Search

CN-121364160-B - Method for measuring influence of garbage incineration bottom ash on mortar performance based on hyperspectral data

CN121364160BCN 121364160 BCN121364160 BCN 121364160BCN-121364160-B

Abstract

The invention provides a method for measuring the influence of garbage incineration bottom ash on mortar performance based on hyperspectral data, which relates to the technical field of building material performance analysis, the invention determines the proportion of influencing components in the bottom ash hyperspectral data to form original data, and sets gradients to determine a plurality of experimental groups with incomplete proportions to obtain characteristic parameters of each experimental group, and constructing a bottom ash performance prediction model, screening a bottom ash combination with the highest performance excitation value by combining a particle swarm optimization algorithm as a reference group, establishing a fitting relation between the doping amount of the reference group and the compressive strength on the basis of the reference group, and finally determining the theoretical optimal bottom ash doping amount position and the corresponding maximum compressive strength on the basis of the fitting relation to determine an optimal doping amount interval. According to the invention, through establishing the bottom ash performance prediction model and combining the blending amount-compressive strength relation fitting, the accurate determination of the optimal blending amount interval of the bottom ash and the optimization and improvement of the mortar performance are realized.

Inventors

  • ZHANG YONGHENG
  • ZHOU HONG
  • GUO ZHONGXUAN

Assignees

  • 中国矿业大学
  • 山东水利职业学院

Dates

Publication Date
20260512
Application Date
20251222

Claims (9)

  1. 1. A method for measuring influence of garbage incineration bottom ash on mortar performance based on hyperspectral data is characterized by comprising the following specific steps: Step 1, hyperspectral data of bottom ash to be analyzed are obtained, the reflectivity of relevant wave bands is screened out from hyperspectral images according to the types of set influencing components, the proportion of each influencing component is determined according to the screened reflectivity data, and original data are formed; Step 2, determining a plurality of groups of experimental groups with incomplete proportions according to the set gradient based on the proportion of the original data, determining the total content of the active oxides of each experimental group, and obtaining the particle size distribution parameters of each experimental group; analyzing the amorphous phase proportion of each experimental group based on an X-ray diffraction technology, and preprocessing the total content of active oxides, the particle size distribution parameters and the amorphous phase proportion of the experimental group to obtain the characteristic parameters of each experimental group; And 4, establishing a performance fitness function based on characteristic parameters of each experimental group to determine performance excitation values of each experimental group, constructing a bottom ash performance prediction model, optimizing the bottom ash performance prediction model based on a particle swarm optimization algorithm, and selecting the experimental group with the highest performance excitation value as a reference group, wherein the method for establishing the performance fitness function and constructing the bottom ash performance prediction model is based on: Constructing a performance fitness function on the basis of an Arrhenius reaction dynamics formula and a BHS model to obtain performance excitation values of each group of bottom ash, combining the obtained total active oxide content, particle size distribution parameters and amorphous phase proportion of each group of bottom ash into a characteristic vector, and constructing a bottom ash performance prediction model by taking the characteristic vector of each experimental group as the input of the model and taking the performance excitation value of each experimental group as the output of the model; step 5, setting a plurality of reference groups and a mixing amount scheme of mortar based on the proportion of the reference groups, preparing a plurality of concrete test pieces according to the mixing amount scheme, determining the compressive strength of the concrete test pieces, and constructing a model of the mixing amount of the reference groups and the compressive strength of the mortar test pieces; and 6, finding out the theoretical position of the optimal doping amount of the reference group based on the compressive strength model, calculating the corresponding maximum compressive strength, and finally determining the optimal doping amount interval of the reference group.
  2. 2. The method for measuring the influence of the waste incineration bottom ash on the mortar performance based on the hyperspectral data according to claim 1, wherein hyperspectral data of the bottom ash to be analyzed is obtained, and the reflectivity of relevant wave bands is screened out from hyperspectral images according to the types of set influence components, and the method is as follows: uniformly drying a bottom ash sample to be analyzed, spreading the bottom ash sample on a uniform and flat substrate, and scanning the surface of the sample by using a hyperspectral imager to obtain a three-dimensional hyperspectral data cube, wherein the three-dimensional hyperspectral data cube is expressed as Wherein Represented as a spatial coordinate in terms of a set of dimensions, As a function of the wavelength(s), For the measured spectral intensity, calculating the reflectivity of the bottom ash sample to be analyzed by comparing the spectral response of the bottom ash sample with the spectral response of the standard reflecting plate acquired in advance; And measuring the content of chemical components of the bottom ash by using an X-ray fluorescence spectrometer, determining the influence components in the bottom ash to be analyzed, selecting corresponding reflection band intervals according to the spectral characteristics of the influence components, extracting the characteristic band reflectivity data corresponding to the components from hyperspectral data to form a reflectivity characteristic vector, wherein the reflectivity characteristic vector contains relevant bands of the influence components of the bottom ash.
  3. 3. The method for determining the influence of the garbage incineration bottom ash on the mortar performance based on hyperspectral data according to claim 2, which is characterized by establishing a mapping model, determining the proportion of each influence component based on the screened reflectivity data, and forming the original data, wherein the method comprises the following steps: Building a mapping model based on a neural network, wherein an input layer of the model is used for receiving the input reflectivity characteristic vector and corresponds to the selected characteristic vector The reflectivity of each wave band is set in the hidden layer of the model The neuron uses nonlinear activation function to process reflectivity eigenvector and extract eigenvalue information, and the output layer of model is used for outputting the first layer of bottom ash Predicted values of the content of the individual influencing components; Collecting standard bottom ash sample with known content, measuring hyperspectral reflectivity data, extracting characteristic band reflectivity, determining corresponding component content by experimental chemical analysis, initializing model, and determining characteristic band number in input layer Number of neurons in hidden layer Initializing the weight and bias of a mapping model, and adopting a mean square error as a loss function; Iteratively updating the weight and the bias parameters by using a nonlinear optimization algorithm, taking a minimized loss function as an optimization target, calculating gradients and counter-propagating errors to adjust the weight and the bias in a mapping model, extracting new sample data of bottom ash to be predicted, extracting a reflectivity vector, and inputting the reflectivity vector into a trained mapping model to obtain the content of each influence component in the bottom ash to be analyzed; Summarizing the content of all influencing components in the bottom ash to be analyzed, and forming the component proportion original data of the bottom ash sample as the basic data of subsequent analysis.
  4. 4. The method for determining the influence of the garbage incineration bottom ash on the mortar performance based on hyperspectral data according to claim 3, wherein the method for determining the total content of active oxides in each experimental group by setting gradients to determine a plurality of experimental groups with different proportions is characterized by obtaining the particle size distribution parameter of each experimental group according to the following steps: Selecting allowable change step length of each component based on the raw data of the proportion of the bottom ash component, defining gradient vector, and selecting the number of steps to be regulated The method comprises the steps of performing gradient change on each component to generate a plurality of proportion candidate values, and generating all experimental groups by arranging and combining the candidate values of all components; calculating the total content of active oxides in each experimental group based on the mass ratio of silicon dioxide, aluminum oxide, calcium oxide and ferric oxide in the bottom ash of each experimental group; Obtaining particle size distribution parameters of each group of bottom ash, wherein the particle size distribution parameters of each group of bottom ash comprise fineness, uniformity and specific surface area, and the particle size distribution parameters are automatically measured and output based on a laser particle size meter measurement program, and the common characteristic particle sizes are as follows 、 And , The particle size corresponding to the 10% cumulative distribution, representing the fine particle fraction, Is 50% cumulative distribution corresponding to particle size, indicating median particle size, The particle size corresponding to 90% cumulative distribution represents coarse particle section, and the bottom ash particle size is defined as Characterizing fineness of each group of bottom ash by using an arithmetic average particle diameter, and defining uniformity of each group of bottom ash by using concentration degree of particle size distribution; setting the particle size shape as a sphere, and defining the specific surface area of the particle size of each group of bottom ash by utilizing a specific surface area formula for calculating the sphere according to the density of each group of bottom ash obtained by a laser particle analyzer and combining the fineness of each group of bottom ash obtained by calculation.
  5. 5. The method for determining the influence of the bottom ash of the garbage incineration on the mortar performance based on the hyperspectral data according to claim 4, which is characterized by analyzing the amorphous phase proportion of the bottom ash of each experimental group and preprocessing the total content of the active oxides, the particle size distribution parameter and the amorphous phase proportion of the experimental group to obtain the characteristic parameter of each experimental group, wherein the method comprises the following steps: Measuring the phase content of mineral crystals in each group of bottom ash by an X-ray diffraction technology, calculating the amorphous phase proportion by an internal standard method, normalizing and preprocessing the obtained total content of active oxides, particle size distribution parameters and the amorphous phase proportion in each experimental group, and converting all the data into And taking the total content of active oxides, the particle size distribution parameter and the amorphous phase proportion in the experiment groups after normalization treatment as characteristic parameters of each experiment group.
  6. 6. The method for determining the influence of the waste incineration bottom ash on the mortar performance based on hyperspectral data according to claim 5, wherein the method for establishing a performance fitness function to calculate the performance excitation value of the bottom ash of each experimental group and establishing a bottom ash performance prediction model is based on the following steps: The method comprises the steps of constructing a bottom ash performance prediction model based on a neural network learning structure, wherein the ash performance prediction model comprises an input layer, a hidden layer and an output layer, the input layer is responsible for receiving feature vectors, the hidden layer is an intermediate layer between the input layer and the output layer in the neural network and is responsible for carrying out feature extraction and information processing on the input feature vectors, a nonlinear activation function is used in the hidden layer to capture complex modes, and the output layer generates a final prediction result of the model, namely a performance excitation value of each group of bottom ash.
  7. 7. The method for determining the influence of the waste incineration bottom ash on the mortar performance based on hyperspectral data according to claim 6, wherein the method for optimizing the bottom ash performance prediction model based on a particle swarm optimization algorithm selects an experimental group with the highest performance excitation value as a reference group, and is based on the following steps: Searching for an optimizable bottom ash parameter combination by using a particle swarm optimization algorithm, optimizing a bottom ash performance prediction model, initializing a particle swarm, wherein each particle represents a group of bottom ash parameter combinations, setting the position and the speed of the particle, wherein the position represents a combination of the weight and the threshold value of the prediction model, the speed defines the moving direction and the stride of the particle in a search space, randomly generating a group of weight and threshold value as the initial position of the particle at the beginning of each iteration, generating the initial position of the particle based on normal distribution, uniformly distributing the particle in the whole search space, and updating the speed and the position of the particle; presetting a performance excitation threshold value, repeatedly evaluating the loss and updating the position and speed of particles, calculating the performance excitation value of the current bottom ash combination in each iteration, comparing the performance excitation value calculated in each iteration with the performance excitation threshold value, defining the particles corresponding to the current bottom ash combination as optimal particles if the performance excitation value of the current bottom ash combination exceeds the preset threshold value, and ensuring that the prediction of the optimal particles on the model reaches the optimal performance by retraining the model again when the found optimal particle position is used for updating the weight and the threshold value of the model; And selecting an experimental group with the highest performance excitation value as a reference group based on the optimized bottom ash performance prediction model.
  8. 8. The method for determining the influence of the garbage incineration bottom ash on the mortar performance based on hyperspectral data according to claim 7 is characterized in that a plurality of reference groups and a mixing amount scheme of mortar are set, a plurality of concrete test pieces are prepared according to the mixing amount scheme, the compressive strength of the concrete test pieces is determined, and a model of the reference group mixing amount and the compressive strength of the mortar test pieces is constructed according to the following method: screening an experimental group with optimal performance based on a particle swarm optimized bottom ash performance prediction model, and designing different mass percentage doping amounts by taking the experimental group as a reference group for doping amount design Series, determining the doping gradient range The mixing amount is expressed as the proportion of the bottom ash mass to the total mass of the mortar, the components are accurately weighed according to the proportion, uniformly mixed, a cubic mortar test piece is prepared according to the standard, the concrete mortar test piece is maintained to the experimental specified age, and the compressive strength of the mortar test piece under each mixing amount gradient is measured; Taking the mixing amount of each reference group as the input of a model, taking the compressive strength of a mortar test piece corresponding to each reference group as the output of the model, constructing a compressive strength model, and fitting the nonlinear change of the compressive strength along with the mixing amount by using a quadratic polynomial according to the chemical principle that the bottom ash is mixed with alkali to excite the mortar; Arranging the measured multiple groups of reference group doping amounts and the compressive strength of the corresponding mortar test pieces in an experiment, and constructing a fitting equation set so that the error between the true value and the fitting value of the compressive strength of the mortar test pieces is minimum under the gradient doping amount of each reference group; and respectively calculating partial derivatives of the fitting parameters on the basis of the fitting equation set, enabling the partial derivatives to be equal to zero to obtain a set of normal equation set, obtaining values of the fitting parameters by solving the normal equation set, and finally substituting the fitting parameters into a quadratic polynomial to obtain a fitting relation between the bottom ash doping amount and the compressive strength of the mortar test piece.
  9. 9. The method for determining the influence of the bottom ash of the garbage incineration on the mortar performance based on the hyperspectral data according to claim 8, wherein the theoretical position of the optimal bottom ash doping amount is found, the corresponding maximum compressive strength is calculated, and the optimal bottom ash doping amount interval is finally determined according to the following formula: Finding out the theoretical position of the optimal bottom ash doping amount based on a fitting relation between the bottom ash doping amount and the compressive strength of the mortar test piece, wherein the theoretical position is a maximum point of the fitting relation, defining the maximum point of the fitting relation as the theoretical position of the optimal bottom ash doping amount, substituting the obtained theoretical position of the optimal bottom ash doping amount corresponding to the abscissa on a fitting curve into the fitting relation to calculate the maximum compressive strength in a plurality of groups of mortar test pieces, setting a compressive strength threshold coefficient, screening out the bottom ash doping amount range with the compressive strength not lower than the threshold limit in the fitting curve, establishing an equation of the fitting relation and the maximum compressive strength under the compressive strength threshold coefficient, and finally solving the equation to obtain two real roots, wherein the two roots form the optimal doping amount interval meeting the compressive strength threshold condition.

Description

Method for measuring influence of garbage incineration bottom ash on mortar performance based on hyperspectral data Technical Field The invention relates to the technical field of building material performance analysis, in particular to a method for measuring the influence of garbage incineration bottom ash on mortar performance based on hyperspectral data. Background The alkali-activated mortar is widely focused on preparing high-performance, low-carbon and environment-friendly building materials by utilizing industrial waste residues, and the garbage incineration bottom ash is used as a potential raw material, and the addition of the alkali-activated mortar can not only change the physical and mechanical properties of the mortar, but also influence the microstructure and durability of the mortar. However, as the physical and chemical properties of the bottom ash of the garbage incineration are complex, and the components of the bottom ash from different sources have large differences, how to scientifically evaluate the mixing effect of the bottom ash in the alkali-activated mortar, determine the reasonable mixing amount range and reveal the mechanism of the influence of the bottom ash on the performance of the mortar is a technical difficulty in current research and engineering application. In the prior art, the utilization of the bottom ash of the garbage incineration is evaluated by a single index, the system characterization of the multidimensional characteristic of the bottom ash is lacking, the quantitative relation between the characteristic parameter of the bottom ash and the performance of the alkali-activated mortar is not established, a scientific prediction model is lacking, a determined optimal bottom ash mixing amount is often found in the traditional technology, an intelligent optimization algorithm is not fully applied to optimize the bottom ash proportion, the standardization degree of an experimental method is insufficient, the data accuracy and the repeatability are poor, the influence of the multi-factor coupling effect on the performance of the mortar is not comprehensively considered, a reasonable performance threshold value and an optimal mixing amount interval determination method are lacking, the recycling utilization efficiency of the bottom ash is low, and the requirements of actual engineering on the stability and the optimality of the mortar performance are difficult to meet. It is therefore necessary to propose a method for determining the effect of waste incineration bottom ash on mortar performance based on hyperspectral data to solve the problems. The above information disclosed in the background section is only for enhancement of understanding of the background of the disclosure and therefore it may include information that does not form the prior art that is already known to a person of ordinary skill in the art. Disclosure of Invention The invention aims to provide a method for measuring the influence of garbage incineration bottom ash on mortar performance based on hyperspectral data, so as to solve the problems in the prior art. In order to achieve the above purpose, the present invention provides the following technical solutions: A method for measuring influence of garbage incineration bottom ash on mortar performance based on hyperspectral data specifically comprises the following steps: Step 1, hyperspectral data of bottom ash to be analyzed are obtained, the reflectivity of relevant wave bands is screened out from hyperspectral images according to the types of set influencing components, the proportion of each influencing component is determined according to the screened reflectivity data, and original data are formed; Step 2, determining a plurality of groups of experimental groups with incomplete proportions according to the set gradient based on the proportion of the original data, determining the total content of the active oxides of each experimental group, and obtaining the particle size distribution parameters of each experimental group; analyzing the amorphous phase proportion of each experimental group based on an X-ray diffraction technology, and preprocessing the total content of active oxides, the particle size distribution parameters and the amorphous phase proportion of the experimental group to obtain the characteristic parameters of each experimental group; Step 4, based on characteristic parameters of each experimental group, establishing a performance fitness function to determine performance excitation values of each experimental group, constructing a bottom ash performance prediction model, optimizing the bottom ash performance prediction model based on a particle swarm optimization algorithm, and selecting the experimental group with the highest performance excitation value as a reference group; step 5, setting a plurality of reference groups and a mixing amount scheme of mortar based on the proportion of the reference groups, preparing a plur