64 results about "Least squares support vector machine" patented technology

The invention discloses a thermal power plant boiler combustion control method and system, and relates to the field of boiler combustion system control technical equipment. By collecting control loop data of a boiler combustion system in real time, dynamic characteristics, stability and response efficiency of a loop can be analyzed through a multi-dimensional performance evaluation model (including six indexes of steady-state tracking performance, static tracking performance, maximum control deviation, steady-state error, over-limit time and comprehensive tracking performance); based on the evaluation result, the air-coal ratio, the oxygen amount set value and the over-fire air door opening degree are dynamically adjusted through a combustion linkage algorithm, and intervention correction is conducted on set values of loops such as superheat degree control, primary air, secondary air and the coal amount of a coal mill when the performance of the control loop is deteriorated; combining a least square support vector machine to predict NOx concentration and boiler efficiency; and finally, combustion optimization is realized through closed-loop control. The problems that traditional PID control lags behind and loop coordination is poor are solved, boiler efficiency is improved, and pollutant emission is reduced.

The invention relates to the field of vehicle route planning, in particular to a dynamic multi-target vehicle route planning method and system based on prediction and recombination, and the method comprises the steps: building a mathematical model of dynamic multi-target vehicle route planning, initializing a population through real number coding, adjusting the population to meet a constraint, carrying out the iteration through a genetic algorithm, and obtaining a candidate solution set; a Pareto front set is obtained and clustered, and a clustering center is recorded as a special individual; and when environment change is detected, predicting individuals in a new environment by using a gray model or a least square support vector machine, and constructing a new population until an optimal solution set is output. According to the method, the convergence speed of the algorithm is high, the response to the environment change is more sensitive and timely, the dynamic multi-target vehicle routing problem is effectively solved, and the application effect and the economic benefit of the vehicle routing in the actual life are effectively promoted.

The invention relates to the technical field of power cable intelligent monitoring, and aims to solve the technical problems that in an existing cable state monitoring system, multi-source heterogeneous data fusion is insufficient, the coupling relation between physical quantities is difficult to reveal, and insulation aging, current-carrying capacity and fault probability cannot be quantitatively predicted according to evaluation results. The invention discloses a cable state multi-source data fusion and prediction system. The system comprises a data acquisition module, a feature processing module, a prediction analysis module and a cloud management platform. The system collects partial discharge, surface temperature and vibration data of the cable through the distributed terminal; performing spectrogram decomposition and fusion of the multi-source data by adopting a non-subsampled contourlet transform algorithm to generate multi-scale fusion features; building a prediction model based on a particle swarm optimization least square support vector machine, and outputting an insulation aging state prediction value, a current-carrying capability evaluation value and a fault probability prediction value of the cable; and data management and full-life-cycle service are realized through the cloud platform.

The invention provides a dynamic modeling simulation method and system for the energy efficiency ratio of a solar seawater desalination system, and belongs to the technical field of seawater desalination and system modelling. Membrane surface resistance, selective permeability and direct-current bus voltage ripple data in the photovoltaic electrodialysis process are firstly obtained; secondly, Fourier transform is carried out on ripple data, then the ripple data and membrane parameters are spliced to generate an input matrix, the matrix is imported into a deep belief network, and a restricted Boltzmann machine is used for extracting an unsteady-state ion impedance vector reflecting the influence of voltage fluctuation; a nonlinear regression model of the vector and unit water production energy consumption is established through a least square support vector machine; finally, the water production rate and the energy efficiency ratio are calculated according to the predicted energy consumption and the photovoltaic power, and a dynamic simulation curve is generated. According to the method, the nonlinear influence of the photovoltaic voltage ripples on the membrane impedance can be quantified through deep learning, and the precision of predicting the energy efficiency ratio of the seawater desalination system under the fluctuating power supply working condition is remarkably improved.

The application discloses a kind of power forest fire intelligent monitoring method, device and equipment based on through remote fusion, and storage medium, it is related to forest fire intelligent monitoring technical field, comprising: obtaining the position information of first monitoring node, and obtaining the temperature and humidity data and smoke concentration data corresponding to position information as environmental data;Position information and environmental data are input into least square support vector machine model for processing, and fire risk probability is obtained;When fire risk probability is greater than preset risk threshold, position information, environmental data and fire risk probability are combined to obtain fire preliminary screening information, and fire preliminary screening information is uploaded to cloud server, so that cloud server fuses satellite remote sensing data to complete fire confirmation, realize the non-blind area monitoring coverage of power forest fire along transmission line, realize the preferential transmission of key fire data, reduce communication resource waste, improve system response speed and transmission reliability of key data.

The present disclosure belongs to the technical field of power systems, and particularly relates to a load ultra-short-term prediction method and system based on a least squares support vector machine, which comprises the following steps: obtaining historical load of a load point; constructing a prediction model by using a least squares support vector machine; predicting the ultra-short-term load of the load point based on the obtained historical load and the constructed prediction model to obtain a first load ultra-short-term prediction result; calculating the error of the obtained first load ultra-short-term prediction result; predicting the obtained error to obtain an error prediction result; and obtaining a load ultra-short-term prediction result based on the obtained first load ultra-short-term prediction result and the error prediction result.

The application discloses a load prediction method and system based on big data, and relates to the technical field of power grid load prediction.The method comprises the following steps: based on a least squares support vector machine, pre-processing load historical data; through decomposing the load historical data with reduced complexity, obtaining a zero-crossing rate and sample entropy, and determining the multi-frequency components of the load data; through a preset hybrid algorithm and in combination with the multi-frequency components of the load data, training a multi-factor weighted combination analysis model; based on the multi-factor weighted combination analysis model and according to an improved grey wolf algorithm, determining the weight of the load prediction result of each prediction factor module; and weighting and combining the load prediction results of each prediction factor module to obtain a final load prediction result.The application improves the robustness of the model, dynamically updates the model output result, optimizes the weight proportion among the factor modules, and improves the adaptability of load prediction in a complex environment.

The invention discloses a battery SOH estimation method based on a GAF-CNN-GWO-LSSVM, and belongs to the technical field of battery management systems. The method comprises the following steps: extracting a voltage time sequence in a partial charging process of the lithium ion battery, converting the sequence into a two-dimensional image by utilizing a Gramian angular field (GAF) method, and constructing a GASF image and a GADF image; inputting the obtained image into a two-dimensional convolutional neural network (2D-CNN) to extract deep image features; searching an optimal hyper-parameter of a least square support vector machine (LSSVM) model by using a grey wolf optimization algorithm (GWO); and inputting the extracted feature vectors into an LSSVM model to carry out SOH value prediction. The method has both characteristic expressive power and modeling precision, has relatively high adaptivity and engineering practicability, and is suitable for online health state evaluation of the power battery and the energy storage system.

This invention discloses a method and system for monitoring the operating status of power transmission and transformation equipment. First, real-time operating data of the power transmission and transformation equipment is collected and standardized for preprocessing. Then, feature extraction is performed on the preprocessed data to obtain feature data of the power transmission and transformation equipment. A pre-trained least squares support vector machine model is used to obtain the equipment operating status prediction result. Next, the equipment operating status prediction result is converted into a state confidence score. The state confidence scores are then fused using an improved D-S evidence theory method based on Euclidean distance to obtain a comprehensive confidence score for the equipment operating status. Finally, based on the comprehensive confidence score, an exponentially weighted moving average algorithm is used to construct a dynamic threshold for graded early warning of the power transmission and transformation equipment. This invention solves the technical problem that simple models cannot cope with the nonlinear correlation of multiple parameters in power transmission and transformation, and accurately adapts to the actual operation and maintenance needs of multi-parameter collaborative monitoring of power transmission and transformation systems.

The invention discloses a short-term load prediction method and system based on similar days and a combination model, and relates to the technical field of electric power, and the method comprises the steps: determining the meteorological influence factors of a multi-element load through a Pearson's correlation coefficient method, carrying out the similar day selection of the meteorological factors, the load date type and a price mechanism, constructing a historical data set, and carrying out the prediction of the similar days. A historical data set is decomposed into intrinsic mode function components under different frequencies by adopting improved variational mode decomposition, the intrinsic mode function components are predicted by adopting an improved least square support vector machine model, and an optimal short-term load prediction result is output. According to the method, meteorological influence factors are determined, similar days are selected, a historical data set is constructed, the historical data set is decomposed into intrinsic mode function components, the intrinsic mode function components are predicted, an optimal short-term load prediction result is output, a prediction model with higher adaptability is provided, and the accuracy and efficiency of short-term load prediction are improved.

The invention provides a fault identification method, system and device for gas insulated switchgear, and a medium. The fault identification method comprises the following steps: collecting a discharge signal of the gas insulated switchgear; decomposing the discharge signal into eigenmode function components through a time-varying filtering empirical mode decomposition algorithm; wherein algorithm parameters of the time-varying filtering empirical mode decomposition algorithm are optimized through a chaos subtraction optimization algorithm; screening out eigenmode function components with the highest correlation with the discharge signals, calculating the fault features of each screened eigenmode function component, and inputting the fault features into a least square support vector machine for classification and recognition to obtain the fault type of the gas insulated switchgear. According to the invention, the accuracy and stability of signal decomposition can be effectively improved.

The application discloses a road condition recognition method based on multi-source heterogeneous data fusion. Firstly, the application adopts multiple sensors to collect road image data and vehicle speed, acceleration and wheel speed data, then pre-processes each part of data and extracts features by using different algorithms, then performs feature-level fusion and dimension reduction processing on the extracted feature vectors by using a multi-source heterogeneous data space-time fusion strategy, and finally trains and tests by using a least squares support vector machine based on particle swarm optimization to establish a road condition recognition model. Through the pre-processing, feature extraction and recognition model establishment of the data collected by multiple sensors, the application realizes accurate and efficient recognition of road conditions caused by different severe weather. The application can fully exploit multiple sensor resources, and then comprehensively analyze the collected data, so as to improve the road condition classification recognition accuracy and environmental adaptability.

A closed-loop intelligent optimization control system for a boiler combustion process comprises four modules: a system calculation module, a system monitoring module, a system communication module and a system interface module. A system calculation module calculates the optimization quantity of secondary air, burnout air, coal feeding amount offset and oxygen amount fixed value of each layer of the hearth, and meanwhile, if the modeling error is large, an online support vector machine model is updated; in each control period, a system calculation module needs to judge whether a current optimization system is input or not, if yes, the output control quantity is calculated according to the process, and if not, the output control quantity of an original control system is tracked; boiler combustion optimization is researched by means of a neural network and the like; and an online least square support vector machine is developed to establish a boiler dynamic model system, and intelligent closed-loop dynamic combustion optimization control of the boiler is promoted.

The application provides a tool state detection method based on a main shaft current signal, comprising the following steps: designing an orthogonal experiment related to a cutting speed, a feed rate and a cutting depth; collecting a single-phase current of a main shaft motor driver by using a current sensor; collecting a wear amount of a rear tool face of a milling cutter after each experiment, fitting a tool wear curve according to the collected wear amount; performing denoising on the collected original signal of the single-phase current of the main shaft motor driver based on a third-fourth quantile method of a sliding window; extracting time-frequency domain features and time-frequency joint domain features of the single-phase current signal of the main shaft motor driver based on the preprocessed data; selecting n features from the time-frequency domain features and the time-frequency joint domain features as input of a prediction model by using grey correlation degree analysis; establishing a prediction model based on a least square support vector machine regression model, optimizing the prediction model by using a genetic algorithm, and predicting the tool wear amount based on the optimized prediction model.

The invention discloses an aflatoxin G1 content detection method based on terahertz metamaterial resonance enhancement, a terahertz metamaterial absorber is composed of a plurality of periodic structure units, and each periodic structure unit is of a square structure. The periodic structure unit comprises four cross-shaped structures located in the middle and four strip-shaped structures located on the peripheries of the four cross-shaped structures, terahertz spectrum information of aflatoxin G1 solutions with different concentrations is collected based on the terahertz metamaterial absorber, and it is found through analysis that the terahertz spectrum information of the aflatoxin G1 solutions with different concentrations is within the frequency band of 0.5-3.0 THz. Along with the increase of the concentration of the aflatoxin G1 solution, the amplitudes of characteristic peaks at 0.7 THz and 2.1 THz are regularly attenuated and slightly blue-shifted, in the established least square support vector machine model, the performance of the model which is subjected to non-information variable elimination characteristic extraction and adopts an RBF kernel function is better, the RP is 0.9451, and the detection limit LOD is 2.18 * 10 <-6 > mu g / ml. With the adoption of the method, rapid, nondestructive and high-sensitivity detection of the aflatoxin G1 can be realized.

The application provides a short-term power load prediction method based on Spearman-IPSO-LSSVM, comprising the following steps: obtaining historical power load data and corresponding historical meteorological data of a power grid area to be measured; determining the correlation between the historical power load data and the historical meteorological data based on the Spearman correlation coefficient method, and selecting historical meteorological data with a correlation greater than a preset correlation threshold as key meteorological data; constructing a least squares support vector machine prediction model based on the key meteorological data; optimizing the least squares support vector machine prediction model by using an improved particle swarm optimization algorithm to obtain a least squares support vector machine optimization model; and predicting power grid load feature data at a time to be predicted based on the least squares support vector machine optimization model to obtain a prediction result of the power grid load, which can improve the generalization ability and parameter optimization efficiency of the least squares support vector machine optimization model and improve the accuracy of the prediction result.

The invention relates to the technical field of textile machinery control, in particular to a key quality characteristic cooperative control method for an air-jet vortex spinning machine, and aims to solve the core problems of low strength, poor evenness and high fiber falling rate of air-jet vortex spun yarns in China. The method comprises the following steps: firstly, constructing a'strength-evenness-fiber falling rate 'multi-quality characteristic coupling relation model by utilizing a cross coupling technology, measuring the coupling degree of the three parts through an entropy coupling algorithm, and clarifying an interaction rule among the characteristics; then designing a fuzzy controller based on the Lie group theory and T-S fuzzy logic, tracking tension-detail-weak ring online data and solving an optimal'balance point '; combining expert knowledge and a least square support vector machine to construct a quality characteristic analysis model and a data deviation model, and integrating through a generic relationship theory to obtain a model controller; and finally, fusing the two controllers by using an H-infinity robust control theory to form a combined controller to realize cooperative control.

The present application relates to the field of power systems and their digitization technology, and more particularly to a power transmission and transformation equipment data filling method and system based on time series prediction, which infers missing values through small least squares support vector machine and dynamic Bayesian network, and replaces missing data in complete time series curves with existing data rules; It shows strong robustness when dealing with long-time data missing or sudden abnormalities, and can effectively avoid model distortion caused by data blank; Through the continuity prediction of time series and the filling of blank data, the digital twin model will maintain its real-time and accurate reflection of the operation state of the power transmission and transformation equipment; This provides more reliable support for equipment fault diagnosis, state monitoring and predictive maintenance, thereby improving the operation efficiency and safety of the power transmission and transformation equipment.

The application provides a kind of six-dimensional force fiber optical bone drill operator dynamic modeling and its online error compensation method, it is related to optical fiber sensing technical field, the method steps include the six-dimensional force sensor with eight optical fibers is configured, four optical fibers are vertically suspended, and the other four optical fibers are inclined to be suspended, a segment of fiber bragg grating is arranged on each optical fiber;The six-dimensional force sensor is subjected to step calibration test, the center wavelength drift of eight gratings is recorded, and the actual applied force value is used as reference value to construct measurement dataset;Based on the measurement dataset, the improved great white shark optimization algorithm is used to optimize the least squares support vector machine model, the six-dimensional force sensor is dynamically modeled, and the best decoupling model representing the nonlinear dynamic relationship between the six-dimensional force sensor wavelength drift and the six-dimensional force value is obtained, and the best decoupling model is used to decouple the center wavelength drift of fiber bragg grating into six-dimensional force output.

The invention belongs to the technical field of data processing, and particularly relates to an online analysis instrument nonlinear error correction method based on manifold learning, and the method comprises the steps: obtaining a high-dimensional feature vector set containing original physical quantity readings and auxiliary environment parameters; and calculating a signal transient response entropy and an environmental coupling stress index of the data of each dimension, and further deducing a manifold tangent space distortion rate representing the bending degree of a data structure. On this basis, distortion weighted distance measurement is constructed to replace a traditional Euclidean distance, high-dimensional features are mapped to a low-dimensional space by using an improved local linear embedding algorithm, and finally an error prediction model is established through a least square support vector machine. According to the method, physical perception measurement is introduced, so that the problems of data manifold curling and Euclidean distance failure caused by sudden change of the environment are reduced, neighborhood selection errors are avoided, and the measurement precision and stability of the instrument in the multi-physics coupling environment are improved.

The present application relates to water body COD detection technical field, specifically to a kind of water body COD detection method based on spectral technology, comprising the following steps: S1: obtaining standard absorbance data: using ultraviolet absorption spectrometry, the spectral data of COD standard solution is collected, and standard absorbance data is obtained;S2: the characteristic extraction of standard absorbance data is carried out by continuous projection algorithm, and the standard absorbance data is screened using feature information;S3: with least square support vector machine as detection model, the data obtained by step S2 screening is divided into training set and test set, training detection model using training set, then the detection result accuracy of detection model is tested using test set;S4: the absorbance data of the water sample to be measured is collected, and the detection model obtained in step S3 is used to detect the COD content of the water sample to be measured;The present application determines the detection model parameter using particle swarm optimization algorithm, and the COD content of the water sample to be measured can be accurately obtained by obtaining the detection model.

The invention belongs to the technical field of thermal power generating unit boiler combustion system optimization, and provides a multi-stage dynamic heterogeneous proxy model combustion optimization method for a thermal power generating unit boiler system. Comprising the steps of data acquisition and core operation variable screening, multi-objective optimization problem construction, normalization processing, preliminary fitting, local refinement, weighted fusion, knowledge base construction, knowledge migration and retraining, and global optimization and combination updating. According to the method, a heterogeneous modeling framework comprising a Kriging model, a least square support vector machine and an El-l recurrent neural network is constructed, and a multi-stage dynamic training and self-adaptive weight fusion mechanism is utilized, so that high-precision characterization of complex nonlinear features of the combustion system is realized; by introducing an adaptive transfer learning strategy, knowledge transfer and model retraining are realized by using historical working condition data, and the modeling and simulation cost is remarkably reduced.

The invention discloses an intelligent strip shape defect judgment method based on strip shape feature data extraction. The method comprises the following steps: firstly, carrying out data acquisition and preprocessing; secondly, carrying out feature extraction on the strip shape data by using a Legendre polynomial; secondly, training a least square support vector machine model by utilizing a plate shape data sample of a known defect category; and finally, carrying out feature extraction on to-be-judged plate shape data, inputting the to-be-judged plate shape data into the trained least square support vector machine model, judging plate shape defect types, and outputting corresponding defect types and severity. According to the method, Legendre polynomial decomposition is adopted, the strip shape data are expressed as the sum of several standard modes, strip shape features are effectively extracted, and the data dimension and complexity are reduced. Compared with the traditional support vector machine algorithm, the least square support vector machine algorithm has higher calculation efficiency and better generalization performance, and can predict the plate shape defect category more accurately.

The invention belongs to the technical field of landslide displacement prediction, and discloses a loess landslide displacement prediction method based on an improved education competition optimization algorithm and an ICEEMDAN-LSSVM, and the method comprises the steps: carrying out the preprocessing and normalization of collected landslide data; decomposing the original displacement sequence into a plurality of intrinsic mode functions and residual terms by utilizing adaptive noise complete ensemble empirical mode decomposition (ICEEMDAN); a least square support vector machine (LSSVM) model is established, and an improved educational competition optimization algorithm (IECO) is adopted to carry out automatic optimization on kernel parameters and penalty coefficients of the model. According to the IECO algorithm, population diversity is enhanced through Latin hypercube sampling, adaptive t distribution variation and multi-scale Gaussian collaborative variation strategies are introduced, and dynamic balance between global exploration and local development is achieved. And finally, superposing and reconstructing prediction results of the components to complete displacement prediction. The method has the advantages of high prediction precision, strong robustness and the like, and provides reliable technical support for early warning and prevention and control of landslide disasters.

The invention discloses a quantitative identification and classification method for different types of rock breaking modes of a surface mine. The method comprises the following steps: acquiring vibration signals of different types of rock breaking modes of the surface mine to obtain an original vibration data set; performing time-frequency peak de-noising processing on the original vibration data set to obtain a real data sample; converting the one-dimensional vibration signal in the real data sample into a two-dimensional feature image based on a GAF coding method; inputting the two-dimensional feature image into a multi-scale convolutional neural network model for feature extraction, and taking features output by a full connection layer of the multi-scale convolutional neural network model as input of a least square support vector machine classifier; and adopting an eagle-Cauchy improved sparrow optimization algorithm to optimize hyper-parameters of the least square support vector machine classifier, and outputting a classification result of the rock breaking mode.

The invention relates to the technical field of signal detection, and discloses a pipeline leakage detection method based on an acoustic emission signal and DBN-GA-LSSVM hybrid architecture, computer equipment, a computer readable storage medium and a computer program product in order to solve the problem of low detection precision of a traditional pipeline leakage detection method. The method comprises the following steps: collecting an acoustic emission signal during pipeline operation; converting the acoustic emission signal from a one-dimensional time-domain signal into a two-dimensional time-frequency scale map by using continuous wavelet transform; non-local mean filtering and self-adaptive histogram equalization are adopted to process the scale image, and an enhanced leakage induction scale image is obtained; inputting the enhanced leakage induction scale map into a deep belief network, and outputting a feature vector; optimizing the feature vector by using a genetic algorithm; and inputting the optimized feature vector into a least square support vector machine, classifying the health state of the pipeline, and realizing leakage state identification or leakage-free state identification. By adopting the method, the accuracy of pipeline leakage detection can be improved.

The application provides a fire spreading prediction method and device for a power transmission line, and relates to the technical field of computer processing.The method comprises the following steps: collecting combustible branch data and meteorological branch data; inputting the combustible branch data and the meteorological branch data into a fire burning probability model, and extracting combustible features and meteorological features which are associated with fire burning; wherein the fire burning probability model adopts a least squares support vector machine to classify data, analyzes conversion values corresponding to burning state records in a preset range of the power transmission line, and determines data which is associated with the fire burning state according to the conversion values; and integrating the combustible features and the meteorological features into a three-dimensional cellular automaton, simulating a fire spreading process based on a starting position and a starting time of the fire, and determining a fire spreading prediction result.

The invention discloses an electric power mountain fire intelligent monitoring method, device and equipment based on conduction remote fusion and a storage medium, and relates to the technical field of mountain fire intelligent monitoring, and the method comprises the steps: obtaining the position information of a first monitoring node, and obtaining the temperature and humidity data and smoke concentration data corresponding to the position information as environment data; inputting the position information and the environment data into a least square support vector machine model for processing to obtain a fire risk probability; when the fire risk probability is greater than a preset risk threshold value, combining the position information, the environment data and the fire risk probability to obtain fire preliminary screening information, and uploading the fire preliminary screening information to a cloud server, so that the cloud server fuses satellite remote sensing data to complete fire confirmation; non-blind area monitoring coverage of electric power mountain fire along the power transmission line is achieved, priority transmission of key fire data is achieved, waste of communication resources is reduced, and the response speed of the system and the transmission reliability of the key data are improved.

The invention discloses a jackfruit quality evaluation method based on microminiature hyperspectrum combined with machine learning, and the method comprises the steps: obtaining hyperspectral signals of jackfruits with different maturity degrees under the wave band of 713-920 nm, determining physicochemical indexes according to a traditional method, preprocessing the collected spectral signals through the methods of multivariate scatter correction, standard normal variable transformation and the like, and calculating the quality of the jackfruits with different maturity degrees. A jack fruit quality evaluation model is constructed by combining machine learning methods such as partial least squares, a support vector machine and a one-dimensional convolutional neural network on the basis of characteristic wave band screening algorithms such as a continuous projection algorithm and competitive adaptive reweighted sampling, and effective prediction of the jack fruit storage quality is realized by only using 10 characteristic wave band parameters. According to the method, the maturity and key quality indexes of the jackfruit pulp can be nondestructively detected only by collecting the microminiature hyperspectral signals of the jackfruit pulp, and in the links of planting, storing, processing and selling the jackfruit, the technology can remarkably improve the efficiency and accuracy of quality monitoring and support on-site rapid detection.

The invention provides a method for detecting the content of ergosterol in lentinus edodes based on near infrared spectroscopy and application. And rapidly detecting the content of the ergosterol in the shiitake mushrooms by adopting a near infrared spectrum technology, and inputting spectral data of a sample to be detected into the optimal model to obtain a predicted value of the ergosterol, so that the prediction of the content of the ergosterol in the shiitake mushrooms is realized. According to the method, the SG smoothing algorithm and the normalization algorithm are combined to preprocess the spectrum, noise generated when the sensor obtains the spectrum data can be effectively removed, and baseline and scattering correction is carried out; the variable combined population analysis-genetic algorithm is used for carrying out characteristic wavelength extraction on an original spectrum, so that required important variables can be effectively extracted, redundant information is efficiently removed, and the operation rate of the model is improved; the content of ergosterol in shiitake mushrooms is predicted by adopting the least square support vector machine model based on the crown porcupine optimization algorithm, and the model is high in adaptive capacity and high in prediction accuracy. And a new technical approach is provided for rapidly detecting the content of ergosterol.