoring system, improves combustion efficiency and safety, and reduces energy waste and environmental pollution.

[0004] In response to the above solution, this applicant has found that the above technology has at least the following technical problems: 1. The existing technology lacks microscopic and multi-dimensional monitoring means, making it difficult to accurately obtain key indicators such as coal powder combustion, and difficult to adapt to microscopic hardware, resulting in limited accuracy of monitoring data and inability to timely detect subtle combustion anomalies in the combustion chamber. At the same time, accurately judging whether the combustion dynamics are unbalanced may lead to inaccurate judgment of the combustion status and miss the best adjustment opportunity. When the combustion dynamics are unbalanced, there is no detailed control strategy analysis for different degrees of imbalance. This may lead to excessive or insufficient adjustments, affecting combustion efficiency and pollutant emission control.

[0005] 2. Existing technologies lack systematic and diverse response strategies. When faced with varying degrees of combustion dynamic imbalance, they are unable to provide comprehensive and effective solutions. Instead, they may only employ conventional, general measures, failing to achieve personalized optimization and control. Furthermore, without multiple damage assessment time points, creep damage assessments of combustion chamber components cannot be performed in real time or regularly. Potential component damage may not be detected promptly, increasing the risk of equipment failure.

[0006] 3. Existing technologies struggle to accurately determine the hidden damage risk level of each component, hindering the development of maintenance plans and preventative measures. This can lead to sudden equipment failures and disrupt the normal operation of the power plant. Furthermore, existing technologies may utilize relatively independent monitoring and control links, lacking an integrated system based on the power Internet of Things (IoT). This inability to achieve data sharing and collaborative analysis reduces the efficiency and accuracy of power plant anomaly analysis. It is difficult to leverage advanced technologies such as the IoT and data analytics to implement intelligent anomaly analysis and decision support, requiring extensive manual data processing and judgment, which is not only inefficient but also prone to human error. Summary of the Invention

[0007] In view of the above-mentioned technical deficiencies, the purpose of the present invention is to provide a smart power plant abnormality analysis system and method based on the power Internet of Things.

[0008] In order to solve the above technical problems, the present invention adopts the following technical solutions: In the first aspect, the present invention provides a smart power plant abnormality analysis system based on the power Internet of Things, including: a micro-dynamic monitoring module: used to configure micro-hardware in each combustion chamber of the target power plant, so as to evaluate whether the corresponding coal powder combustion dynamics in each combustion chamber of the target power plant are unbalanced at each monitoring point.

[0009] Control strategy analysis module: used to analyze the control strategy corresponding to a combustion chamber of a target power plant at a certain monitoring point when the corresponding pulverized coal combustion in the combustion chamber of the target power plant at the monitoring point is dynamically unbalanced.

[0010] Creep damage assessment value analysis module: used to set several damage assessment time points when each combustion chamber of the target power plant is in operation, and then analyze the creep damage assessment value corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point.

[0011] Hidden damage risk assessment module: used to determine the risk level of hidden damage corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point based on the creep damage assessment value corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point.

[0012] In the second aspect, the present invention provides a smart power plant abnormality analysis method based on the power Internet of Things, including: step one, micro-dynamic monitoring: configuring micro-hardware in each combustion chamber of the target power plant, so as to evaluate at each monitoring point whether the corresponding coal powder combustion dynamics in each combustion chamber of the target power plant are unbalanced.

[0013] Step 2: Analysis of control strategy: When the pulverized coal combustion in a combustion chamber of a target power plant at a certain monitoring point is dynamically unbalanced, the control strategy corresponding to the combustion chamber of the target power plant at the monitoring point is analyzed.

[0014] Step 3: Analysis of creep damage assessment values: When each combustion chamber of the target power plant is in operation, several damage assessment time points are set, and then the creep damage assessment values corresponding to each component in each combustion chamber of the target power plant are analyzed at each damage assessment time point.

[0015] Step 4. Assessment of hidden damage risk: Based on the creep damage assessment value corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point, the risk level of hidden damage corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point is determined.

[0016] The beneficial effects of the present invention are as follows: 1. In this embodiment, microscopic hardware is deployed within each combustion chamber of a target power plant through a microscopic dynamic monitoring module, enabling precise sensing of subtle changes in pulverized coal combustion. Hardware parameters are intelligently adjusted based on the number of abnormal operating conditions, making pulverized coal combustion dynamic monitoring more targeted and accurate. Pulverized coal fluidization indicators and flame radical indicators are acquired from different perspectives, and a scientific evaluation model is used to calculate pulverized coal combustion dynamic assessment values. This provides strong support for accurately determining whether combustion is imbalanced, thereby effectively improving combustion efficiency and ensuring a stable combustion process. When pulverized coal combustion dynamic imbalance is detected, the control strategy analysis module can formulate and implement a refined control strategy based on the specific degree of imbalance. Whether fine-tuning the secondary air ratio and ammonia injection position for minor imbalances, or significantly adjusting various parameters and changing the injection pattern for moderate or severe imbalances, these measures can quickly and effectively correct combustion imbalances, improving energy utilization and reducing pollutant emissions caused by incomplete combustion, achieving energy conservation and emission reduction goals while ensuring stable operation of the combustion equipment.

[0017] 2. In this embodiment of the present invention, a creep damage assessment value analysis module and a hidden damage risk assessment module are combined to conduct comprehensive and in-depth monitoring and assessment of creep damage in various components within each combustion chamber of a target power plant. Ultrasonic signals are acquired using high-temperature piezoelectric composite sensors. These signals, combined with operating parameters collected by the DCS system, are substituted into a calculation formula to obtain a creep damage assessment value. This value is then compared with a set range to determine the hidden damage risk level. This approach enables early detection of potential damage risks in equipment, allowing operations and maintenance personnel to rationally schedule maintenance based on different risk levels, avoiding downtime losses caused by sudden equipment failures, extending equipment life, reducing equipment operation and maintenance costs, and improving equipment reliability and safety. This enables intelligent management of power plant equipment and combustion processes. The data exchange and collaborative operation between these modules enable the system to process large amounts of monitoring data in real time and make rapid and accurate analysis and judgments. Furthermore, the system automatically adjusts control strategies or issues early warning information based on the analysis results, providing a scientific basis for decision-making in power plant operations and management, improving the plant's intelligence level and management efficiency, and contributing to the goal of a smart power plant.

[0018] 3. In the embodiment of the present invention, in terms of hardware configuration, the micro hardware parameters are dynamically adjusted according to the number of abnormal operating conditions, which not only ensures the accuracy and effectiveness of monitoring, but also avoids the waste of resources caused by over-configuration. For combustion chambers with fewer abnormal operating conditions, hardware equipment with lower performance parameters is used, while for combustion chambers with more abnormal operating conditions, the performance parameters of the hardware equipment are improved. This rational use of resources reduces the construction and operation costs of the system and improves the cost-effectiveness of the system. In terms of pollutant control, the emission of pollutants such as nitrogen oxides and carbon soot can be significantly reduced by optimizing combustion control strategies, such as ammonia injection optimization and soot suppression. This not only enables the power plant to comply with strict environmental protection regulations and reduce negative impacts on the environment, but also enhances the social image of the power plant and lays the foundation for the sustainable development of the power plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] 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.

[0020] Figure 1 This is a schematic diagram of the system module connection of the present invention.

[0021] Figure 2 The present invention is a flowchart of the steps for implementing the method. DETAILED DESCRIPTION

[0022] 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.

[0023] The present invention is implemented as follows Figure 1 As shown in the figure, the smart power plant abnormality analysis system based on the power Internet of Things includes: a micro-dynamic monitoring module, a control strategy analysis module, a creep damage assessment value analysis module and a hidden damage risk assessment module.

[0024] The control strategy analysis module is connected to the microscopic dynamic monitoring module and the creep damage assessment value analysis module respectively, and the creep damage assessment value analysis module is connected to the hidden damage risk assessment module.

[0025] Micro-dynamic monitoring module: used to configure micro-hardware in each combustion chamber of the target power plant, so as to evaluate whether the corresponding pulverized coal combustion dynamics in each combustion chamber of the target power plant are unbalanced at each monitoring point.

[0026] In a specific embodiment, the micro hardware is configured in each combustion chamber of the target power plant, and the specific configuration process is as follows: A1. Obtain the number of abnormal operating conditions corresponding to each combustion chamber of the target power plant, and compare the number of abnormal operating conditions corresponding to each combustion chamber of the target power plant with the set thresholds.

[0027] It should be noted that abnormal operating conditions include flame extinction, flickering, deflagration, flashback, excessive soot, and burner blockage. By screening the records that trigger alarms from the power plant SIS monitoring information system, the number of occurrences of abnormal operating conditions is counted by timestamp.

[0028] A2. If the number of abnormal operating conditions corresponding to each combustion chamber of the target power plant is within the first threshold, the microwave resonance imaging equipment frequency range is selected to be 2-5 GHz, the power is selected to be 1-5 W, the scanning range covers 60%-80% of the transmission pipeline cross-section, the spatial resolution is 5-10 mm, the CCD camera frame rate is selected to be 25-50 frames / second, the pixel size is 1024×768-2048×1536, the sensitivity is 800-1600, the TDLAS sensor wavelength range is selected to be 1.3-1.4 μm, the CH free radical wavelength range can be selected to be 3.2-3.4 μm, the accuracy is ±5%, the measurement range is 0-100 ppm, and the UV imager wavelength range is selected to be 200-400 nm, the resolution is 320×240-640×480, and the dynamic range is 10-10,000 lux.

[0029] A3. If the number of abnormal operating conditions corresponding to each combustion chamber of the target power plant is between the first and second thresholds, the microwave resonance imaging equipment frequency range is selected to be 5-10 GHz, the power is 5-10 W, the scanning range covers 80%-90% of the transmission pipeline cross-section, and the spatial resolution reaches 2-5 mm. The ultra-high-speed CCD camera is selected to have a frame rate of 100-200 frames per second, a pixel size of 2048×1536-4096×3072, and a sensitivity of 1600-3200. The humidity sensor is selected to have a measurement range of 0-20% RH and an accuracy of ±1% RH. The TDLAS sensor is selected to have a wavelength range of 1.3-1.4 μm, a spacing of 5-10 cm between adjacent sensors, an accuracy improved to ±3%, and a measurement range of 0-50 ppm. The ultraviolet imager is selected to have a resolution increased to 640×480-1024×768, and a dynamic range of 5-50,000 lux.

[0030] A4. If the number of abnormal operating conditions corresponding to each combustion chamber of the target power plant is greater than the second threshold, the microwave resonance imaging equipment shall have a frequency range of 10-20 GHz, a power of 10-20 W, a scanning range that completely covers the cross-section of the transmission pipeline, and a spatial resolution of 1-2 mm. The ultra-high-speed CCD camera shall have a frame rate of 500-1000 frames per second, a pixel size of 4096×3072-8192×6144, and a sensitivity of 3200-6400. The data analysis system shall have the ability to process 10-100 GB of data per second, adopt a parallel computing architecture, and have a data storage capacity of 1-10 TB. The TDLAS sensor shall have a wavelength range of 1.5-1.6 μm, a spacing of 2-5 cm between adjacent sensors, an accuracy of ±1%, a measurement range of 0-20 ppm, and a response time of less than 10 ms. The ultraviolet imager shall have a resolution of 1024×768-2048×1536 and a dynamic range of 1-100,000 lux.

[0031] In a specific embodiment, the microscopic dynamic monitoring module further includes a pulverized coal combustion dynamic evaluation value analysis unit: the pulverized coal combustion dynamic evaluation value analysis unit is used to obtain the pulverized coal fluidization uniformity evaluation value and the flame free radical evaluation value corresponding to each combustion chamber of each target power plant at each monitoring point, and record them as and , where n represents the number corresponding to each monitoring point, , w is any integer greater than 2, m represents the number corresponding to each combustion chamber, , r is any integer greater than 2, and then the corresponding pulverized coal combustion dynamic evaluation value in each combustion chamber of the target power plant at each monitoring point is obtained by analysis.

[0032] In a specific embodiment, the analysis obtains the corresponding pulverized coal combustion dynamic evaluation value in each combustion chamber of the target power plant at each monitoring point. The specific analysis process is as follows: the pulverized coal fluidization uniformity evaluation value and the flame free radical evaluation value corresponding to each combustion chamber of the target power plant at each monitoring point are substituted into the calculation formula: The dynamic evaluation value of pulverized coal combustion in each combustion chamber of the target power plant at each monitoring point is obtained. ,in, and They are the standard pulverized coal fluidization uniformity evaluation value and the standard flame free radical evaluation value corresponding to the set combustion chamber, Indicates the temperature corresponding to each combustion chamber of the target power plant at each monitoring point, It represents the average temperature of each combustion chamber of the target power plant during the historical period.

[0033] It should be noted that the numerator of the formula comprehensively considers the deviation of the uniform evaluation value of pulverized coal fluidization and the deviation of the flame radical evaluation value. Through cube root operation, it can comprehensively reflect the degree of deviation of the pulverized coal fluidization and flame radical states in the combustion chamber from the standard value, and more comprehensively reflect the dynamic changes of the combustion state.

[0034] The formula's denominator uses the difference between the current temperature and the historical period average temperature to perform an exponential calculation, accounting for the impact of temperature on combustion state assessment. Temperature is a key factor influencing the combustion process. This setting allows the assessment value to be adjusted based on temperature conditions, making the assessment more accurate and reliable in line with actual combustion conditions. The pulverized coal combustion dynamics assessment value calculated using this formula can provide a quantitative indicator for operational monitoring of each combustor in the target power plant. This facilitates the assessment of whether pulverized coal combustion dynamics are imbalanced, providing data support for optimizing combustion adjustments, improving combustion efficiency, and reducing pollutant emissions.

[0035] In a specific embodiment, the pulverized coal fluidization uniformity evaluation value and the flame free radical evaluation value corresponding to each combustion chamber of the target power plant at each monitoring point are obtained, and the specific acquisition process is as follows: B1. Obtain the pulverized coal fluidization index and the flame free radical index corresponding to each combustion chamber of the target power plant at each monitoring point. The pulverized coal fluidization index includes the pulverized coal concentration uniformity index, the average velocity of the pulverized coal particles, and the pulverized coal particle size distribution range. The flame free radical index includes the soot concentration, the average soot particle size, and the combustion concentration corresponding to each free radical.

[0036] It should be noted that the pulverized coal concentration uniformity index is determined using microwave resonance imaging equipment. This equipment scans and images the pulverized coal within the conveying pipeline, analyzing the distribution of pulverized coal at different locations. By calibrating the image grayscale value or other characteristic parameters with pulverized coal concentration, the image data is converted into pulverized coal concentration values at each location. The average (arithmetic mean) of the concentration at each location is calculated, as is the standard deviation of the concentration data (reflecting the degree of data dispersion). The pulverized coal concentration uniformity index is calculated using the formula: 1 - (standard deviation ÷ average concentration). The average velocity of pulverized coal particles is determined using a CCD camera or an ultra-high-speed CCD camera. By capturing images of pulverized coal particles in motion and employing image analysis techniques such as particle image velocimetry (PIV), the positions of pulverized coal particles at different times are tracked. The particle velocity is calculated using the formula: particle velocity = displacement ÷ time interval. The arithmetic mean is then calculated to obtain the average velocity. The pulverized coal particle size distribution range is determined using a combination of microwave resonance imaging equipment and a TDLAS sensor. Microwave resonance imaging equipment captures coal pulverized particle distribution information. TDLAS sensors use wavelength lasers to interact with coal particles, measuring particle size based on scattering and absorption principles. This comprehensive analysis yields a particle size distribution range. Based on Mie scattering theory or other light scattering models, a correlation is established between signal intensity and particle size, allowing the number distribution of particles of varying sizes to be calculated. The minimum and maximum particle sizes at which the cumulative particle count reaches a set threshold are defined as the particle size distribution range.

[0037] It should also be noted that soot concentration is determined using an ultraviolet imager. This image captures flames within a specific wavelength range. Based on the soot's absorption and scattering characteristics of ultraviolet light, an image analysis algorithm extracts pixel-level light attenuation information. Combined with a standard curve, the equation "soot concentration = (image light attenuation value - background light attenuation value) / curve slope" is used. The average soot particle size is determined using a TDLAS sensor and data analysis system. The TDLAS sensor measures the optical signal associated with soot. The data analysis system processes and analyzes the sensor data, calculating the average soot particle size using a relevant model. The formula "average particle size = Σ(particle size × probability of occurrence)" is used to weight the sum of all particle sizes and their probabilities to obtain the average soot particle size. The combustion concentration of each free radical is determined using a TDLAS sensor. Based on laser absorption spectroscopy, the combustion concentration of each free radical is calculated based on the free radical's absorption of laser light at a specific wavelength, combined with the instrument's accuracy. The TDLAS sensor emits laser light at the wavelength corresponding to the free radical's absorption and measures the incident and outgoing light intensities. Concentration calculation: Based on the Lambert-Beer law, the outgoing light intensity = incident light intensity × e^(-absorption coefficient × free radical concentration × optical path), the formula free radical concentration = -ln(outgoing light intensity ÷ incident light intensity) ÷ (absorption coefficient × optical path) is transformed. Combined with the instrument accuracy (such as ±5%), the free radical combustion concentration is obtained.

[0038] B2. The pulverized coal concentration uniformity index, average velocity of pulverized coal particles, and pulverized coal particle size distribution range corresponding to each combustion chamber of each target power plant at each monitoring point are used as input information and normalized. At the same time, they are entered into the pulverized coal fluidization uniformity assessment value analysis model. After calculation and analysis by the pulverized coal fluidization uniformity assessment value analysis model, the pulverized coal fluidization uniformity assessment value corresponding to each combustion chamber of each target power plant at each monitoring point is finally output. .

[0039] It should be noted that the analysis process of the pulverized coal fluidization uniformity evaluation value corresponding to each combustion chamber of the target power plant at each monitoring point is as follows: the pulverized coal concentration uniformity index, the average velocity of pulverized coal particles, and the pulverized coal particle size distribution range corresponding to each combustion chamber of the target power plant at each monitoring point are respectively recorded as 、 and , substitute into the analytical formula , and obtain the corresponding pulverized coal fluidization uniformity assessment value in each combustion chamber of each target power plant at each monitoring point .

[0040] B3. The soot concentration, average soot particle size, and combustion concentration of each free radical corresponding to each combustion chamber of each target power plant at each monitoring point are used as input information and normalized. At the same time, they are entered into the flame free radical evaluation value analysis model. After calculation and analysis by the flame free radical evaluation value analysis model, the flame free radical evaluation value corresponding to each combustion chamber of each target power plant at each monitoring point is finally output. .

[0041] It should be noted that the flame radical evaluation value corresponding to each combustion chamber of each target power plant at each monitoring point is obtained by analyzing the pulverized coal fluidization uniformity evaluation value corresponding to each combustion chamber of each target power plant at each monitoring point according to the above-mentioned analysis process.

[0042] In a specific embodiment, the evaluation at each monitoring point of whether the corresponding pulverized coal combustion dynamics in each combustion chamber of the target power plant is unbalanced, and the specific evaluation process is as follows: the pulverized coal combustion dynamics evaluation value corresponding to each combustion chamber of the target power plant at each monitoring point is compared with the pulverized coal combustion dynamics evaluation value corresponding to the set standard combustion chamber. If the pulverized coal combustion dynamics evaluation value corresponding to a certain combustion chamber of the target power plant at a certain monitoring point is less than the pulverized coal combustion dynamics evaluation value corresponding to the set standard combustion chamber, then it is evaluated that the pulverized coal combustion dynamics corresponding to the combustion chamber of the target power plant at the monitoring point is not unbalanced. If the pulverized coal combustion dynamics evaluation value corresponding to a certain combustion chamber of the target power plant at a certain monitoring point is greater than or equal to the pulverized coal combustion dynamics evaluation value corresponding to the set standard combustion chamber, then it is evaluated that the pulverized coal combustion dynamics corresponding to the combustion chamber of the target power plant at the monitoring point is unbalanced.

[0043] Control strategy analysis module: used to analyze the control strategy corresponding to a combustion chamber of a target power plant at a certain monitoring point when the corresponding pulverized coal combustion in the combustion chamber of the target power plant at the monitoring point is dynamically unbalanced.

[0044] In a specific embodiment, the control strategy corresponding to the combustion chamber of the target power plant at the monitoring point is analyzed, and the specific analysis process is as follows: C1. If the corresponding pulverized coal combustion in a combustion chamber of a target power plant at a monitoring point is dynamically unbalanced, and the corresponding pulverized coal combustion dynamic evaluation value in the combustion chamber of the target power plant at the monitoring point is greater than 10% of the corresponding pulverized coal combustion dynamic evaluation value in the set standard combustion chamber, it is recorded as a slight imbalance. Then, in the staged combustion, the proportion of secondary air is increased, and the proportion of secondary air in the total air volume is increased by 3%-5%. The distribution of secondary air at different heights or areas is adjusted, and the air volume of the upper secondary air is increased by 5%-8%, and the air volume of the lower secondary air is reduced by 3%-5%. In the ammonia injection optimization, the ammonia injection amount is increased by 2%-5%, and the position of the ammonia injection is adjusted, and the ammonia injection port is appropriately moved 5-10 cm toward the combustion center area. In the soot suppression, the soot generation is suppressed by increasing the steam injection amount, and the steam injection amount is increased by 5%-10%. The amount of combustion aid added is increased by 3%-5%.

[0045] C2. If the corresponding pulverized coal combustion dynamic imbalance in a combustion chamber of a target power plant at a certain monitoring point is present, and the corresponding pulverized coal combustion dynamic assessment value in the combustion chamber of the target power plant at the monitoring point is between 10% and 20% greater than the corresponding pulverized coal combustion dynamic assessment value in the set standard combustion chamber, it is recorded as a moderate imbalance. In staged combustion, the proportion of secondary air in the total air volume is increased by 8%-12%, and the distribution of secondary air at different heights or areas is adjusted, with the upper secondary air volume increased by 15%-20% and the lower secondary air volume reduced by 10%-15%. In ammonia injection optimization, the ammonia injection amount is increased by 8%-12%, and the ammonia injection mode is changed from continuous injection to pulse injection. The frequency of pulse injection is set to 1-2 times per second, and the duration of each injection is 0.5-1 second. In soot suppression, the steam injection amount is increased by 15%-20%, and the amount of combustion aid added is increased by 10%-15%.

[0046] C3. If the corresponding pulverized coal combustion in a combustion chamber of a target power plant at a certain monitoring point is dynamically unbalanced, and the corresponding pulverized coal combustion dynamic assessment value of the target power plant at the monitoring point is more than 20% greater than the corresponding pulverized coal combustion dynamic assessment value of the set standard combustion chamber, it is recorded as a serious imbalance. In the staged combustion, the proportion of secondary air is increased by 15%-20% of the proportion of secondary air in the total air volume, the lower secondary air is closed, and the air volume of the upper secondary air is increased by 30%-40%. In the ammonia injection optimization, the ammonia injection amount is increased by 20%-30%, ammonia injection ports are set in the upper, middle and lower areas of the combustion chamber respectively, and ammonia injection is carried out simultaneously in the three areas of the combustion chamber. In the soot suppression, the steam injection amount is increased by 30%-40%, and a high-efficiency soot inhibitor is added, and the added amount is 0.5%-1% of the mass of the pulverized coal.

[0047] Creep damage assessment value analysis module: used to set several damage assessment time points when each combustion chamber of the target power plant is in operation, and then analyze the creep damage assessment value corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point.

[0048] In a specific embodiment, the creep damage assessment value corresponding to each component in each combustion chamber of the target power plant is analyzed at each damage assessment time point. The specific analysis process is as follows: the fundamental frequency ultrasonic signal and the second harmonic signal corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point are obtained by a high-temperature resistant piezoelectric composite material sensor, and then the fundamental frequency amplitude corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point is recorded. , second harmonic amplitude and fundamental wavelength At the same time, the temperature of each component in each combustion chamber of the target power plant at each damage assessment time point is collected from the DCS system of the thermal power equipment. ,stress and runtime , where m represents the number corresponding to each combustion chamber, , b is any integer greater than 2, k represents the number corresponding to each damage assessment time point, , q is any integer greater than 2, h represents the number corresponding to each component, , y is any integer greater than 2, substitute into the calculation formula: The creep damage assessment values corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point are obtained, where a, b, c, and d are all fitting coefficients. is a natural constant.

[0049] It should be noted that multi-dimensional data fusion analysis utilizes high-temperature resistant piezoelectric composite sensors to acquire fundamental frequency ultrasonic signals and second harmonic signals, recording the fundamental frequency amplitude, second harmonic amplitude, and fundamental frequency wavelength. Ultrasonic signals are sensitive to changes in the component's internal microstructure. Different degrees of creep damage will cause changes in the ultrasonic signal characteristics. These signal parameters can reflect damage-related information such as lattice distortion and dislocations within the component material at a microscopic level. Temperature, stress, and operating time are collected from the thermal power equipment DCS system. Temperature and stress are key external factors that cause component creep, while operating time accumulates creep damage effects. Multi-dimensional data fusion comprehensively considers both internal and external factors influencing component creep damage, resulting in a more accurate assessment. A specific calculation formula is used to generate a creep damage assessment value, transforming complex multi-source data into a quantitative indicator. This allows power plant personnel to intuitively understand the creep damage extent of each combustor component at different damage assessment time points, facilitating the timely identification of severely damaged components and providing a clear basis for decision-making regarding repair and replacement. The fitting coefficients in the formula can be adjusted and calibrated based on the material properties of individual combustor components and actual operating conditions. It can better adapt to different types of components and different operating environments, making the evaluation model more realistic and improving the versatility and accuracy of the evaluation scheme.

[0050] Hidden damage risk assessment module: used to determine the risk level of hidden damage corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point based on the creep damage assessment value corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point.

[0051] In a specific embodiment, the hidden damage risk level corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point is determined, and the specific judgment process is as follows: the creep damage assessment value corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point is compared with the creep damage assessment value interval corresponding to each set hidden damage risk level. If the creep damage assessment value corresponding to a component in a combustion chamber of the target power plant at a certain damage assessment time point is within the creep damage assessment value interval corresponding to a set hidden damage risk level, then the set hidden damage risk level is recorded as the hidden damage risk level corresponding to the component in the combustion chamber of the target power plant at the damage assessment time point.

[0052] It should be noted that the risk levels of latent injuries include: Level I, Level II, Level III and Level IV.

[0053] It's also important to note that when a component is in a safe state (Level I), operations and maintenance primarily focus on routine monitoring and basic maintenance. Daily ultrasonic testing and DCS data logging are maintained, with weekly historical data archiving implemented to provide a solid data foundation for trend analysis. Surface cleaning is also carried out according to a pre-defined schedule, the integrity of the anti-corrosion coating is carefully inspected, and component health records are promptly updated and marked as "normal" to ensure stable equipment operation. When a component reaches a low-risk alert (Level II), the operations and maintenance strategy shifts to enhanced monitoring and preventive maintenance planning. Inspection frequency is increased to once an hour, focusing on tracking the rate of change of the β and D values. Vibration and acoustic emission monitoring are also implemented to assist in verifying damage trends. During this phase, spare parts such as sealing gaskets and vulnerable sensors are stockpiled in advance, a preliminary maintenance plan is developed, and a list of potential replacement parts is compiled to proactively plan for subsequent maintenance. When a component reaches a medium-risk alert (Level III), a multi-pronged approach is required to mitigate damage risk. On the one hand, they applied to reduce the equipment load to 70% of the rated power, strictly controlling the number of starts and stops to reduce thermal fatigue. On the other hand, they seized the downtime window, used a metallographic microscope to detect microscopic cracks, and performed hardness gradient tests to assess the extent of material degradation. In addition, a special emergency repair team was established with clear division of labor to ensure that repair tools and special welding consumables were readily available within 48 hours, establishing a complete emergency response system. When a component encounters a high-risk emergency (Level IV), operations and maintenance must immediately initiate the emergency response process. The shutdown procedure was quickly triggered, the fuel supply was cut off, forced cooling was implemented, and the faulty component was isolated and a warning sign was set up. During the emergency repair phase, the damaged component was removed first to conduct fracture SEM analysis to locate the root cause of the failure. Key components such as turbine blades and pipe elbows were simultaneously replaced, and the structure was restored using a rapid welding process. Afterwards, a comprehensive screening of components from the same batch and under the same operating conditions was carried out, the monitoring model parameters were revised, and the warning thresholds were optimized to achieve an upgrade in systemic risk management.

[0054] The present invention is implemented as follows Figure 2 As shown, the abnormality analysis method of a smart power plant based on the power Internet of Things includes: Step 1, micro-dynamic monitoring: configuring micro-hardware in each combustion chamber of the target power plant, so as to evaluate whether the corresponding coal powder combustion dynamics in each combustion chamber of the target power plant are unbalanced at each monitoring point.

[0055] Step 2: Analysis of control strategy: When the pulverized coal combustion in a combustion chamber of a target power plant at a certain monitoring point is dynamically unbalanced, the control strategy corresponding to the combustion chamber of the target power plant at the monitoring point is analyzed.

[0056] Step 3: Analysis of creep damage assessment values: When each combustion chamber of the target power plant is in operation, several damage assessment time points are set, and then the creep damage assessment values corresponding to each component in each combustion chamber of the target power plant are analyzed at each damage assessment time point.

[0057] Step 4. Assessment of hidden damage risk: Based on the creep damage assessment value corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point, the risk level of hidden damage corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point is determined.

[0058] 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. The smart power plant abnormality analysis system based on the power Internet of Things is characterized by: include: Micro-dynamic monitoring module: used to configure micro-hardware in each combustion chamber of the target power plant, so as to evaluate whether the corresponding pulverized coal combustion dynamics in each combustion chamber of the target power plant are unbalanced at each monitoring point; Control strategy analysis module: when the dynamic imbalance of pulverized coal combustion in a combustion chamber of a target power plant at a certain monitoring point is detected, the corresponding control strategy of the combustion chamber of the target power plant at that monitoring point is analyzed; Creep damage assessment value analysis module: used to set several damage assessment time points when each combustion chamber of the target power plant is in operation, and then analyze the creep damage assessment value corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point; Hidden damage risk assessment module: used to determine the risk level of hidden damage corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point based on the creep damage assessment value corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point.

2. The smart power plant abnormality analysis system based on the power Internet of Things according to claim 1 is characterized in that: The micro hardware is configured in each combustion chamber of the target power plant. The specific configuration process is as follows: A1. Obtain the number of abnormal operating conditions corresponding to each combustion chamber of the target power plant, and compare the number of abnormal operating conditions corresponding to each combustion chamber of the target power plant with each set threshold value; A2. If the number of abnormal operating conditions corresponding to each combustion chamber of the target power plant is within the first threshold, the microwave resonance imaging equipment frequency range is selected to be 2-5 GHz, the power is selected to be 1-5 W, the scanning range covers 60%-80% of the transmission pipeline cross-section, the spatial resolution is selected to be 5-10 mm, the CCD camera frame rate is selected to be 25-50 frames / second, the pixel size is selected to be 1024×768-2048×1536, the sensitivity is selected to be 800-1600, the TDLAS sensor wavelength range is selected to be 1.3-1.4 μm, the CH free radical wavelength range can be selected to be 3.2-3.4 μm, the accuracy is ±5%, the measurement range is 0-100 ppm, and the UV imager wavelength range is selected to be 200-400 nm, the resolution is selected to be 320×240-640×480, and the dynamic range is selected to be 10-10,000 lux; A3. If the number of abnormal operating conditions corresponding to each combustion chamber of the target power plant is between the first and second thresholds, the microwave resonance imaging equipment frequency range is selected to be 5-10 GHz, the power is 5-10 W, the scanning range covers 80%-90% of the transmission pipeline cross-section, and the spatial resolution reaches 2-5 mm. The ultra-high-speed CCD camera is selected to have a frame rate of 100-200 frames per second, a pixel size of 2048×1536-4096×3072, and a sensitivity of 1600-3200. The humidity sensor is selected to have a measurement range of 0-20% RH and an accuracy of ±1% RH. The TDLAS sensor is selected to have a wavelength range of 1.3-1.4 μm, a spacing of 5-10 cm between adjacent sensors, an accuracy improved to ±3%, and a measurement range of 0-50 ppm. The resolution of the UV imager is increased to 640×480-1024×768, and a dynamic range of 5-50,000 lux. A4. If the number of abnormal operating conditions corresponding to each combustion chamber of the target power plant is greater than the second threshold, the microwave resonance imaging equipment shall have a frequency range of 10-20 GHz, a power of 10-20 W, a scanning range that completely covers the cross-section of the transmission pipeline, and a spatial resolution of 1-2 mm. The ultra-high-speed CCD camera shall have a frame rate of 500-1000 frames per second, a pixel size of 4096×3072-8192×6144, and a sensitivity of 3200-6400. The data analysis system shall have the ability to process 10-100 GB of data per second, adopt a parallel computing architecture, and have a data storage capacity of 1-10 TB. The TDLAS sensor shall have a wavelength range of 1.5-1.6 μm, a spacing of 2-5 cm between adjacent sensors, an accuracy of ±1%, a measurement range of 0-20 ppm, and a response time of less than 10 ms. The ultraviolet imager shall have a resolution of 1024×768-2048×1536 and a dynamic range of 1-100,000 lux.

3. The smart power plant abnormality analysis system based on the power Internet of Things according to claim 2 is characterized in that: The microscopic dynamic monitoring module also includes a pulverized coal combustion dynamic evaluation value analysis unit: The pulverized coal combustion dynamic evaluation value analysis unit is used to obtain the pulverized coal fluidization uniformity evaluation value and flame free radical evaluation value corresponding to each combustion chamber of the target power plant at each monitoring point, and record them as and , where n represents the number corresponding to each monitoring point, , w is any integer greater than 2, m represents the number corresponding to each combustion chamber, , r is any integer greater than 2, and then the corresponding pulverized coal combustion dynamic evaluation value in each combustion chamber of the target power plant at each monitoring point is obtained by analysis.

4. The smart power plant abnormality analysis system based on the power Internet of Things according to claim 3 is characterized in that: The analysis obtains the corresponding pulverized coal combustion dynamic assessment value in each combustion chamber of the target power plant at each monitoring point. The specific analysis process is as follows: Substitute the pulverized coal fluidization uniformity assessment value and flame free radical assessment value corresponding to each combustion chamber of the target power plant at each monitoring point into the calculation formula: The dynamic evaluation value of pulverized coal combustion in each combustion chamber of the target power plant at each monitoring point is obtained. ,in, and They are the standard pulverized coal fluidization uniformity evaluation value and the standard flame free radical evaluation value corresponding to the set combustion chamber, Indicates the temperature corresponding to each combustion chamber of the target power plant at each monitoring point, It represents the average temperature of each combustion chamber of the target power plant during the historical period.

5. The smart power plant abnormality analysis system based on the power Internet of Things according to claim 4 is characterized in that: The specific acquisition process of obtaining the pulverized coal fluidization uniformity evaluation value and the flame free radical evaluation value corresponding to each combustion chamber of the target power plant at each monitoring point is as follows: B1. Obtain the corresponding pulverized coal fluidization index and flame free radical index for each combustion chamber of the target power plant at each monitoring point. The pulverized coal fluidization index includes the pulverized coal concentration uniformity index, the average velocity of the pulverized coal particles, and the pulverized coal particle size distribution range. The flame free radical index includes the soot concentration, the average soot particle size, and the combustion concentration corresponding to each free radical. B2. The pulverized coal concentration uniformity index, average velocity of pulverized coal particles, and pulverized coal particle size distribution range corresponding to each combustion chamber of each target power plant at each monitoring point are used as input information and normalized. At the same time, they are entered into the pulverized coal fluidization uniformity assessment value analysis model. After calculation and analysis by the pulverized coal fluidization uniformity assessment value analysis model, the pulverized coal fluidization uniformity assessment value corresponding to each combustion chamber of each target power plant at each monitoring point is finally output. ; B3. The soot concentration, average soot particle size, and combustion concentration of each free radical corresponding to each combustion chamber of each target power plant at each monitoring point are used as input information and normalized. At the same time, they are entered into the flame free radical evaluation value analysis model. After calculation and analysis by the flame free radical evaluation value analysis model, the flame free radical evaluation value corresponding to each combustion chamber of each target power plant at each monitoring point is finally output. .

6. The smart power plant abnormality analysis system based on the power Internet of Things according to claim 5 is characterized in that: The specific evaluation process of evaluating whether the corresponding pulverized coal combustion dynamics in each combustion chamber of the target power plant are unbalanced at each monitoring point is as follows: The pulverized coal combustion dynamic evaluation value corresponding to each combustion chamber of the target power plant at each monitoring point is compared with the pulverized coal combustion dynamic evaluation value corresponding to the set standard combustion chamber. If the pulverized coal combustion dynamic evaluation value corresponding to a combustion chamber of the target power plant at a monitoring point is less than the pulverized coal combustion dynamic evaluation value corresponding to the set standard combustion chamber, it is assessed that the pulverized coal combustion dynamics corresponding to the combustion chamber of the target power plant at the monitoring point is not unbalanced. If the pulverized coal combustion dynamic evaluation value corresponding to a combustion chamber of the target power plant at a monitoring point is greater than or equal to the pulverized coal combustion dynamic evaluation value corresponding to the set standard combustion chamber, it is assessed that the pulverized coal combustion dynamics corresponding to the combustion chamber of the target power plant at the monitoring point is unbalanced.

7. The smart power plant abnormality analysis system based on the power Internet of Things according to claim 6 is characterized in that: The control strategy corresponding to the combustion chamber of the target power plant at the monitoring point is analyzed, and the specific analysis process is as follows: C1. If the pulverized coal combustion in a combustion chamber of a target power plant at a certain monitoring point is dynamically unbalanced, and the dynamic assessment value of the pulverized coal combustion in the combustion chamber of the target power plant at the monitoring point is within 10% of the dynamic assessment value of the pulverized coal combustion in the set standard combustion chamber, it is recorded as a slight imbalance. In staged combustion, the proportion of secondary air is increased by 3%-5% of the proportion of secondary air in the total air volume. The distribution of secondary air at different heights or areas is adjusted by increasing the volume of the upper secondary air by 5%-8% and reducing the volume of the lower secondary air by 3%-5%. In ammonia injection optimization, the ammonia injection volume is increased by 2%-5%. The position of ammonia injection is adjusted by moving the ammonia injection port 5-10 cm toward the combustion center. In soot suppression, soot generation is suppressed by increasing the steam injection volume by 5%-10%. The amount of combustion aid added is increased by 3%-5%. C2. If the pulverized coal combustion in a combustion chamber of a target power plant at a certain monitoring point is dynamically unbalanced, and the dynamic evaluation value of the pulverized coal combustion in the combustion chamber of the target power plant at the monitoring point is between 10% and 20% greater than the dynamic evaluation value of the pulverized coal combustion in the set standard combustion chamber, it is recorded as a moderate imbalance. In staged combustion, the proportion of secondary air in the total air volume is increased by 8%-12%, and the distribution of secondary air at different heights or areas is adjusted. The air volume of the upper secondary air is increased by 15%-20%, and the air volume of the lower secondary air is reduced by 10%-15%. In ammonia injection optimization, the ammonia injection amount is increased by 8%-12%, and the ammonia injection mode is changed from continuous injection to pulse injection. The frequency of pulse injection is set to 1-2 times per second, and the duration of each injection is 0.5-1 second. In soot suppression, the steam injection amount is increased by 15%-20%, and the amount of combustion aid added is increased by 10%-15%. C3. If the corresponding pulverized coal combustion in a combustion chamber of a target power plant at a certain monitoring point is dynamically unbalanced, and the corresponding pulverized coal combustion dynamic assessment value of the target power plant at the monitoring point is more than 20% greater than the corresponding pulverized coal combustion dynamic assessment value of the set standard combustion chamber, it is recorded as a serious imbalance. In the staged combustion, the proportion of secondary air is increased by 15%-20% of the proportion of secondary air in the total air volume, the lower secondary air is closed, and the air volume of the upper secondary air is increased by 30%-40%. In the ammonia injection optimization, the ammonia injection amount is increased by 20%-30%, ammonia injection ports are set in the upper, middle and lower areas of the combustion chamber respectively, and ammonia injection is carried out simultaneously in the three areas of the combustion chamber. In the soot suppression, the steam injection amount is increased by 30%-40%, and a high-efficiency soot inhibitor is added, and the added amount is 0.5%-1% of the mass of the pulverized coal.

8. The smart power plant abnormality analysis system based on the power Internet of Things according to claim 1 is characterized in that: The creep damage assessment value corresponding to each component in each combustion chamber of the target power plant is analyzed at each damage assessment time point. The specific analysis process is as follows: The fundamental frequency ultrasonic signal and second harmonic signal corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point are obtained through the high-temperature resistant piezoelectric composite sensor, and then the fundamental frequency amplitude corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point is recorded. , second harmonic amplitude and fundamental wavelength At the same time, the temperature of each component in each combustion chamber of the target power plant at each damage assessment time point is collected from the DCS system of the thermal power equipment. ,stress and runtime , where m represents the number corresponding to each combustion chamber, , b is any integer greater than 2, k represents the number corresponding to each damage assessment time point, , q is any integer greater than 2, h represents the number corresponding to each component, , y is any integer greater than 2, substitute into the calculation formula: The creep damage assessment values corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point are obtained, where a, b, c, and d are all fitting coefficients. is a natural constant.

9. The smart power plant abnormality analysis system based on the power Internet of Things according to claim 8, characterized in that: The specific judgment process for determining the risk level of hidden damage corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point is as follows: The creep damage assessment value corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point is compared with the creep damage assessment value interval corresponding to each set hidden damage risk level. If the creep damage assessment value corresponding to a component in a combustion chamber of the target power plant at a certain damage assessment time point is within the creep damage assessment value interval corresponding to a set hidden damage risk level, the set hidden damage risk level will be recorded as the hidden damage risk level corresponding to the component in the combustion chamber of the target power plant at the damage assessment time point.

10. A method for analyzing abnormalities in a smart power plant based on the power Internet of Things, which executes the abnormality analysis system for a smart power plant based on the power Internet of Things according to any one of claims 1 to 9, characterized in that: include: Step 1: Micro-dynamic monitoring: Micro-hardware is deployed in each combustion chamber of the target power plant to assess whether the corresponding pulverized coal combustion dynamics in each combustion chamber of the target power plant are unbalanced at each monitoring point; Step 2: Analysis of control strategy: When the pulverized coal combustion in a combustion chamber of a target power plant at a certain monitoring point is dynamically unbalanced, the control strategy corresponding to the combustion chamber of the target power plant at the monitoring point is analyzed; Step 3: Analysis of creep damage assessment values: When each combustion chamber of the target power plant is in operation, several damage assessment time points are set, and then the creep damage assessment values corresponding to each component in each combustion chamber of the target power plant are analyzed at each damage assessment time point; Step 4. Assessment of hidden damage risk: Based on the creep damage assessment value corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point, the risk level of hidden damage corresponding to each component in each combustion chamber of the target power plant at each damage assessment time point is determined.

Images