Aero-engine turbine blade multispectral temperature measurement method based on HPSOGA

Abstract

The invention discloses an aero-engine turbine blade multispectral temperature measurement method based on HPSOGA, and belongs to the technical field of turbine blade temperature measurement, and the method comprises the following steps: S1, collecting multispectral radiation data and background reflection radiation data of a turbine blade; s2, initializing an HPSOGA algorithm, and randomly generating an initial particle swarm; s3, calculating an environment complexity factor, updating the dynamic penalty function, and calculating a value of the dynamic penalty function; s4, constructing a multi-objective optimization function; s5, the fitness of all particles is calculated, and an individual optimal solution and a global optimal solution are obtained; s6, updating the speed and position of each particle by using an HPSOGA algorithm, and generating new particles; and iteratively executing the steps S3-S6 until the conditions are met, and outputting a global optimal solution. According to the method, the problems of low measurement precision, poor stability and the like when the turbine blade is subjected to temperature measurement are solved, the dynamic penalty function is introduced, the adaptability and the accuracy of an inversion temperature measurement algorithm are improved, and the reliability and the stability of temperature and emissivity calculation are improved by adopting a multi-target optimization strategy.

Description

Technical Field

[0001] The invention relates to the technical field of turbine blade temperature measurement, and in particular to a multi-spectral temperature measurement method for an aircraft engine turbine blade based on HPSOGA. Background Art

[0002] When it is necessary to measure the temperature of equipment components or specific areas, in many cases, due to factors such as excessively high, unstable, and uneven regional temperatures, direct contact temperature measurement methods such as temperature sensors cannot fully detect accurate temperatures. When facing high-speed moving turbine blades, it is even more inconvenient to install temperature measurement devices. The radiation wavelength intensity of an object is closely related to its temperature, so non-contact multi-spectral temperature measurement technology can be used for indirect temperature measurement. Multi-spectral temperature measurement technology is a high-precision temperature measurement method that collects radiation data of the target object at multiple different wavelengths to perform temperature inversion. It can be applied to measurement applications that require high precision and complex environments, such as aircraft engine turbine blades.

[0003] In multi-spectral temperature measurement, the emissivity of the measured object varies with the wavelength. The common technology is to use the method of setting the emissivity model for prediction, but it is impossible to accurately predict the emissivity change at high temperature, and the measurement effect for some materials is different. There are great limitations, and it is easy to fall into the local optimal solution when solving the temperature. The common method to improve the detection effect is to use constrained optimization to transform the underdetermined equation problem of multi-spectral temperature measurement into an optimization problem. The hybrid particle swarm optimization and genetic algorithm (HPSOGA) combines the global search capability of the particle swarm algorithm and the local search advantage of the genetic algorithm, and has a good application prospect in the multi-spectral temperature measurement of turbine blades. However, there are still many defects, such as not considering the influence of the reflected radiation of the adjacent blades to be measured, high computational complexity and low efficiency, poor stability in the face of environmental noise and interference, and when dealing with the situation where the material emissivity changes due to changes in temperature and surface conditions, further optimization and adjustment are also required. These defects limit its wide application in complex temperature measurement environments and urgently need to be solved by new technical solutions. Summary of the invention

[0004] The present invention overcomes the problems of low measurement accuracy and poor stability of existing multi-spectral temperature measurement technologies when measuring the temperature of turbine blades, and provides a multi-spectral temperature measurement method for aircraft engine turbine blades based on HPSOGA. Considering the background radiation influence of the turbine blades, a dynamic penalty function based on environmental changes is introduced to improve the adaptability and accuracy of the inversion temperature measurement algorithm. Considering the influence of material emissivity changes with temperature, a multi-objective optimization strategy is adopted to improve the reliability and stability of temperature and emissivity calculations.

[0005] In order to achieve the above object, the present invention adopts the following scheme: The multi-spectral temperature measurement method of aero-engine turbine blades based on HPSOGA includes the following steps: S1: Use a spectrometer to collect multi-spectral radiation data of turbine blades and background reflection radiation data; S2: Initializing the parameters of the HPSOGA algorithm and the parameters of the dynamic penalty function, and randomly generating an initial particle swarm, wherein the information of each particle in the initial particle swarm includes a temperature estimation value and an emissivity estimation value of the turbine blade; S3: using the background reflected radiation data to calculate the environmental complexity factor, and updating the penalty intensity coefficient and tolerance threshold of the dynamic penalty function according to the environmental complexity factor, calculating the theoretical reflected radiation value corresponding to the temperature estimation value of each particle according to Planck's law, and using the penalty intensity coefficient, tolerance threshold and theoretical reflected radiation value to describe the dynamic penalty function; S4: Calculate the error between the estimated temperature value and the estimated emissivity value of each particle, and the error between the preset temperature value and the preset emissivity value, and construct a multi-objective optimization function; S5: combining the dynamic penalty function and the multi-objective optimization function to calculate the fitness of all particles, and obtaining the individual optimal solution and the global optimal solution of each particle in the particle swarm according to the fitness; S6: Use the HPSOGA algorithm to update the speed and position of each particle in the particle swarm according to the individual optimal solution and the global optimal solution, generate new particles and add them to the particle swarm; iteratively execute steps S3-S6 until a preset number of iterations is reached or the change in the fitness of the particles is lower than a preset threshold, and output the temperature estimation value and the emissivity estimation value of the particles of the global optimal solution as the temperature estimation value and the emissivity estimation value of the turbine blade.

[0006] Preferably, in step S3, the environment complexity factor EFC(gen) is calculated using the following formula: in, is the background radiation data R collected in the past M times m The average value of .

[0007] Preferably, the penalty intensity coefficient α(gen) and the tolerance threshold θ(gen) of the dynamic penalty function are updated as follows: Among them, α0 is the initial penalty intensity coefficient, θ0 is the initial tolerance threshold, γ is the sensitivity coefficient, γ>0, and δ is the adjustment coefficient, δ>0.

[0008] Preferably, the dynamic penalty function P(T,gen) is calculated as follows: Among them, R e (T) is the theoretical reflected radiation value corresponding to temperature T obtained by algorithm inversion.

[0009] Preferably, step S4 specifically includes the following steps: Calculate the temperature error of the particle , calculate the particle's emissivity error , where T m is the estimated temperature of the current particle, T0 is the preset temperature value, ε m is the estimated emission rate of the current particle, and ε0 is the preset emission rate; The temperature error values ​​and emissivity error values ​​calculated recently are statistically calculated to obtain the average temperature error value. and the average emissivity error ; Calculate the dynamic adjustment target weights for temperature and emissivity separately: Among them, ω 1,0 is the initial base weight for temperature, ω 2,0 is the initial weight for the emissivity, μ is the adjustment sensitivity parameter, μ>0, τ is a small amount to avoid the division by zero problem; Construct a multi-objective optimization function: .

[0010] Preferably, step S4 further comprises defining a synergy factor: , the multi-objective optimization function is adjusted to: Where λ≥0 is the weight of the synergy factor.

[0011] Preferably, in step S5, the fitness of the particle is: , where J(ε m , T m , gen) is a multi-objective optimization function, P(T, gen) is a dynamic penalty function; the fitness of each particle is calculated, and the individual optimal solution for a single particle in the particle swarm and the global optimal solution for all particles are obtained according to the fitness.

[0012] Preferably, the step S6 includes the following steps: Use the PSO algorithm to update the speed and position of each particle in the particle swarm: in, is the current velocity corresponding to the particle temperature, is the current speed corresponding to the emission rate, is the updated velocity corresponding to the particle temperature, is the updated velocity corresponding to the emissivity, is the current position corresponding to the particle temperature, is the current position corresponding to the emissivity, is the updated position corresponding to the particle temperature, is the updated position corresponding to the emission rate; ω is the inertia weight of the PSO algorithm, c1 and c2 are learning factors, r1 and r2 are balance coefficients, and pbest T and pbest ε are the individual optimal solutions for temperature and emissivity, gbest T and gbest ε are the global optimal solutions for temperature and emissivity respectively; T m is the estimated temperature of the particle, ε m is the estimated emission rate of the particle; The GA algorithm is used to combine partial solutions through selection, crossover, and mutation to generate new particles, merge the newly generated particles into the particle swarm, and delete the same number of particles as the newly generated particles in order of fitness from low to high to maintain the size of the particle swarm unchanged.

[0013] The present invention has at least the following beneficial effects: (1) a penalty function is added to the optimization process, and an environmental complexity factor is introduced. The penalty parameter is dynamically adjusted according to the fluctuation degree of the background reflected radiation data, so that the penalty intensity coefficient and the tolerance threshold change adaptively. The dynamic penalty function allows the inversion algorithm to dynamically adjust the calculation parameters according to the changes of environmental factors such as background radiation, so that it can maintain a high-accuracy temperature measurement effect when facing different operating conditions and external interference; (2) the algorithm optimizes the emissivity and temperature at the same time, tracks the average value of the temperature error and the emissivity error in several consecutive iterations, and dynamically adjusts the weights of the temperature and emissivity targets according to the error situation to construct a final multi-objective optimization function, which can not only accurately estimate the temperature, but also consider the influence of the material emissivity changing with temperature, thereby improving the algorithm's adaptability to changes in the physical properties of the material, and thus improving the accuracy and reliability of the overall temperature measurement; (3) by introducing a synergistic factor into the multi-objective optimization function, the problem that the algorithm may tend to unilaterally and quickly reduce a certain target error while ignoring the zero-one target, resulting in an unbalanced optimization result, is avoided, so that the temperature and emissivity can be more balanced and synergistically optimized to ensure the stability of the particle quality and the accuracy of the temperature measurement results. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 The present invention is a schematic diagram of the principle of the multi-spectral temperature measurement method of the aircraft engine turbine blade based on HPSOGA. DETAILED DESCRIPTION

[0015] The present invention is further described in detail below in conjunction with the accompanying drawings so that those skilled in the art can implement the invention with reference to the description.

[0016] like Figure 1 As shown, the multi-spectral temperature measurement method of an aircraft engine turbine blade based on HPSOGA provided by the present invention comprises the following steps: S1: Use a spectrometer to collect multi-spectral radiation data of turbine blades and background reflection radiation data.

[0017] As a key device, the spectrometer can accurately capture the radiation information of turbine blades at multiple different wavelengths. These radiation data contain important characteristics of turbine blade temperature. Since turbine blades work in a high temperature environment, they will emit electromagnetic radiation containing different energies, and there is a corresponding physical correlation between the radiation intensity of different wavelengths and the blade temperature. By collecting multi-spectral radiation data in the specific band of the main analysis through the spectrometer, the real-time radiation spectrum information of the turbine blade can be obtained, providing data support for the subsequent temperature inversion calculation. In the actual measurement environment, factors such as ambient light will generate reflected radiation on the surface of the turbine blade. These background reflected radiations will interfere with the analysis of the turbine blade's own radiation data. For example, the light emitted by other heat-generating components and lighting sources in the engine compartment will be reflected when it hits the turbine blade. There is also mutual influence of reflected radiation between turbine blades. If these background reflected radiations are not considered, large errors may be introduced in the subsequent temperature calculation process. By accurately collecting background reflected radiation data, the environmental impact can be effectively analyzed and corrected in the subsequent algorithm processing, thereby improving the accuracy of temperature measurement.

[0018] S2: Initialize the parameters of the HPSOGA algorithm and the parameters of the dynamic penalty function, and randomly generate an initial particle swarm, wherein the information of each particle in the initial particle swarm includes the temperature estimation value and the emissivity estimation value of the turbine blade.

[0019] The parameters of the initialization HPSOGA algorithm set the basic conditions for the operation of the algorithm. These parameters include particle swarm size, inertia weight, learning factor, etc., which will affect the algorithm's search ability and convergence speed. For example, the particle swarm size determines the number of particles involved in the optimization search. If the size is too large, the amount of calculation may increase, while if it is too small, the solution space may not be fully searched. The inertia weight affects the degree to which the particle inherits its own historical speed. A reasonable setting can balance the algorithm's global search and local search capabilities. The learning factor controls the learning step size of the particle toward the individual optimal solution and the global optimal solution, affecting the convergence of the algorithm.

[0020] The dynamic penalty function is used to handle constraints. In this temperature measurement method, the initial setting of its parameters will affect the penalty intensity for solutions that do not meet the constraints. For example, the setting of the initial penalty intensity coefficient and tolerance threshold will determine the degree of screening of particles that do not meet the basic requirements (such as large deviations from the theoretical reflected radiation value) in the early stage of the algorithm, and guide the algorithm to search towards a reasonable solution space to increase the solution efficiency and accuracy.

[0021] Each particle in the randomly generated initial particle swarm contains the temperature estimate and emissivity estimate of the turbine blade. In multi-spectral temperature measurement, temperature and emissivity are interrelated key parameters that need to be solved simultaneously. Although the particles are randomly generated, the combination of the initial estimates is limited to a reasonable range, which includes the possible variation range of the actual temperature value and emissivity of the turbine blade, so that the algorithm starts searching in a wide solution space and increases the possibility of finding the global optimal solution. For example, the temperature estimate may be randomly selected within the common operating temperature range of the turbine blade, and the emissivity estimate is set according to the material properties. As the algorithm runs, the particles will continuously update their position and velocity, gradually approaching the actual temperature and emissivity values.

[0022] S3: Use the background reflected radiation data to calculate the environmental complexity factor, and update the penalty intensity coefficient and tolerance threshold of the dynamic penalty function according to the environmental complexity factor, calculate the theoretical reflected radiation value corresponding to the temperature estimate of each particle according to Planck's law, and calculate the dynamic penalty function using the penalty intensity coefficient, tolerance threshold and theoretical reflected radiation value.

[0023] The core of the dynamic penalty function is to adjust the penalty intensity of the inverted temperature so that it is synchronized with environmental changes. When the measured data of the background reflected radiation differs greatly from the predicted value, the penalty function will increase the penalty of the inverted temperature, prompting the algorithm to avoid selecting temperature values ​​that may increase errors due to environmental changes. With the help of this dynamic penalty function, the improved HPSOGA algorithm of the present invention can adaptively adjust the optimization direction when facing environmental disturbances, strengthen the penalty for unreliable solutions, and thus maintain a high temperature measurement accuracy under conditions such as high temperature and high background radiation. The penalty intensity coefficient can be adjusted according to actual application requirements, and the tolerance threshold is used to define the acceptable error range between the background radiation data and the predicted value; the environmental complexity factor ECF (gen) is used to measure the complexity and uncertainty of the environmental conditions under the current iterative algebra gen, and the environmental complexity factor ECF is used to dynamically adjust the penalty intensity coefficient and the tolerance threshold. The larger the value of ECF (gen), the more drastic the change in the background reflected radiation, and the greater the impact on the results; when the amount of reflected radiation increases, the penalty intensity coefficient is increased to strengthen the penalty, and the tolerance threshold is reduced to tighten the tolerance, thereby imposing stricter constraints on mismatched temperature solutions. It is defined by counting the fluctuations of the background radiation measurement data of the last several generations. Planck's law describes the relationship between the energy distribution of blackbody radiation and temperature. In this method, this law is used in combination with the estimated temperature of the particle to calculate the theoretical reflected radiation value. This theoretical value is used in the subsequent algorithm to measure the degree of deviation between the estimated temperature of the particle and the actual situation.

[0024] S4: Calculate the error between the estimated temperature value and the estimated emissivity value of each particle, the error between the preset temperature value and the preset emissivity value, and construct a multi-objective optimization function. The present invention introduces multi-objective optimization in the inversion optimization process of the HPSOGA algorithm, and optimizes the emissivity and temperature at the same time. When the error temperature is relatively high, the weight of the temperature target should be increased, and vice versa, the weight of the emissivity target should be increased, so as to achieve adaptive adjustment and effectively balance the optimization degree of these two parameters to ensure the accuracy and reliability of the final temperature measurement result.

[0025] S5: The dynamic penalty function and the multi-objective optimization function are combined to calculate the fitness of all particles, and the individual optimal solution and the global optimal solution of each particle in the particle swarm are obtained according to the fitness.

[0026] Combining the dynamic penalty function and the multi-objective optimization function to calculate the fitness can comprehensively evaluate the comprehensive performance of each particle in satisfying environmental constraints and approaching the true temperature and emissivity. For example, if the temperature and emissivity estimates of a particle make the value of the dynamic penalty function smaller, and the error term in the multi-objective optimization function is also smaller, then its fitness will be relatively high, indicating that the particle is more likely to be close to the true solution. If the fitness of the current particle is better than the fitness of its historical optimal position, then the position of the current particle is updated to the individual optimal solution. At the same time, in the entire particle swarm, the particle with the highest fitness will be searched and used as the global optimal solution. These optimal solutions will serve as an important reference for subsequent particle updates. For example, in the formula for updating the particle speed and position of the PSO algorithm, the individual optimal solution (pbest) and the global optimal solution (gbest) will guide the particles to move in a better direction, so that the particle swarm can continuously approach the true temperature and emissivity values ​​during the iteration process, thereby improving the accuracy of temperature measurement. By repeating this process continuously, the algorithm can gradually select the temperature and emissivity estimates that best meet the actual situation and achieve accurate measurement of the temperature of the turbine blades of aircraft engines.

[0027] S6: Use the HPSOGA algorithm to update the speed and position of each particle in the particle swarm according to the individual optimal solution and the global optimal solution, generate new particles and add them to the particle swarm; iteratively execute steps S3-S6 until a preset number of iterations is reached or the change in the fitness of the particles is lower than a preset threshold, and output the temperature estimation value and the emissivity estimation value of the particles of the global optimal solution as the temperature estimation value and the emissivity estimation value of the turbine blade.

[0028] When using the HPSOGA algorithm, the particle swarm optimization (PSO) part enables particles to adjust their positions in the solution space according to their own historical speed, individual optimal solution and global optimal solution information, search in a better direction, and accelerate the convergence to the optimal solution. At the same time, the genetic algorithm (GA) is used to combine partial solutions through selection, crossover and mutation to generate new particles. The selection operation selects excellent individuals according to the fitness of the particles, so that particles with high fitness have a greater probability of being selected to participate in subsequent operations, ensuring the inheritance of excellent genes; the crossover operation exchanges and combines part of the information of the selected individuals to increase the diversity of solutions; the mutation operation randomly changes certain genes of the particles with a certain probability to prevent the algorithm from falling into a local optimum.

[0029] A test example for the above method: Prepare the temperature measurement environment, install thermocouples at the corresponding positions of the turbine blades, and heat the turbine blades to 1100K. Use a spectrometer to collect multi-spectral radiation data in the 1100nm-1600nm band for the turbine blades. Use a spectrometer to obtain background reflection radiation data, and obtain background radiation data records for the past M times through multiple measurements. Filter and smooth the spectral radiation data to reduce the impact of random noise on temperature inversion. Calculate the blackbody radiation intensity at any temperature T according to Planck's law.

[0030] Initialize the HPSOGA algorithm parameters: set the particle swarm size N, PSO inertia weight ω, learning factors c1 and c2, crossover rate and mutation rate of the genetic algorithm, and the maximum number of iterations Gmax.

[0031] Initialize the dynamic penalty function parameters: set the basic penalty intensity α0 and basic threshold θ0, sensitivity coefficients γ, δ.

[0032] Initialize multi-objective optimization parameters: set initial weight ω 1，0 ,ω 2，0 As well as the sensitivity parameter μ, the synergy factor weight λ, and the small amount τ.

[0033] An initial particle swarm is randomly generated, each particle contains a temperature estimate and an emissivity estimate, and their initial values ​​are uniformly distributed within a reasonable range.

[0034] Calculate the environmental complexity factor ECF, update the penalty function coefficient according to ECF(gen), calculate the theoretical reflected radiation value for the temperature of the current particle, calculate the dynamic penalty function, and calculate the temperature error and emissivity error of the particle. Calculate the average value based on the error statistics of the last several generations, dynamically adjust the target weight according to the average value, and construct a multi-objective optimization function. Combine the multi-objective optimization function with the dynamic penalty function to obtain the fitness of the particle, calculate the fitness of all particles in the group, and determine the individual optimal solution pbest and the global optimal solution gbest of each particle according to the fitness. Each particle has its own individual optimal solution. Initially, the current position of each particle is set to its individual optimal position, and the corresponding fitness value is set to the individual optimal fitness value. In each iteration, calculate the fitness value of the current position of the particle. If the fitness value of the current position is better than the previously recorded individual optimal fitness value, update the individual optimal position and individual optimal fitness value. The global optimal solution is the best solution among the individual optimal solutions of all particles in the entire particle swarm. Initially, compare the individual optimal fitness values ​​of all particles, and select the best one as the global optimal solution. In each iteration, the individual optimal fitness values ​​of all particles are also compared. If the individual optimal fitness value of a particle is better than the current global optimal fitness value, the global optimal solution is updated. The PSO formula is used to update the velocity and position of the particle, and the genetic algorithm operation is applied to the population every several generations: partial solutions are combined through selection, crossover, and mutation to generate new particles, which are merged with the population updated by PSO. The merged solution set is sorted from best to worst according to fitness, and the top N particles with better fitness are retained as the new generation of particle swarms. Repeat the iteration, and update ECF (gen), dynamic penalty coefficient, and dynamic weight after each generation of iteration. Stop the iteration when the maximum number of iterations Gmax is reached or the fitness change is lower than the preset threshold. Output the temperature estimate and emissivity estimate of the gbest particle at the end of the iteration as the final inversion result, that is, the true temperature of the blade and the corresponding emissivity estimated by the inversion algorithm.

[0035] This method adds a dynamic penalty function in the optimization process and introduces an environmental complexity factor. The penalty parameters are dynamically adjusted according to the fluctuation degree of the background reflected radiation data, so that the penalty intensity coefficient and the tolerance threshold change adaptively. The dynamic penalty function allows the inversion algorithm to dynamically adjust the calculation parameters according to the changes in environmental factors such as background radiation, so that it can maintain a high-accuracy temperature measurement effect when facing different operating conditions and external interference; the algorithm optimizes the emissivity and temperature at the same time, tracks the average value of the temperature error and the emissivity error in several consecutive generations of iterations, and dynamically adjusts the weights of the temperature and emissivity targets according to the error situation to construct the final multi-objective optimization function, which can not only accurately estimate the temperature, but also consider the influence of the material emissivity changing with temperature, thereby improving the algorithm's adaptability to changes in the physical properties of the material, thereby improving the accuracy and reliability of the overall temperature measurement.

[0036] In another technical solution, the following formula is used in step S3 to calculate the environment complexity factor EFC(gen): in, is the background radiation data R collected in the past M times m The average value of .

[0037] The way to update the penalty intensity coefficient α(gen) and tolerance threshold θ(gen) of the dynamic penalty function is: Among them, α0 is the initial penalty intensity coefficient, θ0 is the initial tolerance threshold, γ is the sensitivity coefficient, γ>0, and δ is the adjustment coefficient, δ>0.

[0038] The dynamic penalty function P(T,gen) is calculated as follows: Among them, R e (T) is the theoretical reflected radiation value corresponding to the temperature T obtained by the algorithm inversion. T represents the temperature obtained by inversion, R m It is the background radiation data measured by the spectrometer and actually calculated.

[0039] In another technical solution, step S4 specifically includes the following steps: Calculate the temperature error of the particle , calculate the particle's emissivity error , where T m is the estimated temperature of the current particle, T0 is the preset temperature value, ε m is the estimated emission rate of the current particle, and ε0 is the preset emission rate; The temperature error values ​​and emissivity error values ​​calculated recently are statistically calculated to obtain the average temperature error value. and the average emissivity error : M is the evaluation window length of the most recent generations.

[0040] Calculate the dynamic adjustment target weights for temperature and emissivity separately: Among them, ω 1,0is the initial base weight for temperature, ω 2,0 is the initial weight for the emissivity, μ is the adjustment sensitivity parameter, μ>0, τ is a small amount to avoid the zero division problem; when When it is relatively large, will increase accordingly, making the algorithm pay more attention to the accuracy of temperature; when When it is relatively large, Increased to emphasize the optimization of emissivity.

[0041] Construct a multi-objective optimization function: .

[0042] Step S4 also includes defining a synergy factor: , the multi-objective optimization function is adjusted to: Where λ≥0 is the weight of the synergy factor. When the temperature error and the emissivity error differ greatly and are unbalanced, S(gen) increases. To reduce this imbalance, a synergy term is added to the optimization target and weighted with an adjustable coefficient λ to promote the simultaneous improvement of temperature and emissivity. This avoids the problem that the algorithm may tend to unilaterally and quickly reduce the error of a certain target while ignoring the zero-one target, resulting in an unbalanced optimization result. This allows the temperature and emissivity to be more balanced and synergistically optimized, thereby ensuring the stability of the particle quality and the accuracy of the temperature measurement results.

[0043] In step S5, the fitness of the particle is: , where J(ε m , T m , gen) is a multi-objective optimization function, P(T, gen) is a dynamic penalty function; the fitness of each particle is calculated, and the individual optimal solution for a single particle in the particle swarm and the global optimal solution for all particles are obtained according to the fitness.

[0044] In another technical solution, the step S6 includes the following steps: Use the PSO algorithm to update the speed and position of each particle in the particle swarm: in, is the current velocity corresponding to the particle temperature, is the current speed corresponding to the emission rate, is the updated velocity corresponding to the particle temperature, is the updated velocity corresponding to the emissivity, are the current position corresponding to the particle temperature, is the current position corresponding to the emissivity, is the updated position corresponding to the particle temperature, is the updated position corresponding to the emission rate; ω is the inertia weight of the PSO algorithm, c1 and c2 are learning factors, r1 and r2 are balance coefficients, and pbest T and pbest ε are the individual optimal solutions for temperature and emissivity, gbest T and gbest ε are the global optimal solutions for temperature and emissivity respectively; T m is the estimated temperature of the particle, ε m is the estimated emission rate of the particle; The GA algorithm is used to combine partial solutions through selection, crossover, and mutation to generate new particles. When selecting partial solutions, a proportional selection method can be used. The probability of being selected is determined according to the fitness of the particles. The higher the fitness of the particles, the greater the probability of being selected. The probabilities of all particles form a probability wheel. The wheel is rotated Z times, and the Z particles pointed to by the pointer are selected as partial solutions participating in the crossover and mutation operations of the GA algorithm. The size of Z is selected according to the size of the particle swarm. For example, if the size of the particle swarm is 100, the recommended value range of Z is 3-7. The newly generated particles are merged into the particle swarm, and the particles equal to the newly generated particles are deleted in order from low to high fitness to maintain the size of the particle swarm unchanged. This not only ensures the diversity of the particle swarm, but also avoids the unlimited expansion of the population size, so that the algorithm can continuously and efficiently search for the optimal solution under limited resources.

[0045] During the optimization process, the HPSOGA algorithm uses the advantages of both the PSO algorithm and the GA algorithm to achieve global search and local improvement. PSO quickly searches the global solution space through speed and position updates, while the selection, crossover and mutation operations of the GA algorithm increase population diversity and avoid local optimality. The introduction of dynamic penalty functions and multi-objective optimization strategies runs through the entire iterative process, enabling the algorithm to adaptively adjust the optimization direction and focus according to real-time environmental conditions and optimization progress. When the environmental complexity increases, the dynamic penalty function strengthens the constraints on poor solutions to ensure that the algorithm can still obtain reliable inversion results under high disturbance conditions. When there is an obvious unbalanced improvement between temperature and emissivity, the dynamic multi-objective optimization strategy guides the algorithm to simultaneously improve the accuracy of both through dynamic weights and synergy factors, ensuring that the final temperature measurement results are both accurate and stable. This improved optimization strategy enables the algorithm to ensure the high accuracy of temperature estimation while maintaining the stability of emissivity estimation, thereby effectively improving the robustness and reliability of the entire temperature measurement process.

[0046] It should be noted that, although the above describes the various steps in a specific order, it does not mean that the various steps must be performed in the above specific order. In fact, some of these steps can be performed concurrently or even in a different order, as long as the required functions can be achieved. The number of devices and processing scales described here are used to simplify the description of the present invention, and the application, modification and variation of the present invention are obvious to those skilled in the art.

[0047] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the implementation modes, and they can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the illustrations shown and described herein.

Claims

1. The multi-spectral temperature measurement method of aircraft engine turbine blades based on HPSOGA is characterized by: The following steps are involved: S1: Use a spectrometer to collect multi-spectral radiation data of turbine blades and background reflection radiation data; S2: Initializing the parameters of the HPSOGA algorithm and the parameters of the dynamic penalty function, and randomly generating an initial particle swarm, wherein the information of each particle in the initial particle swarm includes a temperature estimation value and an emissivity estimation value of the turbine blade; S3: using the background reflected radiation data to calculate the environmental complexity factor, and updating the penalty intensity coefficient and tolerance threshold of the dynamic penalty function according to the environmental complexity factor, calculating the theoretical reflected radiation value corresponding to the temperature estimation value of each particle according to Planck's law, and using the penalty intensity coefficient, tolerance threshold and theoretical reflected radiation value to describe the dynamic penalty function; S4: Calculate the error between the estimated temperature value and the estimated emissivity value of each particle, and the error between the preset temperature value and the preset emissivity value, and construct a multi-objective optimization function; S5: combining the dynamic penalty function and the multi-objective optimization function to calculate the fitness of all particles, and obtaining the individual optimal solution and the global optimal solution of each particle in the particle swarm according to the fitness; S6: Use the HPSOGA algorithm to update the speed and position of each particle in the particle swarm according to the individual optimal solution and the global optimal solution, generate new particles and add them to the particle swarm; iteratively execute steps S3-S6 until a preset number of iterations is reached or the change in the fitness of the particles is lower than a preset threshold, and output the temperature estimation value and the emissivity estimation value of the particles of the global optimal solution as the temperature estimation value and the emissivity estimation value of the turbine blade.

2. The multi-spectral temperature measurement method for aircraft engine turbine blades based on HPSOGA according to claim 1, characterized in that: In step S3, the environment complexity factor EFC(gen) is calculated using the following formula: in, is the background radiation data R collected in the past M times m The average value of .

3. The multi-spectral temperature measurement method for aircraft engine turbine blades based on HPSOGA according to claim 2 is characterized in that: The way to update the penalty intensity coefficient α(gen) and tolerance threshold θ(gen) of the dynamic penalty function is: Among them, α0 is the initial penalty intensity coefficient, θ0 is the initial tolerance threshold, γ is the sensitivity coefficient, γ>0, and δ is the adjustment coefficient, δ>0.

4. The multi-spectral temperature measurement method for aircraft engine turbine blades based on HPSOGA according to claim 3 is characterized in that: The method for updating the parameters of the dynamic penalty function P(T,gen) is: Among them, R e (T) is the theoretical reflected radiation value corresponding to temperature T obtained by algorithm inversion.

5. The multi-spectral temperature measurement method for aircraft engine turbine blades based on HPSOGA according to claim 1, characterized in that: Step S4 specifically includes the following steps: Calculate the temperature error of the particle , calculate the particle's emissivity error , where T m is the estimated temperature of the current particle, T0 is the preset temperature value, ε m is the estimated emission rate of the current particle, and ε0 is the preset emission rate; The temperature error values ​​and emissivity error values ​​calculated recently are statistically calculated to obtain the average temperature error value. and the average emissivity error ; Calculate the dynamic adjustment target weights for temperature and emissivity separately: Among them, ω 1,0 is the initial base weight for temperature, ω 2,0 is the initial weight for the emissivity, μ is the adjustment sensitivity parameter, μ>0, τ is a small amount to avoid the division by zero problem; Construct a multi-objective optimization function: 。 6. The multi-spectral temperature measurement method for aircraft engine turbine blades based on HPSOGA according to claim 5, characterized in that: Step S4 also includes defining a synergy factor: , the multi-objective optimization function is adjusted to: Where λ≥0 is the weight of the synergy factor.

7. The multi-spectral temperature measurement method for aircraft engine turbine blades based on HPSOGA according to claim 1, characterized in that: In step S5, the fitness of the particle is: , where J(ε m , T m , gen) is a multi-objective optimization function, P(T, gen) is a dynamic penalty function; the fitness of each particle is calculated, and the individual optimal solution for a single particle in the particle swarm and the global optimal solution for all particles are obtained according to the fitness.

8. The multi-spectral temperature measurement method for aircraft engine turbine blades based on HPSOGA according to claim 1, characterized in that: The step S6 includes the following steps: Use the PSO algorithm to update the speed and position of each particle in the particle swarm: in, is the current velocity corresponding to the particle temperature, is the current speed corresponding to the emission rate, is the updated velocity corresponding to the particle temperature, is the updated velocity corresponding to the emissivity, is the current position corresponding to the particle temperature, is the current position corresponding to the emissivity, is the updated position corresponding to the particle temperature, is the updated position corresponding to the emission rate; ω is the inertia weight of the PSO algorithm, c1 and c2 are learning factors, r1 and r2 are balance coefficients, and pbest T and pbest ε are the individual optimal solutions for temperature and emissivity, gbest T and gbest ε are the global optimal solutions for temperature and emissivity respectively; T m is the estimated temperature of the particle, ε m is the estimated emission rate of the particle; The GA algorithm is used to combine partial solutions through selection, crossover, and mutation to generate new particles, merge the newly generated particles into the particle swarm, and delete the same number of particles as the newly generated particles in order of fitness from low to high to maintain the size of the particle swarm unchanged.

Images