Method and system for evaluating running state of deep peak regulation process of fluidized bed unit

Abstract

The invention discloses an operation state evaluation method and system for the deep peak regulation process of a fluidized bed unit, and relates to the technical field of fluidized beds, and the method comprises the steps: collecting the combustion condition data of the deep peak regulation process of the fluidized bed unit; generating a particle flow velocity vector diagram, and identifying and marking different flow modes and paths in the particle flow velocity vector diagram; generating a non-uniform index of the whole flow field through particle flow velocity and particle concentration distribution of each flow mode area in the flow field; generating a bed temperature distribution diagram, recognizing a high temperature-flow mode region by combining with the particle flow velocity vector diagram, and calculating a coking risk index of the high temperature-flow mode region; and calculating a coking risk index of the whole flow field, comparing the coking risk index of the whole flow field with a risk threshold value, and when the coking risk index of the whole flow field is greater than or equal to the risk threshold value, giving out an early warning, identifying potential risks, and avoiding serious problems such as coking.

Description

Technical Field

[0001] The present invention relates to the technical field of fluidized bed, and particularly to a method and system for evaluating the operating state during the deep peak shaving process of a fluidized bed unit. Background Art

[0002] In recent years, new energy power generation such as wind power and photovoltaic power has been vigorously developed. However, the supply of new energy power has inherent characteristics such as intermittency, volatility, and seasonality, which puts higher requirements on the regulation and consumption capacity of the power grid. Due to advantages such as wide fuel adaptability, high combustion efficiency, low stable combustion load, and low pollutant control cost, fluidized bed units have become important objects for thermal power flexibility transformation.

[0003] In the Chinese invention application with the publication number of CN116663776A, a method and system for determining the deep peak shaving ability of a circulating fluidized bed boiler are disclosed. Step 1: Under the deep peak shaving operating state of the circulating fluidized bed boiler unit, determine the main parameter set for determining the deep peak shaving ability of the circulating fluidized bed boiler unit; Step 2: Analyze and determine the determination method and range of each determination parameter index; Step 3: Determine the deep peak shaving ability of the circulating fluidized bed boiler unit. By establishing a comprehensive determination system, accurately determine the deep peak shaving ability of the circulating fluidized bed boiler, so that the circulating fluidized bed unit can better meet the requirements of grid-source coordinated and safe operation under future high-proportion new energy conditions.

[0004] However, during the deep peak shaving operation, with the dynamic change of the load, the flow pattern of the fluid also undergoes complex changes, which makes the current monitoring strategies for static and fixed areas in the current technology seem inadequate and no longer able to effectively adapt. Especially when the load decreases, the flow characteristics and distribution state of the particles inside the bed layer may tend to be more uneven, and the phenomena of channeling and uneven flow are likely to be significantly enhanced. The direct consequence of this uneven flow is that the particle concentration in local areas abnormally increases, forming so-called "hot spot" areas, which are extremely likely to become the breeding ground for coking problems, thus posing a serious threat to the stable operation of the system. Summary of the Invention

[0005] (1) Technical Problems to be Solved

[0006] Aiming at the deficiencies of the prior art, the present invention provides a method and system for evaluating the operating state during the deep peak shaving process of a fluidized bed unit. By the particle flow velocity and particle concentration distribution during the deep peak shaving process of the fluidized bed unit, different flow patterns and paths in the particle flow velocity vector diagram are identified and marked, and combined with the bed layer temperature distribution, the coking risk of the entire flow field is analyzed to identify potential risks and avoid the occurrence of serious problems such as coking.

[0007] (2) Technical Solutions

[0008] To achieve the above objectives, the present invention is realized through the following technical solutions: A method for evaluating the operating state during the deep peak shaving process of a fluidized bed unit, comprising the following steps:

[0009] Collect the combustion condition data during the deep peak shaving process of the fluidized bed unit;

[0010] Obtain the particle flow velocity data during the deep peak shaving process of the fluidized bed unit, generate a particle flow velocity vector diagram, and identify and mark different flow patterns and paths in the particle flow velocity vector diagram;

[0011] According to the identified flow patterns, divide the flow field into different flow pattern regions, and obtain the non-uniformity index of the entire flow field through the particle flow velocity and particle concentration distribution in each flow pattern region of the flow field;

[0012] Obtain the bed temperature data during the deep peak shaving process of the fluidized bed unit, generate a bed temperature distribution diagram, combine it with the particle flow velocity vector diagram, identify the high-temperature - flow pattern region, and calculate the coking risk index of the high-temperature - flow pattern region;

[0013] Integrate the non-uniformity index of the entire flow field and the coking risk indices of all high-temperature - flow pattern regions, calculate the coking risk index of the entire flow field, compare the coking risk index of the entire flow field with the risk threshold, and issue a warning when the coking risk index of the entire flow field is greater than or equal to the risk threshold.

[0014] Further, the collection of the combustion condition data includes: arranging a number of temperature measuring points at different heights and regions of the fluidized bed, using thermocouples to monitor the change of the bed temperature; measuring the flow velocity of the particles in the fluidized bed through a laser Doppler velocimeter; and using an optical probe to monitor the particle concentration in the fluidized bed in real time.

[0015] Further, the generation of the particle flow velocity vector diagram includes: mapping the particle flow velocity data onto a grid model, where each grid point corresponds to the position coordinates and velocity vectors of different particles, and using a spatial interpolation algorithm to fill the grid points with missing particle flow velocity data to obtain the particle flow velocity vector diagram.

[0016] Further, identifying and marking different flow patterns and paths in the particle flow velocity vector diagram includes:

[0017] Adopt a local window to extract the velocity vector features of each grid point and the window area, perform pattern recognition on the extracted velocity vector features through a machine learning algorithm, and classify different flow patterns in the flow field;

[0018] Adopt a streamline tracing algorithm to generate the flow paths in the flow field, and mark the traced flow paths according to the classification results of the flow patterns.

[0019] Furthermore, for each flow pattern region, the average particle flow velocity is calculated, and by calculating the ratio between the maximum and minimum values of the average particle flow velocities in all flow pattern regions, the non-uniformity index of the particle flow velocity in the entire flow field is obtained;

[0020] Furthermore, the particle concentration distribution data during the deep peak shaving process of the fluidized bed unit is obtained. For each flow pattern region, the average particle concentration is calculated, and by calculating the ratio between the maximum and minimum values of the average particle concentrations in all flow pattern regions, the non-uniformity index of the particle concentration distribution in the entire flow field is obtained;

[0021] Combining the non-uniformity index of the particle flow velocity and the non-uniformity index of the particle concentration distribution in the entire flow field, the non-uniformity index of the entire flow field is calculated by the geometric mean method.

[0022] Furthermore, the generation of the bed temperature distribution map includes: mapping the temperature data onto the grid model of the fluidized bed, where each grid point corresponds to different position coordinates and its temperature value. For grid points with missing temperature data, spatial interpolation algorithms are used for filling to obtain the bed temperature distribution map.

[0023] Furthermore, the identification process of the high-temperature - flow pattern region includes:

[0024] Based on the temperature values of each grid point, the average temperature and standard deviation of the bed temperature are calculated. The sum of the average temperature and the standard deviation is used as the temperature threshold. The region with a temperature higher than the temperature threshold is marked as the local high-temperature region. The bed temperature distribution map and the particle flow velocity vector map are superimposed to determine and mark the flow pattern region corresponding to the local high-temperature region, which is marked as the high-temperature - flow pattern region.

[0025] Furthermore, the generation of the coking risk index for the high-temperature - flow pattern region includes:

[0026] By spatially matching, the particle concentration distribution data and the bed temperature data of each high-temperature - flow pattern region are integrated. The average particle concentration and the average temperature of the marked high-temperature - flow pattern region are calculated, and the product of the average particle concentration and the average temperature is used as the coking risk index for this high-temperature - flow pattern region.

[0027] Furthermore, the calculation formula for the coking risk index of the entire flow field is as follows:

[0028]

[0029] where Cr represents the coking risk index of the entire flow field, U represents the non-uniformity index of the entire flow field, Cr kdenotes the coking risk index of the k-th high-temperature - flow pattern region, ω k denotes the weight of the k-th high-temperature - flow pattern region, where the weight is the ratio of the area of the k-th high-temperature - flow pattern region to the total area of all high-temperature - flow pattern regions, and k = 1, 2, …, K, where K represents the number of high-temperature - flow pattern regions.

[0030] An operating state evaluation system for a fluidized bed unit during deep peak shaving process, comprising:

[0031] A data acquisition module that acquires combustion condition data during the deep peak shaving process of the fluidized bed unit;

[0032] A particle flow analysis module that obtains particle flow velocity data during the deep peak shaving process of the fluidized bed unit, generates a particle flow velocity vector diagram, and identifies and marks different flow patterns and paths in the particle flow velocity vector diagram;

[0033] A flow field uniformity analysis module that divides the flow field into different flow pattern regions according to the identified flow patterns, and obtains the non-uniformity index of the entire flow field through the particle flow velocity and particle concentration distributions in each flow pattern region in the flow field;

[0034] A coking risk assessment module that obtains the bed temperature data during the deep peak shaving process of the fluidized bed unit, generates a bed temperature distribution diagram, combines it with the particle flow velocity vector diagram, identifies the high-temperature - flow pattern regions, and calculates the coking risk index of the high-temperature - flow pattern regions;

[0035] An early warning module that comprehensively calculates the coking risk index of the entire flow field based on the non-uniformity index of the entire flow field and the coking risk indices of all high-temperature - flow pattern regions, compares the coking risk index of the entire flow field with the risk threshold, and issues an early warning when the coking risk index of the entire flow field is greater than or equal to the risk threshold.

[0036] (3) Beneficial effects

[0037] The present invention provides an operating state evaluation method and system for a fluidized bed unit during deep peak shaving process, having the following beneficial effects:

[0038] (1) By generating a particle flow velocity vector diagram, it can monitor the flow state and change trend of particles in the fluidized bed in real time, identify and mark different flow patterns and paths, such as eddy currents, main flows, and backflows, and can timely detect potential uneven fluidization phenomena such as channeling and uneven flow, so as to give an early warning and take corresponding measures.

[0039] (2) The non-uniformity index of the entire flow field can be used to evaluate the non-uniformity of the flow field in the fluidized bed during the deep peak shaving process, including two aspects: the particle flow velocity and the particle concentration distribution. Thus, a more comprehensive understanding of the actual state of the flow field can be achieved. After dividing the flow field into different flow pattern regions and conducting specific analysis for each region, it helps to accurately identify the regions with problems in the flow field, such as regions with too fast or too slow particle flow velocity, or too high or too low particle concentration.

[0040] (3) By mapping the bed temperature data onto the grid model, the local high-temperature regions in the fluidized bed can be accurately identified, which helps to timely detect potential hot spots and take corresponding measures to prevent adverse situations such as coking. By calculating the coking risk index of the high-temperature - flow pattern region, the coking risk degree of this region can be more accurately reflected, and then targeted adjustments and optimizations can be carried out.

[0041] (4) By calculating the coking risk index of the entire flow field, the operating state and potential risks of the fluidized bed unit during the deep peak shaving process can be comprehensively reflected. When the coking risk index exceeds the preset risk threshold, an alarm is issued to timely remind relevant personnel to take measures, thus effectively avoiding the occurrence of serious problems such as coking. Description of the Drawings

[0042] Figure 1 Schematic diagram of the method for evaluating the operating state of the fluidized bed unit during the deep peak shaving process of the present invention;

[0043] Figure 2 Schematic diagram of the system for evaluating the operating state of the fluidized bed unit during the deep peak shaving process of the present invention. Detailed Embodiment

[0044] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0045] Please refer to Figure 1 , the present invention provides a method for evaluating the operating state of a fluidized bed unit during the deep peak shaving process, including the following steps:

[0046] Step 1: Collect the combustion condition data of the fluidized bed unit during the deep peak shaving process, including but not limited to bed temperature, pressure distribution, particle flow velocity, particle concentration distribution, fuel input, air flow rate, bed height and fluctuations;

[0047] The said Step 1 includes:

[0048] Step 101: Arrange several temperature measuring points at different heights and regions of the fluidized bed, and use equipment such as thermocouples or infrared thermometers to monitor the change of the bed temperature; measure the flow velocity of particles at the key cross-sections of the fluidized bed through a Laser Doppler Anemometer (LDA) or other non-contact velocity measurement techniques; use techniques such as optical probes and Electrical Capacitance Tomography (ECT) to monitor the particle concentration in the fluidized bed in real time;

[0049] Step 102: Install flow meters in the fuel input system to record the real-time data of the fuel input; install flow meters in the air supply system to monitor the air flow changes in different air ducts; obtain the change and fluctuation of the bed height in real time through a bed height measuring device (such as an ultrasonic rangefinder);

[0050] It should be noted that when arranging the temperature measuring points and selecting the velocity measurement and concentration monitoring techniques, the specific structure and operating conditions of the fluidized bed unit need to be considered. The positions of the temperature measuring points should be able to comprehensively reflect the change of the bed temperature, avoiding neglecting local overheating or temperature non-uniform areas. At the same time, the measurement of the particle flow velocity and concentration distribution should cover the entire fluidized bed as much as possible to obtain comprehensive particle motion information;

[0051] Step 103: Set the data acquisition frequency and period. For parameters that require simple measurement means such as temperature and pressure, adopt a high-frequency acquisition method, such as acquiring once or multiple times per second. For parameters that require complex measurement means such as particle flow velocity and concentration distribution, set a periodic acquisition plan, such as acquiring once per hour or adjusting according to the operating conditions;

[0052] When in use, combine the content of Step 101 to Step 103:

[0053] By acquiring key parameters such as the bed temperature, pressure distribution, particle flow velocity, and particle concentration distribution, it is possible to grasp the operating state of the fluidized bed unit in the deep peak shaving process in real time, which helps to timely discover potential operating problems, such as abnormal temperature, pressure fluctuation, and poor particle flow, so as to take corresponding measures for treatment to ensure the stable operation of the unit.

[0054] Step Two: Obtain the particle flow velocity data of the fluidized bed unit in the deep peak shaving process, generate a particle flow velocity vector diagram, and identify and mark different flow patterns and paths in the particle flow velocity vector diagram;

[0055] The said Step Two includes:

[0056] Step 201: Obtain the particle flow velocity data during the deep peak shaving process of the fluidized bed unit, and preprocess the particle flow velocity data, including cleaning, removing outliers and noise. Map the particle flow velocity data onto the grid model. Each grid point corresponds to the position coordinates and velocity vectors (including velocity magnitude and direction) of different particles. For grid points with missing data, use a spatial interpolation algorithm (such as linear interpolation) to fill them, and generate a particle flow velocity vector diagram;

[0057] It should be noted that the grid model divides the fluidized bed into several regular grid cells according to its actual size and shape. Each grid point has a clear coordinate position. Map the collected bed temperature data onto the grid model, and each grid point corresponds to a temperature value;

[0058] Step 202: Adopt a local window to extract the velocity vector features of each grid point and within the window area. Use machine learning algorithms (such as support vector machines, decision trees, etc.) to perform pattern recognition on the extracted velocity vector features, and classify different flow patterns in the flow field. For example, identify eddies by recognizing the rotation direction and intensity of the velocity vectors; identify the main flow by tracing the main flow direction of the velocity vectors; identify backflows by detecting velocity vectors opposite to the main flow direction, etc.;

[0059] It should be noted that the local window refers to a small and limited spatial range selected for detailed analysis of a specific area in the analysis of flow field data. This range contains multiple grid points, and each grid point corresponds to a specific position in the flow field;

[0060] It should be noted that the main flow is the main flow path in the flow field. In the velocity vector diagram, the velocity is usually large and the direction is relatively consistent. By the magnitude and direction distribution of the velocity vectors, the main flow area can be identified. The vector diagram of the main flow area usually shows continuous and consistent arrows;

[0061] An eddy is a rotational flow in the flow field. The velocity vectors will show circular motion or spiral motion around a certain center in the eddy area. In the velocity vector diagram, the eddy area is shown as a pattern where the vector arrows rotate around a certain center. The existence and intensity of the eddy can be judged by the rotation direction and velocity magnitude of the vector arrows;

[0062] Backflow refers to the situation where part of the fluid in the flow field flows in the direction opposite to the main flow. In the velocity vector diagram, the backflow area is shown as vector arrows opposite to the main flow direction. These arrows may form obvious reverse flow paths or may form a certain angle with the main flow direction;

[0063] Step 203: Use streamline tracking algorithms (such as streamline and pathline algorithms) to generate flow paths in the flow field. According to the classification results of flow patterns, label the tracked flow paths. For example, mark the main flow path with a specific color or line type, mark the vortex path as a closed curve around a certain center, mark the recirculation path as a line segment opposite to the main flow direction, etc.;

[0064] During use, combine the content of Steps 201 to 203:

[0065] By generating a particle flow velocity vector map, the flow state and change trend of particles in the fluidized bed can be monitored in real time, and different flow patterns and paths, such as vortices, main flows, and recirculations, can be identified and labeled, enabling the timely detection of potential uneven fluidization phenomena such as channeling and preferential flow, and thus giving early warnings and taking corresponding measures.

[0066] Step Three: Divide the flow field into different flow pattern regions according to the identified flow patterns, and generate the non-uniformity index of the entire flow field based on the particle flow velocity and particle concentration distributions in each flow pattern region of the flow field;

[0067] The said Step Three includes:

[0068] Step 301: Divide the flow field into different flow pattern regions according to the identified flow patterns. For each flow pattern region, calculate the average particle flow velocity. By calculating the ratio between the maximum and minimum values of the average particle flow velocities in all flow pattern regions, obtain the non-uniformity index of the particle flow velocity in the entire flow field. The calculation formula is as follows:

[0069]

[0070] where, V i represents the average particle flow velocity in the i-th flow pattern region, i = 1, 2, …, M, M represents the number of flow pattern regions, V xj , V yj , V zj respectively represent the velocity components in the x, y, and z directions at the j-th measurement point, j = 1, 2, …, N, N represents the number of measurement points, and Uv represents the non-uniformity index of the particle flow velocity in the entire flow field;

[0071] It should be noted that the potential risks of uneven flow phenomena such as channeling and preferential flow are evaluated through the magnitude of the particle flow velocity non-uniformity index. Generally, the larger the non-uniformity index, the more uneven the velocity distribution, and the higher the possible risks of channeling and preferential flow;

[0072] Step 302: Obtain the particle concentration distribution data of the fluidized bed unit during deep peak shaving. For each flow pattern region, calculate the average particle concentration. By calculating the ratio between the maximum and minimum values of the average particle concentrations in all flow pattern regions, obtain the non-uniformity index of the particle concentration distribution throughout the flow field. The calculation formula is as follows:

[0073]

[0074] where, C i represents the average particle concentration in the i-th flow pattern region, i = 1, 2, …, M, where M represents the number of flow pattern regions, C j represents the particle concentration at the j-th measurement point, j = 1, 2, …, N, where N represents the number of measurement points, and Uc represents the non-uniformity index of the particle concentration distribution throughout the flow field;

[0075] Step 303: Combine the non-uniformity index of the particle flow velocity and the non-uniformity index of the particle concentration distribution throughout the flow field, and calculate the non-uniformity index of the entire flow field through the geometric mean method; Geometric mean method: where, U represents the non-uniformity index of the entire flow field;

[0076] It should be noted that if the non-uniformity index of the particle flow velocity is high, then the velocity distribution within the flow field will exhibit significant differences. The velocity in some regions may be much higher than that in other regions. This velocity difference will cause intense friction and collisions during the fluid flow, thereby increasing energy loss and noise. At the same time, velocity non-uniformity may also lead to separation or vortices during the fluid flow, further reducing the stability and efficiency of the flow field;

[0077] Similarly, if the non-uniformity index of the particle concentration is high, then the concentration distribution within the flow field will also exhibit significant differences. This concentration difference may lead to a decrease in the heat and mass transfer efficiency because the heat and mass transfer rate between the regions with high concentration and low concentration will be affected. In addition, concentration non-uniformity may also cause non-uniform progress of chemical reactions;

[0078] During use, combine the content of Steps 301 to 303:

[0079] Through the non-uniformity index of the entire flow field, the non-uniformity of the flow field during deep peak shaving of the fluidized bed can be evaluated, including two aspects: the particle flow velocity and the particle concentration distribution, so as to more comprehensively understand the actual state of the flow field. After dividing the flow field into different flow pattern regions and conducting specific analysis for each region, it is helpful to accurately identify the regions with problems in the flow field, such as regions with too fast or too slow particle flow velocity, or too high or too low particle concentration.

[0080] Step 4: Obtain the bed temperature data of the fluidized bed unit during deep peak shaving, generate a bed temperature distribution map, combine it with the particle flow velocity vector map, identify the high-temperature - flow pattern regions, and generate the coking risk index for the high-temperature - flow pattern regions;

[0081] The said Step 4 includes:

[0082] Step 401: Obtain the bed temperature data of the fluidized bed unit during deep peak shaving, map the temperature data onto the grid model of the fluidized bed. Each grid point corresponds to different position coordinates and its temperature value. For the missing data points, use a spatial interpolation algorithm (such as inverse distance weighted interpolation, etc.) to fill them and generate a bed temperature distribution map;

[0083] Step 402: Calculate the average temperature and standard deviation of the bed temperature through the temperature values of each grid point. Take the sum of the average temperature and the standard deviation as the temperature threshold, where the temperature threshold = average temperature + standard deviation. Mark the regions with temperatures higher than the temperature threshold as local high-temperature regions. Superimpose the bed temperature distribution map and the particle flow velocity vector map, determine and mark the flow pattern regions corresponding to the local high-temperature regions, and mark them as high-temperature - flow pattern regions;

[0084] Step 403: Integrate the particle concentration distribution data and the bed temperature data of each high-temperature - flow pattern region through spatial matching, calculate the average particle concentration and the average temperature of the marked high-temperature - flow pattern regions, and take the product of the average particle concentration and the average temperature as the coking risk index for this high-temperature - flow pattern region;

[0085] It should be noted that through spatial matching, the particle concentration and temperature data of each high-temperature - flow pattern region are corresponded one by one to form a comprehensive data set. By corresponding and integrating two sets of data with different but related attributes (particle concentration distribution data and bed temperature data) in the same spatial framework, we can more accurately understand the relationship between the particle concentration and temperature in different regions of the fluidized bed, thereby identifying those regions with both high particle concentration and high temperature, which are usually the places with higher coking risk;

[0086] When in use, combine the content of Step 401 to Step 403:

[0087] By mapping the bed temperature data onto the grid model, we can accurately identify the local high-temperature regions in the fluidized bed, which helps to timely discover potential hot spots, thereby taking corresponding measures to prevent adverse situations such as coking. By calculating the coking risk index of the high-temperature - flow pattern regions, we can more accurately reflect the coking risk degree of this region, so as to carry out targeted adjustments and optimizations.

[0088] Step Five: Calculate the coking risk index of the entire flow field by integrating the non-uniformity index of the entire flow field and the coking risk indices of all high-temperature - flow pattern regions. Compare the coking risk index of the entire flow field with the risk threshold. When the coking risk index of the entire flow field is greater than or equal to the risk threshold, issue a warning.

[0089] The above Step Five includes:

[0090] Step 501: Obtain the non-uniformity index of the entire flow field and the coking risk indices of all high-temperature - flow pattern regions. Calculate the coking risk index of the entire flow field through the non-uniformity index of the entire flow field and the coking risk indices of all high-temperature - flow pattern regions. The calculation formula is as follows:

[0091]

[0092] where Cr represents the coking risk index of the entire flow field, U represents the non-uniformity index of the entire flow field, Cr k represents the coking risk index of the k-th high-temperature - flow pattern region, ω k represents the weight of the k-th high-temperature - flow pattern region, k = 1, 2, …, K, where K represents the number of high-temperature - flow pattern regions, and the weight is the ratio of the area of the k-th high-temperature - flow pattern region to the total area of all high-temperature - flow pattern regions;

[0093] Step 502: Preset the risk threshold. Compare the coking risk index of the entire flow field with the risk threshold. When the coking risk index of the entire flow field is greater than or equal to the risk threshold, it indicates that there is a relatively high coking risk in the current operating state of the fluidized bed unit, and a warning is issued to remind relevant personnel to immediately take measures for adjustment or optimization, such as adjusting parameters such as fuel input, air flow rate, and bed height, or performing necessary maintenance and cleaning work;

[0094] When the coking risk index of the entire flow field is less than the risk threshold, it indicates that the current operating state of the fluidized bed unit is relatively stable and the coking risk is low, and the current operating state continues to be monitored;

[0095] It should be noted that an initial risk threshold is set based on new historical data and expert experience. During the actual operation process, verify the set risk threshold and observe whether the operating state and coking situation of the fluidized bed unit meet expectations near the risk threshold. As the operating time increases and the state of the fluidized bed unit changes, regularly update the risk threshold;

[0096] When in use, combine the content of Step 501 to Step 502:

[0097] By calculating the coking risk index of the entire flow field, the operating status and potential risks of the fluidized bed unit during deep peak shaving can be comprehensively reflected. When the coking risk index exceeds the preset risk threshold, a warning is issued to timely remind relevant personnel to take measures, thereby effectively avoiding the occurrence of serious problems such as coking.

[0098] Please refer to Figure 2 , the present invention also provides an operating status evaluation system for the deep peak shaving process of a fluidized bed unit, including: a data acquisition module, a particle flow analysis module, a flow field uniformity analysis module, a coking risk assessment module, and a warning module;

[0099] Among them, the data acquisition module collects the combustion condition data of the fluidized bed unit during the deep peak shaving process;

[0100] The particle flow analysis module obtains the particle flow velocity data of the fluidized bed unit during the deep peak shaving process, generates a particle flow velocity vector diagram, and identifies and marks different flow patterns and paths in the particle flow velocity vector diagram;

[0101] The flow field uniformity analysis module divides the flow field into different flow pattern regions according to the identified flow patterns, and obtains the non-uniformity index of the entire flow field through the particle flow velocity and particle concentration distributions in each flow pattern region of the flow field;

[0102] The coking risk assessment module obtains the bed temperature data of the fluidized bed unit during the deep peak shaving process, generates a bed temperature distribution diagram, combines the particle flow velocity vector diagram, identifies the high-temperature - flow pattern region, and calculates the coking risk index of the high-temperature - flow pattern region;

[0103] The warning module comprehensively calculates the coking risk index of the entire flow field based on the non-uniformity index of the entire flow field and the coking risk indexes of all high-temperature - flow pattern regions, compares the coking risk index of the entire flow field with the risk threshold, and issues a warning when the coking risk index of the entire flow field is greater than or equal to the risk threshold.

[0104] In the application, several formulas involved are calculated by taking their numerical values after dimensionless treatment, and the formula is obtained by software simulation of a large amount of collected data to approximate the real situation. The coefficients in the formula are set by those skilled in the art according to the actual situation.

[0105] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art will appreciate that the units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution.

[0106] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units. They may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the objectives of the solution of this embodiment.

[0107] As described above, the specific implementation manners of the present application are only described, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should be covered within the protection scope of the present application.

Claims

1. A method for evaluating the operating state during the deep peak shaving process of a fluidized bed unit, characterized in that: It includes the following steps: Collect the combustion condition data during the deep peak shaving process of the fluidized bed unit; Obtain the particle flow velocity data during the deep peak shaving process of the fluidized bed unit, generate a particle flow velocity vector diagram, and identify and label different flow patterns and paths in the particle flow velocity vector diagram; According to the identified flow patterns, divide the flow field into different flow pattern regions, and generate the non-uniformity index of the entire flow field through the particle flow velocity and particle concentration distribution in each flow pattern region of the flow field; Obtain the bed temperature data during the deep peak shaving process of the fluidized bed unit, generate a bed temperature distribution diagram, combine it with the particle flow velocity vector diagram, identify the high temperature-flow pattern region, and calculate the coking risk index of the high temperature-flow pattern region; Integrate the non-uniformity index of the entire flow field and the coking risk index of all high temperature-flow pattern regions, calculate the coking risk index of the entire flow field, compare the coking risk index of the entire flow field with the risk threshold, and issue a warning when the coking risk index of the entire flow field is greater than or equal to the risk threshold.

2. The operating state evaluation method for the deep peak shaving process of a fluidized bed unit according to claim 1, wherein: The collection of combustion condition data includes: arranging a number of temperature measurement points at different heights and regions of the fluidized bed, using thermocouples to monitor the change of the bed temperature; measuring the flow velocity of the particles in the fluidized bed through a laser Doppler velocimeter; and using an optical probe to monitor the particle concentration in the fluidized bed in real time.

3. The operation state evaluation method for the deep peak shaving process of a fluidized bed unit according to claim 1, characterized in that: The generation of the particle flow velocity vector diagram includes: mapping the particle flow velocity data onto a grid model, where each grid point corresponds to the position coordinates and velocity vectors of different particles, and using a spatial interpolation algorithm to fill the grid points with missing particle flow velocity data to obtain the particle flow velocity vector diagram.

4. The operating state evaluation method for the deep peak shaving process of a fluidized bed unit according to claim 3, characterized in that: Identifying and labeling different flow patterns and paths in the particle flow velocity vector diagram includes: Adopting a local window to extract the velocity vector features of each grid point and the window area, performing pattern recognition on the extracted velocity vector features through a machine learning algorithm, and classifying different flow patterns in the flow field; Adopting a streamline tracking algorithm to generate the flow paths in the flow field, and labeling the tracked flow paths according to the classification results of the flow patterns.

5. The operating state evaluation method for the deep peak shaving process of a fluidized bed unit according to claim 4, wherein: For each flow pattern region, calculate the average particle flow velocity, and obtain the non-uniformity index of the particle flow velocity in the entire flow field by calculating the ratio between the maximum and minimum values of the average particle flow velocity in all flow pattern regions.

6. The operating state evaluation method for the deep peak shaving process of a fluidized bed unit according to claim 5, wherein: Obtain the particle concentration distribution data during the deep peak shaving process of the fluidized bed unit, calculate the average particle concentration for each flow pattern region, and obtain the non-uniformity index of the particle concentration distribution in the entire flow field by calculating the ratio between the maximum and minimum values of the average particle concentration in all flow pattern regions; Combined with the non-uniformity index of particle flow velocity and the non-uniformity index of particle concentration distribution in the entire flow field, the non-uniformity index of the entire flow field is calculated by the geometric mean method.

7. The operating state evaluation method for the deep peak shaving process of a fluidized bed unit according to claim 1, wherein: The generation of the bed temperature distribution map includes: mapping the temperature data onto the grid model of the fluidized bed, where each grid point corresponds to different position coordinates and its temperature value. For grid points with missing temperature data, spatial interpolation algorithms are used for filling to obtain the bed temperature distribution map.

8. The operating state evaluation method for the deep peak shaving process of a fluidized bed unit according to claim 7, characterized in that: The identification process of the high-temperature - flow pattern region includes: Through the temperature value of each grid point, calculate the average temperature and standard deviation of the bed temperature. Take the sum of the average temperature and the standard deviation as the temperature threshold. Mark the region with a temperature higher than the temperature threshold as the local high-temperature region. Superimpose the bed temperature distribution map and the particle flow velocity vector map to determine and mark the flow pattern region corresponding to the local high-temperature region, which is marked as the high-temperature - flow pattern region.

9. The operation state evaluation method for the deep peak shaving process of a fluidized bed unit according to claim 8, characterized in that: The generation of the coking risk index for the high-temperature - flow pattern region includes: Integrate the particle concentration distribution data and the bed temperature data of each high-temperature - flow pattern region through spatial matching. Calculate the average particle concentration and the average temperature of the marked high-temperature - flow pattern region. Take the product of the average particle concentration and the average temperature as the coking risk index for this high-temperature - flow pattern region.

10. The operating state evaluation method for the deep peak shaving process of a fluidized bed unit according to claim 1, wherein: The calculation formula for the coking risk index of the entire flow field is as follows: Among them, Cr represents the coking risk index of the entire flow field, U represents the non-uniformity index of the entire flow field, Cr k represents the coking risk index of the k-th high-temperature - flow pattern region, ω k represents the weight of the k-th high-temperature - flow pattern region, and the weight is the ratio of the area of the k-th high-temperature - flow pattern region to the total area of all high-temperature - flow pattern regions. k = 1, 2,..., K, where K represents the number of high-temperature - flow pattern regions.

11. An operating state evaluation system for a fluidized bed unit during deep peak shaving process, which is used to implement the method described in any one of claims 1 to 10, and is characterized in that: Including: A data acquisition module that acquires the combustion condition data during the deep peak shaving process of the fluidized bed unit; A particle flow analysis module that obtains the particle flow velocity data during the deep peak shaving process of the fluidized bed unit, generates a particle flow velocity vector map, and identifies and marks different flow patterns and paths in the particle flow velocity vector map; A flow field uniformity analysis module that divides the flow field into different flow pattern regions according to the identified flow patterns, and obtains the non-uniformity index of the entire flow field through the particle flow velocity and particle concentration distribution in each flow pattern region of the flow field; A coking risk assessment module that obtains the bed temperature data during the deep peak shaving process of the fluidized bed unit, generates a bed temperature distribution map, combines with the particle flow velocity vector map, identifies the high-temperature - flow pattern region, and calculates the coking risk index of the high-temperature - flow pattern region; An early warning module that comprehensively calculates the coking risk index of the entire flow field based on the non-uniformity index of the entire flow field and the coking risk indices of all high-temperature - flow pattern regions. Compare the coking risk index of the entire flow field with the risk threshold. When the coking risk index of the entire flow field is greater than or equal to the risk threshold, an early warning is issued.

Images