6701 results about "Random forest" patented technology

The present invention relates to the technical field of monitoring, in particular to a remote monitoring method and system for an aviation obstruction light. The method comprises the following steps: on the basis of an external sensor, acquiring electromagnetic signals sent by an aviation obstruction light; and by means of using a signal processing algorithm, processing the obtained original signals to eliminate noise interference and standardize the signal format, so as to generate signal-purified data. Using a support vector machine and a random forest algorithm in the present invention enhances the fault mode identification capability and the accuracy of predicting device performance degradation trends, and substantially improves the reliability of fault prediction; the combination of a Kalman filter and a multi-level decision tree provides powerful support for the integration and analysis of multi-source data, thereby ensuring the comprehensiveness and effectiveness of decision-making support information; and using a self-organizing map network and U matrix visualization technology not only shows advantages in the aspects of data mode identification and anomaly detection, but also improves the interpretability of data analysis by means of visual image displaying.

The invention discloses a self-adaptive power grid state court intelligent fusion terminal and a control method thereof, relates to the technical field of intelligent power grids, and solves the defects that an existing fusion terminal is insufficient in self-adaptive capability and limited in data processing and analysis capability. Learning power grid state change in real time through a deep power grid dynamic control algorithm and a prediction analysis engine combining LSTM and random forest, and autonomously adjusting a control strategy; the edge calculation and distributed processing module is utilized, so that the data processing flow is optimized, and the data processing speed and efficiency are greatly improved; the application of time sequence analysis and a machine learning model further excavates and understands a complex data mode; the resource configuration efficiency is improved through an intelligent scheduling algorithm, and a cross-layer coordination mechanism is established through a distributed coordination algorithm, so that rapid issuing and feedback collection of a control instruction are ensured; according to the invention, the intelligent degree of the existing fusion terminal is greatly improved.

The invention relates to the technical field of electrical safety, in particular to an electrical operation risk assessment and early warning system based on big data analysis, which comprises a data acquisition module, a data fusion module, a feature extraction module, a risk assessment module, a real-time monitoring and early warning module, a historical data storage and analysis module and a visual monitoring module. Multi-source data are collected in real time by deploying multiple sensors, risk assessment is carried out through Kalman filtering and support vector regression algorithm fusion processing, feature variable extraction and combination of a support vector machine and a random forest algorithm, real-time monitoring and risk level judgment of an electrical working environment are achieved, long-term risk trend prediction is supported, and the risk assessment accuracy is improved. The visual monitoring module provides a basis for optimizing alarm rules and decision support, and displays an evaluation result, early warning information and an analysis result through a visual interface; the system has the advantages of being accurate in data processing, efficient in risk assessment, timely in early warning and the like, and can be widely applied to risk monitoring and safety management of electrical operation.

The invention provides an equipment supervision data real-time analysis method and system, and the method comprises the steps: calculating an energy value of a frequency band corresponding to a sub-band signal, determining the energy characteristics of the surface roughness and dust deposition distribution uniformity of a blade in each sub-band in a square sum form, and generating energy distribution vectors which are arranged according to a frequency band sequence; performing time-frequency analysis on the vibration signal by using the acquired real-time rotating speed information of the gas turbine, identifying a frequency component corresponding to the eccentric distance value of the rotor and the vibration frequency offset, and determining the amplitude of the frequency component; according to the classification result and the real-time rotating speed information, the comprehensive influence index of the material density change rate and the ash deposition layer thickness difference is calculated, the fault early warning level is determined through a weighted average method, and an early warning signal is generated; and according to the change trend of the early warning signal and the blade edge wear degree, a random forest algorithm is adopted to predict a development curve of the vibration frequency offset in the future target time, and real-time equipment supervision analysis data are obtained.

The invention relates to an intelligent industrial equipment state monitoring device and method, and the method comprises the steps: installing a vibration sensor, an acoustic sensor and an image sensor at key parts of industrial equipment, and comprehensively collecting the operation data of the equipment. In the data preprocessing stage, vibration and acoustic signals are filtered and denoised, and image data are denoised and enhanced. Extracting multi-dimensional characteristic parameters from three aspects of vibration, acoustics and images; a random forest algorithm is adopted for model training, and the method comprises the steps of data preparation, segmentation, decision tree construction, voting mechanism, majority voting, model verification and optimization, testing and the like. In the model identification stage, the real-time features are input into the trained model, and the equipment state is determined through decision tree prediction and voting summarization. And when an abnormal state is detected, setting a multi-level alarm response according to the probability, and generating a maintenance suggestion. According to the method, the whole-process intelligent monitoring of the industrial equipment is realized, and the fault identification accuracy and the maintenance efficiency are improved.

A multi-objective optimization method and system for a shield construction parameter. The method comprises: acquiring an initial shield construction parameter; and optimizing the shield construction parameter by using a multi-objective optimization algorithm, during the optimization of the shield construction parameter, on the basis of the shield construction parameter, obtaining a tunneling speed by means of performing prediction on the basis of random forest, calculating a shield tunneling energy consumption ratio on the basis of the tunneling speed and the shield construction parameter, and taking the maximization of the tunneling speed and the minimization of the shield tunneling energy consumption ratio as two fitness functions of the multi-objective optimization algorithm. The multi-objective optimization method and system for a shield construction parameter take construction efficiency into consideration and reduce the construction cost while ensuring construction safety.

The invention relates to the technical field of data processing, in particular to an intelligent analysis system for electric energy quality and read data, which comprises a data fusion module, a modeling module, an analysis module, a detection module, an optimization module and a control module. The data fusion module aligns data of an electric meter terminal, power grid monitoring equipment and an environment sensor through a sliding time window, and the analysis module calculates a power grid node loss transfer coefficient based on a graph neural network and fuses transformer no-load loss and line contact resistance parameters to generate a dynamic line loss evaluation matrix. And the detection module identifies the power consumption characteristic deviation degree through a random forest classifier, and generates a priority management strategy in combination with a multi-dimensional abnormal scoring model. The control module adaptively selects a communication protocol to execute a regulation and control instruction according to a network state, a heartbeat detection mechanism feeds back operation data of a governance device in real time, model parameters are driven to be iteratively updated, and dynamic cooperation of power supply quality optimization and line loss governance is achieved.

A layout optimization method of water quality monitoring points based on a RF-C-SOM clustering algorithm includes: preprocessing collected water quality data to obtain preprocessed water quality data that are used as data, and using water quality categories as labels to train a random forest model to determine feature importance of water quality indicators; selecting important features based on the feature importance and model training accuracy, performing dimensionality reduction on the preprocessed water quality data to obtain dimension-reduced data; performing a fuzzy clustering on the dimension-reduced data to obtain a water quality section classification result, and based on it, determining initial weight values of a self-organizing mapping algorithm; initializing neurons and training a self-organizing mapping network model with the initial weight values; obtaining a point clustering result through the self-organizing mapping network model; and conducting a water quality index evaluation for the point clustering result before and after screening.

The invention discloses a fault detection visualization processing system and method for an industrial switch, and belongs to the technical field of artificial intelligence. The method comprises the following steps: collecting operation data of an industrial switch from different data sources, performing multi-source data fusion, and constructing a multi-source data fusion data set; extracting abnormal features, training a fault diagnosis model by using a random forest algorithm, inputting real-time data into the model, and performing fault prediction and diagnosis; designing a visual interface, and displaying the operation state and fault information of the industrial switch; functions of real-time refreshing, history backtracking and fault positioning are provided; after a fault is found, a fault source is automatically tracked, a fault propagation path is analyzed, based on a fault type and historical data, a Bayesian network is used to establish a correlation model based on the historical data, and repair suggestions and prevention measures are provided; and analyzing data needing preliminary fault detection, performing preliminary fault detection locally on the industrial switch, and synchronizing edge and cloud data in real time.

The invention discloses a BIM (Building Information Modeling)-based building energy efficiency optimization system and method, particularly relates to the field of building energy efficiency management, and is used for solving the problems of dynamic optimization and collaborative maintenance of building equipment aging and energy efficiency reduction. Initial attenuation data, historical operation data and environmental influence parameters of the equipment are embedded into the data, and dynamic adjustment and real-time tracking of the aging state of the equipment are realized in combination with a sensor network and edge calculation. The maintenance period of the equipment is predicted based on a random forest regression algorithm, a collaborative maintenance plan is generated in combination with physical position information in the BIM, and load optimization and time sequence coordination during multi-equipment maintenance are ensured. By calculating the dynamic adaptability nonlinear response coefficient and the performance regeneration residual nonlinear deviation coefficient, the load adjustment opportunity is accurately judged, the load distribution between the equipment is optimized, the overall energy efficiency of the building is effectively improved, and the full-life-cycle management and energy efficiency optimization of the building equipment are realized.

The invention relates to the technical field of health monitoring, in particular to a cardiovascular disease data fusion and multi-dimensional health assessment method, which comprises the following steps of: acquiring multi-source data of a patient through a sensor and wearable equipment, preprocessing the acquired data, ensuring data integrity, extracting physiological features by adopting a convolutional neural network, and evaluating the health of the patient. The method comprises the steps of extracting non-physiological data features through principal component analysis, constructing a multi-dimensional feature set, identifying cardiovascular disease related risk factors through a random forest algorithm, distributing weights through a logistic regression algorithm to generate individualized risk scores, analyzing time sequence trends of the risk factors based on a long and short-term memory network model, and generating dynamic risk scores in real time. When the score exceeds a preset threshold value, an early warning mechanism is automatically triggered, and a patient and medical staff are notified through an application program; according to the method, accurate assessment and personalized intervention of cardiovascular health are realized through multi-source data fusion and dynamic analysis, and the method has high efficiency and timeliness.

The invention relates to a part surface defect detection and process optimization method and system, and solves the problems that defect detection has defects, missing detection and erroneous judgment are easy to occur, and subsequent process improvement faces huge challenges even if defects are detected, and the method comprises the following steps: inputting a feature set into a double-branch fusion deep learning model, the first branch identifies defect types and quantization parameters by fusing three-dimensional features and two-dimensional features, and the second branch calculates the correlation degree between the defect features and each process through association rule mining and a random forest algorithm; when the three-dimensional features and the two-dimensional features both meet a preset defect threshold value and the association degree of a certain process exceeds a preset value, determining that the process is a root process; and analyzing a deviation value between the key parameter of the source process and the defect quantization parameter, and correcting the parameter through a dynamic adjustment mechanism according to the deviation degree. The method has the advantages that the defects of the part are accurately detected, the procedure is traced, parameters are dynamically adjusted, closed-loop optimization is formed, and the quality of the part is improved.

The invention relates to the technical field of environmental protection, in particular to a big data monitoring and intelligent early warning platform and method for environmental protection. Comprising a multi-source data acquisition module, a data integration and preprocessing module, an environmental risk factor identification module, a real-time monitoring and anomaly detection module, a prediction model and early warning module, a self-adaptive early warning and feedback module and a decision support and visualization module. The data integration and preprocessing module preprocesses multi-source data, the environmental risk factor identification module identifies key risk factors by using an XGBoost algorithm, and carries out accurate prediction and early warning on risks through a random forest and long and short term memory network combination model, and an adaptive feedback mechanism dynamically adjusts an early warning threshold value, so that the early warning efficiency is improved. According to the invention, the intelligent level and the scientific level of environmental protection are obviously improved.

The invention discloses a low-altitude unmanned aerial vehicle flight statistical system, and relates to the technical field of air traffic management. A flight statistical system of a low-altitude unmanned aerial vehicle comprises a multi-source sensing fusion module, a twin airspace modeling module, a behavior portrait modeling module, a non-cooperative target recognition module, a flight statistical analysis module and a self-adaptive scheduling module. According to the invention, a three-dimensional twin airspace model of a monitoring area is constructed based on high-precision map data, a building three-dimensional model and flight information, and space mapping and collision risk analysis of a flight path are carried out, so that real restoration of the flight path and environment collision prediction are realized; the behavior feature vector is generated and the random forest algorithm is adopted to carry out classification modeling, and the behavior portrait of the unmanned aerial vehicle is constructed, so that accurate identification and classification of the behavior pattern of the unmanned aerial vehicle are realized.

The invention provides a soil fertility quality analysis method and system based on corn planting cultivated land, and relates to the technical field of soil quality analysis and evaluation.The soil fertility quality analysis method comprises the steps that a visible-near infrared spectrum image of a soil sample is collected, reflectivity data of a key wave band is extracted from the spectrum image, and a soil health index and a nutrient balance index are calculated; calculating a soil fertility quality comprehensive score for comprehensively evaluating the soil fertility according to the soil health index, the nutrient balance index and the soil moisture content; comparing the comprehensive score of the soil fertility quality with a preset threshold value, and evaluating the soil fertility; a machine learning model is introduced, historical soil data is trained and predicted, a quality analysis model is constructed based on a random forest algorithm, the trained quality analysis model is put into use, and new data is continuously learned to dynamically adjust and update, so that the soil detection process is simplified, and the soil fertility change can be monitored in real time. And agricultural managers are helped to make scientific decisions.

The invention relates to the technical field of computers, and discloses a cultivated land resource quality grade evaluation management method and system, and the method comprises the steps: carrying out the spectrum residual error normalization processing of a multi-temporal remote sensing image, generating a corrected image sequence, effectively inhibiting the reflectivity difference caused by the alternation of wetting and drying of a water body, and achieving the evaluation of the quality grade of cultivated land. A first boundary result and a second boundary result are respectively extracted by using depth segmentation and progressive edge detection, the adaptability and robustness of boundary extraction are enhanced, a difference graph is further generated based on a complex phase difference matrix, the second boundary is corrected, a coherent boundary result is obtained, the boundary time sequence consistency is remarkably improved, and the robustness of boundary extraction is improved. And finally, the cultivated land parcel units are constructed based on the coherent boundaries, and the random forest model is input to complete scoring and grading, so that the stability and traceability of the cultivated land quality evaluation result under multiple temporal conditions are ensured, and the technical targets of stably extracting the boundaries and accurately completing grading in a dynamic change scene are achieved.

The invention relates to the technical field of geological disaster intelligent monitoring, in particular to a geological disaster intelligent monitoring system and method based on multiple sensors. The method comprises the following steps: covering a monitoring area through multiple sensors, and collecting and summarizing environment data; separating effective signals and noise by adopting a space-time adaptive decomposition method, completing data denoising by combining a signal-to-noise ratio dynamic threshold and a local weighted regression smoothing trend residual error, then aligning time and dimensions through linear interpolation and standardization, and integrating multi-sensor data based on an adaptive weighted fusion method; the fused data is subjected to generation and review of a to-be-reviewed mark, so that the data integrity is ensured; key features are extracted, a mixed model based on LSTM and a random forest is constructed to evaluate disaster risks, and a risk grade division rule is set; and finally, outputting fusion data and an analysis result, and generating an early warning signal and a decision suggestion for potential geological disasters. According to the invention, accurate monitoring and risk assessment of geological environment changes are realized.

The invention discloses a geological disaster early warning method and system based on big data analysis, and particularly relates to the technical field of geological disaster early warning. Geological deformation time series data of a target area are obtained through satellite remote sensing monitoring, feature importance is evaluated through a random forest algorithm, and regional geological risk grades are divided; meanwhile, wavelet transformation and long-short-term memory network modeling are carried out on rainfall spatio-temporal data of the meteorological monitoring station, and the potential influence of rainfall is evaluated; high-risk areas are screened, an underground water level change rate and rock-soil body strength correlation model is constructed, and a support vector machine algorithm is adopted to evaluate the landslide probability; and finally, analyzing a geological risk grading result, the potential influence degree of rainfall on the target area and the landslide occurrence probability by adopting an analytic hierarchy process, calculating a comprehensive risk index, comparing the comprehensive risk index with a comprehensive risk threshold value, and judging whether to trigger grading early warning, thereby realizing data fusion and intelligent analysis, early warning in advance, and improving the early warning efficiency. And effective help is provided for disaster prevention and reduction.

The invention discloses a multi-path recall mixed retrieval method and system based on intelligent dynamic weight distribution, and aims to solve the problems that semantic comprehension and keyword matching are difficult to balance and the adaptability is poor due to the adoption of a fixed weight in the existing retrieval technology. The invention provides a multi-path recall mechanism fusing vector semantic retrieval, BM25 keyword retrieval and entity retrieval. A query feature vector containing 13-dimensional features such as semantic complexity, keyword density and entity coverage rate is constructed, a query type is recognized in combination with an SVM and a random forest integration model, a dynamic weight distribution algorithm is designed, and the final weight of each retrieval path is calculated in real time. And an adaptive multi-source enhanced reciprocal ranking fusion (AMSE-RRF) algorithm is further adopted to carry out optimization fusion on multiple paths of results, and a depth reordering model can be selected to improve the precision. According to the method, the accuracy and robustness of retrieval can be remarkably improved in multiple scenes of medical treatment, finance, government affairs and the like according to a millisecond-level self-adaptive adjustment strategy of query features.

The present invention provides a tool wear state monitoring method and system based on multiple types of signals, and relates to the technical field of data processing. The method includes: obtaining data of a cutting force, an acoustic emission signal and a vibration signal, and extracting a plurality of statistical features from data of the cutting force and the acoustic emission signal; extracting a singularity feature from the vibration signal by combining a singularity analysis with a wavelet transform; building a tool wear state monitoring model based on a random forest, using an obtained feature to perform preliminary training, and outputting a wear prediction result; and based on the real-time data of the cutting force, the acoustic emission signal and the vibration signal, monitoring the wear state of the tool through the refined model.

The invention belongs to the technical field of intelligent forecasting of ship performance, and discloses a ship resistance forecasting method and system based on a physical information neural network. The method comprises the following steps: carrying out numerical simulation on the direct navigation motion of a ship in still water to obtain a pressure field and a speed field of a watershed and ship resistance information during the direct navigation motion; constructing and forming a total data set, and establishing a training set, a test set and a verification set; establishing a PINN neural network model fused with physical knowledge; obtaining a neural network model based on physical information; generating a random forest model and training; and performing bidirectional verification on the neural network model based on the physical information by using a random forest model to form a network model for ship resistance forecasting. According to the method, the reliability of the forecasting result in the physical level is effectively improved, and the training efficiency of the neural network model is improved, so that the forecasting efficiency is improved.

The invention provides a road construction project carbon emission ratio toughness analysis method, and belongs to the technical field of carbon emission, machine learning and big data analysis and mining, and the method comprises the steps: obtaining a historical change trend of a carbon emission ratio from historical data of a road construction project, and constructing a dynamic change model of the carbon emission ratio in combination with real-time monitoring data; determining the influence degree and the action mechanism of the interference factors on the carbon emission ratio dynamic change model by analyzing the interaction relationship between the carbon emission ratio and the interference factors; key fluctuation characteristics are extracted from the corrected change trend of the carbon emission ratio, and whether fluctuation of the carbon emission ratio exceeds an acceptable range or not is judged in combination with a preset threshold value; if the fluctuation of the carbon emission ratio exceeds a preset threshold value, performing noise reduction processing on the data by adopting an adaptive filtering algorithm to generate noise-reduced carbon emission ratio data; and training the segmented analysis result by adopting a random forest model in a machine learning algorithm to generate a prediction model of the carbon emission ratio.

The invention relates to the technical field of 5G networks, in particular to a 5G network intelligent optimization method and system, and the method comprises the steps: obtaining 5G network signal data, recognizing an abnormal power spectral density region, carrying out the filtering extraction of the abnormal power spectral density region, and separating interference signals, interference types including narrowband interference, broadband interference and directional interference; extracting features from the obtained interference signals, and performing interference type identification according to a random forest algorithm; starting a corresponding anti-interference means according to the interference type, and generating operation state data in real time; a bee colony algorithm is adopted to simulate bee behaviors for iterative search, and a local optimal resource scheduling strategy is determined; and executing the resource scheduling strategy, feeding back an execution effect, and restarting the bee colony algorithm to determine a new resource scheduling strategy if the execution effect does not reach a set expectation. Therefore, the problems of lack of dynamic adaptive adjustment, single anti-interference means, lack of cross-base station collaboration and the like in the anti-interference aspect in the prior art are solved.

The invention relates to the technical field of fault diagnosis, in particular to an AI-based power system fault diagnosis and early warning system, which comprises a data acquisition module, a data processing module, a fault mode identification module, a fault diagnosis module, an early warning module and a decision support module, multi-source data related to power system fault diagnosis are collected in real time, the data processing module carries out preprocessing and feature extraction on the collected data, and the fault mode recognition module constructs a fault mode recognition model based on a long short-term memory network, a random forest and a convolutional neural network and recognizes a fault mode. The fault diagnosis module carries out fault diagnosis based on real-time data, the early warning module carries out early warning on possible faults in advance according to a diagnosis result, and the decision support module generates an emergency scheduling scheme according to fault diagnosis and early warning information. And the stability and safety of the power system are improved.

The invention provides a deep learning-based rapid ore sorting method under adaptive illumination intensity, and relates to the technical field of ore sorting, the deep learning-based rapid ore sorting method comprises the following steps: obtaining illumination intensity distribution information and ore three-dimensional point cloud data, and calculating ore space orientation parameters based on quaternion attitude estimation; inputting the obtained data into a layered illumination compensation network, and obtaining an illumination normalized enhanced image through adaptive brightness mapping and local light spot correction in combination with reflectivity recovery and non-local mean filtering; inputting the illumination normalized enhanced image and the ore three-dimensional point cloud data into a multi-branch feature extraction network, constructing feature high-order association, and adopting adaptive feature reconstruction and conditional random field optimization features; and inputting the reconstructed features into a classification model based on active learning, optimizing a feature manifold space by using a self-organizing mapping network, carrying out sample labeling in combination with active sampling of adaptive entropy threshold screening and uncertainty perception, and realizing ore classification and sorting through random forest integration.

The invention discloses an intelligent management platform suitable for a power plant, and relates to the technical field of power plant management, and the platform employs an intelligent scheduling system and a DDPG algorithm, and dynamically adjusts a power generation strategy according to the real-time equipment health score, residual life prediction, and the change of energy price and load demand. The power plant can quickly make adjustments when the load demand changes sharply, preferentially dispatch efficient and low-emission equipment, improve the overall energy efficiency and reduce energy waste, and through integration of a sensor network and edge computing, key operation parameters of the equipment are collected in real time, and a dynamic maintenance plan is generated based on health scores and residual life prediction of the equipment. The equipment about to break down is preferentially processed, the random forest model is used for health state evaluation and fault probability prediction, the health score of the equipment can accurately reflect the running state of the equipment, the maintenance time is dynamically adjusted in combination with the load condition of the equipment, and excessive maintenance or maintenance lag is avoided.

A forest point cloud reconstruction method and system based on combination of a handheld radar and an unmanned aerial vehicle, relating to the technical field of remote sensing. The method comprises: on the basis of an unmanned aerial vehicle and a handheld radar device, using a multi-band radar sensor to perform forest terrain and vegetation information acquisition to generate original radar data. The use of the multi-band radar sensor improves the data acquisition accuracy and the coverage range, so that forest terrain and vegetation information is recorded more comprehensively and accurately; a generative adversarial network improves the data quality, and reduces the noise, thereby ensuring the accuracy of subsequent analysis; a convolutional neural network and a random forest algorithm are combined to improve the accuracy of vegetation classification and terrain feature recognition; the generation of comprehensive environmental feature data integrates multidimensional environmental parameters, providing richer information for in-depth analysis; a three-dimensional point cloud model visually displays a forest structure; and time series analysis and a long short-term memory network improve the accuracy of forest change trend prediction, and provide decision support for forest management strategies.

A carbon measurement method for unorganized emissions of greenhouse gas in industrial parks. Through random forest machine learning, combining with cubic spline interpolation and BP neural network to optimize the thought of interpolation, obtaining the influencing factors, and outputting the evaluation report of the impact of the prediction model and meteorological environment on unorganized emissions, obtaining the input variables in the simulation model, Combining equations for simulation, thereby obtaining a specific flow value of unorganized emissions at a certain moment, then multiplying by the concentration of unorganized greenhouse for gas emission, and obtaining carbon emissions, so as to realize the carbon measurement of unorganized emission in industrial parks.

The invention discloses an equipment state sensing system based on peak shifting and danger situation sensing, which relates to the technical field of electric digital data processing and comprises a data acquisition unit, a model training and optimizing unit, a situation sensing unit, a peak shifting regulation and control unit and a system interface and user interaction unit. According to the method, the device state data feature similarity is dynamically calculated by using the Gaussian kernel function, the similarity matrix is adjusted in combination with the gradient update item, dynamic weighting is performed in feature extraction, and redundant features are reduced by adopting the adaptive discarding probability, so that the feature extraction efficiency of the model in a high-dimensional feature space is improved; the problem that the dimension reduction effect is affected by too many redundant features of the equipment state data is solved. Equipment state features are extracted layer by layer through a deep forest algorithm of a multi-layer random forest structure, a decision tree is optimized in combination with a dynamic adjustment weight mechanism and a reinforcement learning strategy, and the classification capability of the model for equipment state changes and abnormal states is enhanced.

The invention relates to the field of particle size distribution measurement, in particular to a particle size distribution measurement method and system based on machine learning and a light scattering method.The method comprises the steps that a to-be-measured particle sample is irradiated through a light source, and meanwhile light scattering intensity data of different scattering angles and different wavelengths are collected through a multi-angle scattered light detector; constructing a multi-modal deep learning model, and forming an integrated learning architecture in combination with a support vector machine model and a random forest model; inputting the preprocessed multi-wavelength light scattering intensity data into the trained integrated learning architecture to obtain a preliminary particle size distribution result of the to-be-detected particle sample; based on the improved Mie scattering theory, a high-precision theoretical model considering the particle shape, the refractive index, the surface roughness and the internal structure is constructed; an improved Bayesian optimization algorithm is adopted, and the initial particle size distribution result is optimized and adjusted by minimizing the error between the theoretical light scattering intensity and the actually collected light scattering intensity, so that a corrected particle size distribution result is obtained.