Vibration absorption optimization method for low-low-temperature economizer

Abstract

The invention discloses a low-low-temperature economizer damping optimization method. The method comprises the steps that S1, problem identification is carried out; s2, frequency analysis; s3, establishing a wind tunnel model test platform; s4, simulation and testing; s5, optimizing the internal structure; s6, comparing the vortex shedding frequency obtained through calculation with the acoustic standing wave frequency, observing whether the vortex shedding frequency and the acoustic standing wave frequency are close to each other or have an integral multiple relationship, and proposing a solution for preventing or relieving the resonance influence according to an analysis result; s7, drawing a data table related to the internal structure optimization scheme according to the internal structure optimization scheme; s8, determining the weight of the internal structure optimization scheme in combination with an entropy method; s9, performing analysis by using a support vector machine model to obtain an optimal scheme in the internal structure optimization schemes; and S10, obtaining an optimal scheme. The method at least has the following beneficial effects that the subsequent fine adjustment data can be calculated and judged according to a small amount of test data, so that the optimal optimization scheme can be obtained, the time for fine adjustment of the adult model is shortened, and the conversion efficiency of the optimization scheme is improved.

Description

Technical Field

[0001] The present application relates to the technical field of economizers, and in particular to a vibration elimination optimization method for low-temperature economizers. Background Art

[0002] Low-temperature economizer is a heat recovery device used in boiler systems. It recovers waste heat gas generated by boilers, heat exchangers and other equipment, transfers heat to the medium that needs to be heated through a heat transfer medium, and realizes the recycling of heat energy.

[0003] During the heat exchange process, flue gas enters the heat exchange tube. Due to the flue gas particles and flue gas flow, the heat exchange tube and the heat exchanger are very likely to vibrate. When the vortex shedding frequency of the heat exchange tube is close to an integer multiple of the acoustic standing wave frequency in the height direction of the heat exchanger body cavity, resonance may occur, which may easily cause both to fall off or be damaged. Therefore, relevant researchers currently optimize the internal structure of the heat exchanger to eliminate vibrations based on the resonance phenomenon.

[0004] The current vibration reduction optimization method requires the establishment of a wind tunnel model test platform for testing, which means that each optimization scheme needs to be made into a full-body model for testing. The overall production process is long, which in turn lengthens the test process and affects the conversion efficiency of the optimization scheme. Summary of the invention

[0005] To this end, the present application provides a low-temperature economizer vibration reduction optimization method to solve the problem in the prior art that the optimization scheme test process is lengthened, affecting the conversion efficiency of the optimization scheme.

[0006] In order to achieve the above objectives, this application provides the following technical solutions:

[0007] A low-temperature economizer vibration elimination optimization method, comprising:

[0008] S1: Problem identification, confirm whether there is resonance in the low-temperature economizer heat exchange tube under specific working conditions, and whether such resonance poses a threat to the safe operation of the equipment. If it is determined that there is a threat, step S2 is implemented;

[0009] S2: Frequency analysis: Determine the vortex shedding frequency and acoustic standing wave frequency of the heat exchange tube through theoretical calculation and experimental measurement, and analyze the relationship between them;

[0010] S3: Establish a wind tunnel model test platform. According to the actual size and working conditions of the low-temperature economizer, design and build a wind tunnel model test platform, and install sensors and measuring equipment in the wind tunnel model;

[0011] S4: Simulation and testing: By adjusting the parameters in the wind tunnel, the low-temperature economizer operating environment under different load conditions is simulated. Under each simulated condition, the vibration data of the heat exchange tube is recorded and its frequency characteristics are analyzed;

[0012] S5: Internal structure optimization: design internal structure optimization scheme based on vibration test results;

[0013] S6: Compare the calculated vortex shedding frequency and acoustic standing wave frequency to see whether they are close to or have an integer multiple relationship. Based on the analysis results, propose solutions to prevent or reduce the impact of resonance.

[0014] S7: Draw a data table related to the internal structure optimization plan;

[0015] S8: Determine the weight of the internal structure optimization scheme by combining the entropy method, and calculate the entropy value of each internal structure optimization scheme;

[0016] S9: Use the support vector machine model to analyze and obtain the optimal solution among the internal structure optimization solutions;

[0017] S10: Determine the optimal solution based on the optimization degree of each internal structure optimization solution.

[0018] Optionally, the specific operating conditions include high load conditions, medium load conditions, and low load conditions.

[0019] Optionally, the specific steps of frequency analysis in S2 include:

[0020] S2.1: Determine the type, size and material of the heat exchange tubes to be analyzed, and set the operating conditions to be analyzed;

[0021] S2.2: Determine the vortex shedding frequency and acoustic standing wave frequency of the heat exchange tube and analyze the relationship between them;

[0022] S2.3: Obtain the actual flow rate of the fluid in the heat exchange tube and calculate the vortex shedding frequency;

[0023] S2.4: Measure the cavity size of the heat exchanger body, calculate the acoustic standing wave frequency, analyze the boundary conditions of the cavity, and correct the acoustic standing wave frequency;

[0024] S2.5: Compare the frequency values. Compare the calculated vortex shedding frequency and the acoustic standing wave frequency to see if they are close to or have an integer multiple relationship. If the vortex shedding frequency is close to or has an integer multiple relationship with the acoustic standing wave frequency, there may be a resonance risk. Further analyze the impact of resonance on the heat exchange tube and heat exchanger.

[0025] Optional internal structure optimization solutions include: adding anti-vibration baffles, adjusting side panel openings, adding elastic elements between the heat exchange tubes and the supporting structure, adding damping materials at key locations of the heat exchange tubes, adjusting the size, shape and distribution of the side panel openings, adding rectification mechanisms at the openings, and strengthening the structural strength.

[0026] Optionally, the entropy method includes the following steps:

[0027] S8.1: Data standardization: Standardize the raw data of each internal structure optimization scheme to eliminate the dimension effect. For the positive index, the formula is:

[0028]

[0029] For negative indicators, the formula is:

[0030]

[0031] Among them, x ij represents the value of the i-th object on the j-th index, x max and x min Respectively represent the maximum and minimum values ​​of the indicator;

[0032] S8.2: Calculate the weight of indicators: Calculate the information entropy of each indicator through the standardized data, and calculate the weight of each indicator according to the information entropy. The smaller the entropy value of the indicator, the greater the weight, and vice versa;

[0033] S8.3: Weight each indicator according to the determined weight to obtain the final comprehensive score.

[0034] Optionally, the steps for building a support vector machine model are:

[0035] S9.1: Feature extraction, taking the entropy value of each internal structure optimization scheme as the feature value input;

[0036] S9.2: Feature selection, select feature values ​​with high discreteness and large contribution to the classification task;

[0037] S9.3: Data preprocessing, necessary standardization of eigenvalues;

[0038] S9.4: Select a linear kernel as the kernel function to map the normalized eigenvalues ​​to a high-dimensional feature space;

[0039] S9.5: Set parameters, set the regularization parameter C;

[0040] S9.6: Cross-validation: Use cross-validation techniques to evaluate model performance and select the best parameter combination;

[0041] S9.7: Draw a confusion matrix to visually display the classification results of the model;

[0042] S9.8: Use the trained support vector machine model to predict new samples and obtain their category labels;

[0043] S9.9: According to the category label, obtain the optimization degree of each internal structure optimization solution.

[0044] Optionally, the vortex shedding frequency is calculated as:

[0045]

[0046] Where: f is the vortex shedding frequency, unit: Hz, St is the Strouhal number, for the flow around a cylinder, the Strouhal number is 0.2, V is the fluid velocity, unit: m / s, D is the diameter of the cylinder, unit: m.

[0047] Optionally, the acoustic standing wave frequency is calculated as:

[0048]

[0049] Where: f n is the standing wave frequency of the nth mode, unit: Hz, n is the mode number, L is the length of the cavity, unit: m, v is the speed of sound, unit: m / s.

[0050] Compared with the prior art, this application has at least the following beneficial effects:

[0051] 1. It can calculate and judge the subsequent fine-tuning data based on a small amount of test data, so as to obtain the best optimization solution, reduce the time of fine-tuning the adult model, and improve the conversion efficiency of the optimization solution.

[0052] 2. Use the entropy method to determine the weight of each optimization scheme to the optimization results, so as to determine the focus, reduce the exploration of the optimization scheme direction, and reduce the test time of the optimization scheme. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more intuitively illustrate the prior art and the present application, exemplary drawings are given below. It should be understood that the specific shapes and structures shown in the drawings should not generally be regarded as limiting conditions for implementing the present application; for example, those skilled in the art are capable of easily making conventional adjustments or further optimizations to the addition / reduction / attribution division, specific shapes, positional relationships, connection methods, dimensional ratios, etc. of certain units (components) based on the technical concepts and exemplary drawings disclosed in the present application.

[0054] Figure 1 A flow chart of a low-temperature economizer vibration elimination optimization method provided in accordance with an embodiment of the present application. DETAILED DESCRIPTION

[0055] The present application is further described below in detail through specific embodiments in conjunction with the accompanying drawings.

[0056] The present invention provides a low-temperature economizer vibration elimination optimization method, comprising:

[0057] S1: Problem identification, confirm whether there is resonance in the low-temperature economizer heat exchange tube under specific working conditions, and whether such resonance poses a threat to the safe operation of the equipment. If it is determined that there is a threat, step S2 is implemented. The specific working conditions include high-load working conditions, medium-load working conditions, and low-load working conditions. Among them, under high-load working conditions: the flue gas temperature is high, the flow rate is fast, the heat load of the economizer heating surface is large, and there may be a problem of increased flue resistance; under medium-load working conditions: the flue gas temperature is moderate, the flow rate is relatively slow, the heat load of the economizer heating surface is moderate, and the flue resistance is relatively small; under low-load working conditions: the flue gas temperature is low, the flow rate is slow, the heat load of the economizer heating surface is small, the main steam flow rate is low, and the degree of influence of the extraction steam squeezed by the economizer on the working state of the steam turbine is relatively obvious;

[0058] S2: Frequency analysis: Determine the vortex shedding frequency and acoustic standing wave frequency of the heat exchange tube through theoretical calculation and experimental measurement, and analyze the relationship between them;

[0059] Specifically, when the vortex shedding frequency is close to or equal to the natural frequency of the structure, the structure will resonate. This phenomenon is called vortex-induced vibration, which may cause damage to the structure;

[0060] The specific steps of frequency analysis in S2 include:

[0061] S2.1: Determine the type, size and material of the heat exchange tube to be analyzed, and set the operating conditions to be analyzed, such as flow rate, temperature, pressure, etc.;

[0062] S2.2: Determine the vortex shedding frequency and acoustic standing wave frequency of the heat exchange tube and analyze the relationship between them, where the calculation formula of the vortex shedding frequency is:

[0063]

[0064] Where: f is the vortex shedding frequency (unit: Hertz, Hz), St is the Strouhal number. For the flow around a cylinder, the Strouhal number is 0.2. The specific value may vary depending on the flow conditions. V is the fluid velocity (unit: meter / second, m / s), and D is the diameter or other characteristic length of the cylinder (unit: meter, m).

[0065] The formula for calculating the acoustic standing wave frequency is:

[0066]

[0067] Where: f n is the standing wave frequency of the nth mode (unit: Hertz, Hz), n is the mode number (a positive integer representing the mode of the standing wave, such as the fundamental frequency, second harmonic, etc.), L is the length of the cavity or the length of the string (unit: meter, m), and v is the speed of sound (unit: meter / second, m / s).

[0068] S2.3: Obtain the actual flow rate of the fluid in the heat exchange tube and calculate the vortex shedding frequency;

[0069] S2.4: Measure the height, width and other dimensions of the heat exchanger cavity, calculate the acoustic standing wave frequency, analyze the boundary conditions of the cavity (such as wall material, damping, etc.), and correct the acoustic standing wave frequency;

[0070] S2.5: Compare the frequency values. Compare the calculated vortex shedding frequency and the acoustic standing wave frequency to see if they are close to or have an integer multiple relationship. If the vortex shedding frequency and the acoustic standing wave frequency are close to or have an integer multiple relationship, there may be a resonance risk. Further analyze the impact of resonance on the heat exchange tube and heat exchanger.

[0071] S3: Establish a wind tunnel model test platform. According to the actual size and working conditions of the low-temperature economizer, design and build a wind tunnel model test platform to simulate the airflow and vibration conditions under different load conditions, and install sensors and measuring equipment in the wind tunnel model to monitor the vibration of the heat exchange tubes, airflow velocity, temperature and other parameters in real time;

[0072] S4: Simulation and testing: by adjusting the air flow velocity, temperature and other parameters in the wind tunnel, the low-temperature economizer operating environment under different load conditions is simulated. Under each simulated condition, the vibration data of the heat exchange tube is recorded and its frequency characteristics are analyzed;

[0073] S5: Internal structure optimization. Based on the vibration test results, the internal structure optimization plan is designed. The internal structure optimization plan includes: adding anti-vibration baffles, adjusting the side plate openings, adding elastic elements between the heat exchange tubes and the supporting structure, adding damping materials at key locations of the heat exchange tubes, adjusting the size, shape and distribution of the side plate openings, adding rectification mechanisms at the openings, and strengthening the structural strength.

[0074] S6: Compare the calculated vortex shedding frequency and acoustic standing wave frequency to see whether they are close to or have an integer multiple relationship. Based on the analysis results, propose solutions to prevent or reduce the impact of resonance.

[0075] S7: Draw a data table related to the internal structure optimization plan;

[0076] S8: Determine the weight of the internal structure optimization scheme by combining the entropy method, and calculate the entropy value of each internal structure optimization scheme;

[0077] Specifically, the entropy method includes the following steps:

[0078] S8.1: Data standardization: Standardize the raw data of each internal structure optimization scheme to eliminate the dimension effect. For the positive index, the formula is:

[0079]

[0080] For negative indicators, the formula is:

[0081]

[0082] Among them, x ij represents the value of the i-th object on the j-th index, x max and x min Respectively represent the maximum and minimum values ​​of the indicator;

[0083] S8.2: Calculate the weight of indicators: Calculate the information entropy of each indicator through the standardized data, and calculate the weight of each indicator according to the information entropy. The smaller the entropy value of the indicator, the greater the weight, and vice versa;

[0084] S8.3: Weight each indicator according to the determined weight to obtain a final comprehensive score, which can be used to evaluate the pros and cons of different objects or to rank them;

[0085] S9: Use the support vector machine model to analyze and obtain the optimal solution among the internal structure optimization solutions;

[0086] Specifically, the steps for building the support vector machine model are:

[0087] S9.1: Feature extraction, taking the entropy value of each internal structure optimization scheme as the feature value input;

[0088] S9.2: Feature selection, select feature values ​​with high discreteness and large contribution to the classification task;

[0089] S9.3: Data preprocessing, perform necessary standardization on the feature values ​​to ensure the stability and accuracy of model training. Standardization usually includes data normalization, dimension removal and other operations so that different features are comparable in value.

[0090] S9.4: Select a linear kernel as the kernel function to map the normalized eigenvalues ​​to a high-dimensional feature space to handle nonlinear separable problems;

[0091] S9.5: Set parameters, set the regularization parameter C to control the complexity and generalization ability of the model;

[0092] S9.6: Cross-validation: Use cross-validation techniques to evaluate model performance and select the best parameter combination; cross-validation divides the data set into multiple subsets, takes one of the subsets as the test set, and the remaining subsets as the training set for training and testing, thereby obtaining performance evaluation indicators of the model under different parameters;

[0093] S9.7: Draw a confusion matrix to visually display the classification results of the model;

[0094] S9.8: Use the trained SVM model to predict new samples and obtain their category labels;

[0095] S9.9: Obtain the optimization degree of each internal structure optimization solution according to the category label;

[0096] S10: Determine the optimal solution based on the optimization degree of each internal structure optimization solution.

[0097] The technical features of the above embodiments may be arbitrarily combined (as long as there is no contradiction in the combination of these technical features). To make the description concise, not all possible combinations of the technical features in the above embodiments are described; these embodiments that are not explicitly written should also be considered to be within the scope of this specification.

Claims

1. A low-temperature economizer vibration elimination optimization method, characterized in that: include: S1: Problem identification, confirm whether there is resonance in the low-temperature economizer heat exchange tube under specific working conditions, and whether such resonance poses a threat to the safe operation of the equipment. If it is determined that there is a threat, step S2 is implemented; S2: Frequency analysis: Determine the vortex shedding frequency and acoustic standing wave frequency of the heat exchange tube through theoretical calculation and experimental measurement, and analyze the relationship between them; S3: Establish a wind tunnel model test platform. According to the actual size and working conditions of the low-temperature economizer, design and build a wind tunnel model test platform, and install sensors and measuring equipment in the wind tunnel model; S4: Simulation and testing: By adjusting the parameters in the wind tunnel, the low-temperature economizer operating environment under different load conditions is simulated. Under each simulated condition, the vibration data of the heat exchange tube is recorded and its frequency characteristics are analyzed; S5: Internal structure optimization: design internal structure optimization scheme based on vibration test results; S6: Compare the calculated vortex shedding frequency and acoustic standing wave frequency to see whether they are close to or have an integer multiple relationship. Based on the analysis results, propose solutions to prevent or reduce the impact of resonance. S7: Draw a data table related to the internal structure optimization plan; S8: Determine the weight of the internal structure optimization scheme by combining the entropy method, and calculate the entropy value of each internal structure optimization scheme; S9: Use the support vector machine model to analyze and obtain the optimal solution among the internal structure optimization solutions; S10: Determine the optimal solution based on the optimization degree of each internal structure optimization solution.

2. A low-temperature economizer vibration elimination optimization method according to claim 1, characterized in that: Specific operating conditions include high load conditions, medium load conditions, and low load conditions.

3. A low-temperature economizer vibration elimination optimization method according to claim 1, characterized in that: The specific steps of frequency analysis in S2 include: S2.1: Determine the type, size and material of the heat exchange tubes to be analyzed, and set the operating conditions to be analyzed; S2.2: Determine the vortex shedding frequency and acoustic standing wave frequency of the heat exchange tube and analyze the relationship between them; S2.3: Obtain the actual flow rate of the fluid in the heat exchange tube and calculate the vortex shedding frequency; S2.4: Measure the cavity size of the heat exchanger body, calculate the acoustic standing wave frequency, analyze the boundary conditions of the cavity, and correct the acoustic standing wave frequency; S2.5: Compare the frequency values. Compare the calculated vortex shedding frequency and the acoustic standing wave frequency to see if they are close to or have an integer multiple relationship. If the vortex shedding frequency is close to or has an integer multiple relationship with the acoustic standing wave frequency, there may be a resonance risk. Further analyze the impact of resonance on the heat exchange tube and heat exchanger.

4. A low-temperature economizer vibration elimination optimization method according to claim 1, characterized in that: The internal structure optimization plan includes: adding anti-vibration partitions, adjusting the side panel openings, adding elastic elements between the heat exchange tubes and the supporting structure, adding damping materials at key locations of the heat exchange tubes, adjusting the size, shape and distribution of the side panel openings, adding rectification mechanisms at the openings and strengthening the structural strength.

5. A low-temperature economizer vibration elimination optimization method according to claim 1, characterized in that: The entropy method includes the following steps: S8.1: Data standardization: Standardize the raw data of each internal structure optimization scheme to eliminate the dimension effect. For the positive index, the formula is: For negative indicators, the formula is: Among them, x ij represents the value of the i-th object on the j-th index, x max and x min Respectively represent the maximum and minimum values ​​of the indicator; S8.2: Calculate the weight of indicators: Calculate the information entropy of each indicator through the standardized data, and calculate the weight of each indicator according to the information entropy. The smaller the entropy value of the indicator, the greater the weight, and vice versa; S8.3: Weight each indicator according to the determined weight to obtain the final comprehensive score.

6. A low-temperature economizer vibration elimination optimization method according to claim 1, characterized in that: The steps to build the support vector machine model are: S9.1: Feature extraction, taking the entropy value of each internal structure optimization scheme as the feature value input; S9.2: Feature selection, select feature values ​​with high discreteness and large contribution to the classification task; S9.3: Data preprocessing, necessary standardization of eigenvalues; S9.4: Select a linear kernel as the kernel function to map the normalized eigenvalues ​​to a high-dimensional feature space; S9.5: Set parameters, set the regularization parameter C; S9.6: Cross-validation: Use cross-validation techniques to evaluate model performance and select the best parameter combination; S9.7: Draw a confusion matrix to visually display the classification results of the model; S9.8: Use the trained support vector machine model to predict new samples and obtain their category labels; S9.9: According to the category label, obtain the optimization degree of each internal structure optimization solution.

7. A low-temperature economizer vibration elimination optimization method according to claim 3, characterized in that: The calculation formula of vortex shedding frequency is: Where: f is the vortex shedding frequency, unit: Hz, St is the Strouhal number, for the flow around a cylinder, the Strouhal number is 0.2, V is the fluid velocity, unit: m / s, D is the diameter of the cylinder, unit: m.

8. A low-temperature economizer vibration elimination optimization method according to claim 3, characterized in that: The formula for calculating the acoustic standing wave frequency is: Where: f n is the standing wave frequency of the nth mode, unit: Hz, n is the mode number, L is the length of the cavity, unit: m, v is the speed of sound, unit: m / s.

Images