328 results about "Multivariable linear regression" patented technology

The invention discloses a strip-shaped compound planting mode water and fertilizer zoning management method and system, and relates to the technical field of modern agriculture, and the method comprises the following steps: installing a sensor network in a field, collecting data through a soil moisture sensor, an intelligent water meter and an unmanned aerial vehicle multispectral camera, threshold values are set according to the water demand and the fertilizer demand in the crop growth cycle to judge fertigation, crop demands are predicted by applying multiple linear regression and a random forest algorithm, a fertigation plan is optimized, the growth trend is analyzed, the yield potential is evaluated, the influence of the irrigation level is researched, and an irrigation strategy adjustment suggestion is provided. The system collects field data through an integrated sensor network, accurately sets an irrigation and fertilization threshold value, predicts crop demands by using an advanced algorithm, optimizes a water and fertilizer management plan, effectively analyzes a growth trend and evaluates yield potential, provides a scientific basis for irrigation strategy adjustment, and significantly improves modern agricultural production efficiency and resource utilization efficiency.

The invention discloses an artificial intelligence rice water and fertilizer real-time monitoring method and system, and relates to the technical field of agricultural intelligent decision making, and the method comprises the steps: inputting a farmland feature data set into a soil thermodynamic diagram generation model, carrying out the high-resolution reconstruction of the farmland feature data set through a GAN adversarial network, and generating a whole-field high-precision soil thermodynamic diagram; based on the whole-field high-precision soil thermodynamic diagram, a collision relation between the fertilization amount and historical farming data is detected according to an FCL causal algorithm, a preliminary causal diagram is generated, and a causal diagram structure of the fertilization amount and the historical farming data is constructed by adopting a multiple linear regression method; based on a causal diagram structure, the multi-order causal effect of the fertilization amount, the soil parameters and the historical yield is analyzed through a dynamic allocation algorithm, and a water and fertilizer regulation and control strategy is formulated in combination with a multi-objective optimization algorithm. According to the method, the soil thermodynamic diagram generation model is constructed, so that the fuzzy problem of the edge of the field and the salinization area is solved, a high-fidelity soil space state substrate is provided for water and fertilizer regulation and control, and invalid irrigation is reduced.

The invention discloses a supply chain production scheduling optimization method and system based on multi-source data. According to the method, supplier purchase data is extracted through a data crawler, raw material sharing is analyzed in combination with a knowledge graph, and a raw material sharing list is generated; on the basis of delivery records and product attributes, a quality stable value is predicted through linear regression, process similarity is calculated through a text similarity algorithm, and a process similarity matrix is constructed; in combination with historical sales data, a market demand prediction model is constructed by applying multiple linear regression and time sequence analysis. A complex relation among raw material sharing, process similarity and market demands is described through a graph neural network, a product association network graph is generated, an optimal balance point is found between delivery time and a resource utilization rate through Pareto optimization, and a production scheduling scheme is formed; and finally, integrating the performance score, the quality stable value, the raw material sharing list and the production scheduling scheme through an integer programming algorithm, and optimizing a supplier combination. According to the invention, the production scheduling efficiency and precision are improved, and complex business requirements are met.

The invention provides a 110V transformer winding insulation resistance absorption ratio detection method, which belongs to the technical field of transformer windings, and is characterized in that transformer operation state parameters and environmental influence factors are acquired through a multi-channel synchronous acquisition system, and thermodynamic and electrical models are established. The research adopts methods of principal component analysis, numerical integration and the like, an insulation resistance change rule is analyzed under a standard test voltage, a weight coefficient matrix is constructed in combination with an operation state and an environmental factor, a measured value is corrected through multiple linear regression and a correction coefficient method, and finally, the insulation resistance is obtained through statistical average and standard deviation analysis. The accurate evaluation of the insulation resistance absorption ratio of the transformer winding is realized; according to the method, the influence of the complex working environment and the operation state of the transformer on the insulation performance is fully considered, and the problem that various complex factors in the operation process of the transformer cannot be comprehensively considered and compensated in the prior art is solved by adopting the means of mathematical modeling, data correction, statistical analysis and the like; therefore, the technical problem of large deviation of the measurement result is solved.

The invention discloses a collaborative planning method for a regional integrated energy system, and the method comprises the steps: firstly collecting regional historical energy consumption data and various external factor data, and predicting an energy demand through employing a gray prediction and multiple linear regression combined algorithm; exploring existing energy supply facilities in the region and evaluating renewable energy potential; determining a candidate type of the integrated energy system component according to the result, establishing an optimal configuration model, and solving through a particle swarm optimization algorithm; constructing an energy network layout planning model, and determining an optimal topological structure and parameters of the network; establishing a dynamic operation model, and formulating a collaborative operation strategy by using a model prediction control algorithm; and finally, comprehensively evaluating the planning scheme, and analyzing and adjusting the scheme by utilizing sensitivity according to an evaluation result. According to the method, multiple factors are comprehensively considered, and the problems that in existing regional integrated energy system planning, demand prediction is not accurate, resource evaluation is not comprehensive, component configuration and network layout lack optimization collaboration, and the operation strategy is single are effectively solved.

The invention relates to the technical field of carbon emission treatment, in particular to a building full-life-cycle carbon emission calculation method based on multiple linear regression. Comprising the following steps: acquiring carbon emission data of each stage of a building through a BI model, and extracting key characteristic variables such as a material carbon emission coefficient and energy consumption intensity by adopting a Latin hypercube sampling method and a fuzzy clustering algorithm; modeling carbon emission by using a multiple linear regression model, and constructing a carbon emission prediction model; optimizing model parameters through a differential evolution algorithm; and finally, calculating the total amount of carbon emission, analyzing key influence factors in a high-carbon emission stage through a causal reasoning algorithm, proposing an optimization strategy, generating an analysis report, and realizing accurate prediction and effective optimization of the carbon emission in the whole life cycle of the building. According to the method, the carbon emission of the whole life cycle of the building can be accurately evaluated, and powerful support can be provided for optimization decision-making of the carbon emission.

The invention provides a farmland yield prediction method and system based on soil parameter inversion, and the method specifically comprises the steps: collecting the soil profile information and earth surface three-dimensional information of a target farmland through a ground penetrating radar and a laser radar, and carrying out the precise inversion of the water content and porosity of soil based on a water-porosity inversion model, therefore, a high-precision three-dimensional soil distribution model is constructed, crop growth monitoring data is combined, a farmland yield prediction model is established, the relationship among soil structure characteristics, crop growth indexes and meteorological factors is quantified, and high-precision farmland yield prediction is realized. According to the method, through accurate modeling of the double-pore structure and optimization of the multiple linear regression prediction model, yield prediction is more accurate and reliable, and the method is particularly suitable for farmland management under different soil types and meteorological conditions.

The invention relates to the technical field of batteries, in particular to an all-vanadium redox flow battery performance prediction method based on parameter compensation. The method comprises the following steps: firstly, according to structure parameters of an all-vanadium redox flow battery in an energy storage power station, constructing a multi-physical field coupling simulation model comprising electrochemical reaction, ion transmission, fluid dynamics and thermal management; operating the model according to the operating parameters within a preset operating time period, and obtaining galvanic pile performance index data; carrying out sensitivity analysis on the structural parameters by adopting an orthogonal test method, and obtaining a regression coefficient through multiple linear regression; sorting the regression coefficients, selecting a target regression coefficient, establishing a parameter mapping relation according to a performance index fluctuation value, and performing compensation when the fluctuation value change exceeds a threshold value; and finally, determining a weight factor based on an analytic hierarchy process and an entropy weight method, and screening key structure parameters. According to the method, the limitations of fixed parameters and single environment in a traditional method are overcome, and accurate prediction of the performance of the all-vanadium redox flow battery in different operating environments is realized.

The invention discloses a rice polishing precision control method, device and equipment and a storage medium, and belongs to the technical field of rice processing. The method comprises the following steps: fitting a rice processing data prediction model through a multiple linear regression algorithm, inputting rice polishing precision into the rice processing data prediction model to obtain rice processing data, polishing rice to be polished according to the rice processing data, and adjusting working parameters of rice polishing equipment to obtain polished rice. Polishing processing data can be automatically adjusted according to the polishing precision, the conditions that rice is excessively polished and the polishing precision does not reach the standard are prevented, and energy waste is reduced.

The invention relates to the technical field of automatic medical treatment, provides an infusion process control scheme, and particularly relates to an infusion port risk prediction method and device and electronic equipment. According to the method, clinical-related medical data is constructed and screened through a multiple linear regression method to obtain clinical infusion risk-related data, and the clinical infusion risk-related data is coded and subjected to weight updating to obtain an input sequence; and performing risk prediction on the input sequence based on the prediction model to obtain a final risk prediction result.

The invention relates to the technical field of agricultural carbon neutralization, in particular to a cultivated land vegetation NEP simulation and prediction method and device and a medium, and the method comprises the steps: obtaining cultivated land vegetation observation data in a region, and calculating an enhanced vegetation index and a surface water index based on the cultivated land vegetation observation data; calculating the net primary productivity and the soil heterotrophic respiratory capacity in the vegetation growth season; nEP space-time simulation is carried out; obtaining a cultivated land vegetation NEP impact factor in the region, constructing a ridge regression model, and calculating the relative contribution of the cultivated land vegetation NEP impact factor to the NEP; and calculating a regression coefficient by adopting a ridge regression model, establishing a multiple linear regression prediction equation based on the regression coefficient, and performing NEP simulation prediction by adopting the multiple linear regression prediction equation. According to the method, the carbon absorption capacity of cultivated land vegetation in the growing season is accurately simulated by combining climatic change scenes and agricultural management practices, and the relationship among grain production, carbon emission reduction and ecological protection can be balanced.

The invention provides an in-situ curing and repairing method for heavy metals in river sediment. The in-situ curing and repairing method comprises the following steps: S1, detecting the content and physicochemical properties of the heavy metals in the river sediment; s2, designing a repair material formula; s3, preparing and putting a repairing material; s4, mixing and stirring the bottom mud and the repairing material; s5, monitoring and evaluating the repairing effect; and S6, repairing effect feedback and adjustment. According to the method, multiple linear regression, curved surface fitting, self-organizing mapping and mixed density network algorithms are fused, the sediment heavy metal content and physicochemical property data are fully utilized, a repair material formula can be accurately designed, and compared with a traditional single algorithm or empirical formula design, the repair material proportion can better fit the actual pollution condition, and the repair efficiency is improved. The utilization rate of repair materials is improved.

The embodiment of the invention relates to a wear prediction model construction method, a wear prediction method, a wear prediction device and a vehicle-mounted infotainment system, and the method comprises the steps: fitting a multiple linear regression formula, and carrying out the training optimization of the multiple linear regression formula through a training data set, enabling an error term and a loss function value of a wear prediction model to be within a set range, and enabling the precision of the wear prediction model to be improved. And constructing a wear prediction model. Through the wear prediction model, the real-time wear conditions of vehicle tires in different driving environments can be accurately predicted, accurate driving data can be provided during driving, and the vehicle driving safety is improved; and meanwhile, the tire replacement can be reminded, so that the use safety and the use efficiency of the tire are improved.

The invention relates to the technical field of welding, and particularly discloses an anti-fatigue welding process for a long-distance pipeline supporting steel structure. The process comprises the steps that a font groove structure is determined, and pre-welding polishing pretreatment and layered welding are conducted; fatigue samples of weld toe areas with different arc radiuses are collected, crack feature coordinates and stress concentration coefficients are extracted, failure modes are divided based on clustering, the arc radiuses are verified as main control factors of fatigue failure through multiple linear regression, and a core control range is determined by combining process capability indexes; carrying out fatigue verification on the basis of core parameter extension radius gradient, carrying out process compatibility matching in combination with a controllable interval and a thermal deformation interval of equipment, and outputting a radius candidate value through a response surface method; on-site construction constraints are collected, laboratory path space compatibility is analyzed, a formed track is optimized in a segmented mode, and constraint compensation factors are embedded. The anti-fatigue performance of the weld toe area of the supporting steel structure can be improved, and quality guarantee is provided for welding of the long-distance pipeline supporting steel structure.

The invention relates to a brittleness index calculation method and device for a superior paleozoic mud shale stratum. The brittleness index is an arithmetic mean value of an intermediate parameter obtained through Young modulus data and an intermediate parameter obtained through Poisson's ratio data. Wherein the intermediate parameter obtained through the Young modulus data is a normalized value of the Young modulus, and the intermediate parameter obtained through the Poisson's ratio data is a normalized value of the Poisson's ratio. According to the method, multiple linear regression is carried out by using conventional logging data, the shear wave time difference model is constructed to fit the shear wave data, the correlation coefficient between the obtained brittleness index and the rock brittleness index obtained by the array acoustic logging data is high, and the method is suitable for solving the rock brittleness index in the absence of the array acoustic logging data. And calculating the brittleness index of the strong-heterogeneity shale formation aiming at complex mineral components in the paleozoic region.

The invention discloses a method for determining pesticides in water by liquid chromatography and tandem mass spectrometry, which comprises the following steps: acquiring retention time data of different pesticide compounds in a liquid chromatography system, recording retention behavior characteristics of each pesticide compound under optimized chromatographic conditions by adjusting the composition proportion of a mobile phase and a gradient elution program, and determining the retention behavior characteristics of each pesticide compound under optimized chromatographic conditions. Obtaining a standardized retention time spectrum library data set; establishing a quantitative relation model between molecular structure parameters and chromatographic retention time by adopting a multiple linear regression algorithm through key parameters such as molecular weight, polar surface area and lipid-water partition coefficient in the molecular structure parameter matrix, and obtaining a structure-retention correlation prediction model; and constructing a classification prediction model between molecular structure parameters and environmental durability by adopting a support vector machine algorithm through activity index data in the biological activity prediction result, and determining the environmental durability grade of the pesticide compound according to molecular stability parameters and degradation half-life characteristic values.

The invention relates to the technical field of traffic management, and discloses a road low-visibility monitoring method and system based on video analysis, and the method comprises the steps: carrying out the quantification of the degradation features of a reference object region obtained through dynamic recognition in a target road monitoring video, and generating a degradation value sequence of multiple features of the reference object region; and performing spatial-temporal feature extraction on the degradation value sequence to obtain a steady-state feature vector of the reference object region, performing multiple linear regression calculation, performing early warning grading on the road visibility in the target road monitoring video according to the obtained dynamic visibility index of the target road monitoring video, and generating an early warning scheme. Through multi-frame trajectory association and streaming verification, four-dimensional features of a reference object area are synchronously extracted, collinearity features are automatically removed, a high-precision dynamic visibility index is output, the problems of repeated signal calculation and prediction errors are avoided, and the accuracy and stability of road low-visibility monitoring are improved.

The invention provides a circulating water low-turbidity water quality online control process based on alkalinity control. On-line monitoring equipment including an alkalinity analyzer, a turbidity meter and the like is arranged at key positions such as a water inlet of a circulating water system. The alkalinity analyzer adopts an acid-base titration and potential detection technology, the measurement precision reaches + / -0.01 mmol / L, and data is transmitted at least once per minute. By simulating a multi-working-condition experiment and by means of multiple linear regression and a neural network, an alkalinity and turbidity correlation model is constructed, and the prediction accuracy of the model exceeds 95%. And the central control system performs fusion analysis on water quality parameters by applying algorithms such as fuzzy logic and the like and sends an instruction to the intelligent dosing system. The system is internally provided with an advanced algorithm and can adaptively adjust the dosing of the medicament. Practice shows that the process can stably control turbidity and reduce equipment scaling and medicament consumption cost, and has outstanding advantages in the aspect of circulating water quality control.

The invention discloses a saline-alkali soil improvement effect evaluation method based on digital twinning, and relates to the technical field of saline-alkali soil improvement effect evaluation, and the method comprises the following steps: collecting saline-alkali soil improvement effect monitoring data including multi-dimensional soil data, crop growth data and meteorological data, and carrying out the preprocessing of the collected data, calculating the salinization index, fertility index, porosity and permeability of the soil, analyzing the soil improvement effect of the saline-alkali soil to obtain the grade of the soil improvement effect of the saline-alkali soil, and obtaining an improvement effect feedback coefficient by utilizing the preprocessed crop growth data and meteorological data and combining with a multiple linear regression algorithm; the multi-dimensional data acquisition technology, the multiple linear regression algorithm, the digital twinborn model construction technology and the model optimization technology are closely combined with the modern information technology, so that the problems of incomplete analysis data, inaccurate evaluation result and low intelligent degree possibly existing in a traditional evaluation method are solved.

The invention discloses a coal-fired boiler combustion instability monitoring method and system based on multi-parameter fusion, and the method comprises the steps: constructing a hearth flame imaging system which comprises an image detector, a lens, a stainless steel cavity and a cooling air channel; the flame image intensity is converted into radiation intensity through blackbody furnace calibration, and the flame temperature and emissivity are calculated based on the Planck law; extracting flame characteristic parameters including average radiation intensity, temperature, emissivity and standard deviation thereof; constructing a load-flame characteristic parameter model, and predicting parameter reference values under different loads through multiple linear regression; and calculating a combustion instability index CII, carrying out weighted fusion on the normalized deviation of the real-time measured value and the predicted value, and judging that CII is equal to 1 when the flame area is 0 or the average temperature is lower than 900 DEG C. The flame radiation image and the unit operation parameters are fused, and the limitation of traditional single-parameter monitoring is solved; combustion instability dynamic quantitative evaluation is achieved through the CII index, and the method is suitable for early warning of the deep peak regulation working condition.

The invention relates to a wind noise modeling method and system based on machine learning and application, and belongs to the field of marine acoustics and environmental noise modeling, and the method comprises the steps of data preprocessing and feature extraction, hybrid network model building, hybrid network model training and verification. According to the method, a hybrid network model of multiple linear regression and a multi-layer perceptron is constructed based on a known physical mechanism of wind noise and two main noise generation mechanisms of surface turbulence and bubble oscillation, a linear relation and a non-linear relation are modeled respectively, outputs of the two models are integrated through a weighted fusion strategy, and a multi-layer perceptron model is constructed. Smooth transition modeling from a low-wind-speed linear relation to a high-wind-speed nonlinear relation is achieved.

The invention relates to the technical field of exploration and development of water flooded layers, in particular to a sandy conglomerate water flooded layer porosity determination method based on an XRD (X-Ray Diffraction) logging technology, which comprises the following steps of: performing correlation analysis on the content of each mineral in mineral content data and the actually measured porosity of the same group; screening out mineral types of which the determination coefficient with the actually measured porosity is greater than a determination coefficient set value; performing multiple linear regression fitting on the content of each mineral type obtained by screening and the corresponding actually measured porosity of the same group to obtain an optimal multiple linear regression model; and for the rock debris sample of the non-coring section of the reservoir stratum of the glutenite water flooded layer, obtaining the porosity calculated value of the rock debris sample through the optimal multiple linear regression model. The porosity data of the rock debris sample of the non-coring section of the reservoir stratum of the glutenite water-flooded layer can be obtained, and the porosity data of the oil reservoir water-flooded layer of the whole well can be obtained by combining the porosity data of the coring section of the rock debris sample, so that the porosity data of the whole oil reservoir water-flooded layer can be obtained.

The invention discloses a drainage pipe network liquid level and risk prediction method, relates to the technical field of drainage pipe networks, and solves the problems that in the prior art, a hydrology and hydrodynamics mechanism model needs a large amount of basic data and is complex in source, and if the data precision and accuracy are not enough, the deviation between a calculation result of the model and an actual result is large. The invention relates to a method for judging rainy days and screening rainfall periods according to rainfall data. A least square method is adopted to establish a multiple linear regression relation among the independent variable accumulative rainfall capacity, the rainfall duration and the dependent variable pipe network net rising liquid level, algorithm training is completed, and therefore the drainage pipe network liquid level is predicted; the critical rainfall and the rainfall are calculated through the set drainage pipe network liquid level threshold value, the rainfall is compared with the critical rainfall, and whether the drainage pipe network liquid level has risks or not can be judged; according to the method, drainage pipe network facilities and related topographic data do not need to be considered, and the over-fitting phenomenon possibly caused by complicated parameter training is avoided.

The invention discloses an overhead transmission line X-ray intelligent flaw detection method based on a six-rotor unmanned aerial vehicle, and relates to the technical field of X-ray intelligent flaw detection, and the method comprises the following steps: collecting flaw detection data including flight attitude data, X-ray imaging data, overhead transmission line data and positioning data, carrying out preprocessing and feature extraction on the collected data; adjusting the hovering position of the six-rotor unmanned aerial vehicle based on the preprocessed positioning data; and based on an output result of the intelligent flaw detection model, analyzing the severity of internal defects of the overhead transmission line, and further generating an X-ray intelligent flaw detection report of the overhead transmission line. According to the method, a multi-sensor data acquisition technology, a data preprocessing technology, a feature extraction technology, a weight analysis technology, a flight attitude adjustment technology, a multiple linear regression modeling technology and a neural network modeling technology are closely combined with a modern information technology; accurate detection and high-precision positioning of internal defects of the overhead transmission line are achieved.

The invention relates to a mechanical evaluation system based on rotation and inclination of a bracket-free appliance, and belongs to the technical field of orthodontic equipment. The system comprises four core units: an integral dental arch constraint unit simulates oral temperature through a constant-temperature water bath assembly, adjusts model postures through a camera holder type adjustable dental arch base, and constructs a precise constraint environment; the clinical displacement driving unit is based on an anchorage center bearing lever structure, and positioning-driving-data synchronization is achieved through adjustable anchorage positioning, multi-direction servo driving and displacement closed-loop calibration. The single-tooth mechanical sensing unit collects dynamic mechanical data, and interference is removed through Kalman filtering; and the data processing unit corrects attenuation deviation by using multiple linear regression in combination with environmental parameters, generates a mechanical attenuation curve, calculates a time attenuation percentage, and outputs a mechanical evaluation report by comparing with a clinical suitable force application interval. The evaluation accuracy and clinical suitability of the method provide a scientific basis for the optimization of an orthodontic scheme.

The invention belongs to the technical field of battery management, and particularly discloses a parameter identification method of an equivalent circuit model and an SOC estimation method and system.The parameter identification method of the equivalent circuit model comprises the steps that the equivalent circuit model in the charging direction and the discharging direction is built; respectively carrying out mixed pulse tests on the equivalent circuit models in the charging direction and the discharging direction of each SOC point to be tested to obtain voltage and current data of the parameter identification test of each SOC point to be tested; and obtaining key parameters of the equivalent circuit model in the charging direction and the discharging direction by using a multiple linear regression method. The SOC estimation method comprises the following steps: determining a battery SOC estimation path according to an open-circuit voltage change rate; and according to the key parameters and the SOC estimation path of the battery, establishing simulation models in the charging direction and the discharging direction, and obtaining SOC estimation values in the charging direction and the discharging direction of the battery by using the simulation models. The accuracy of the equivalent circuit model can be improved, the SOC estimation precision is further improved, and the method is more suitable for actual working conditions.

The invention relates to a large underground cavern group crustal stress field inversion method under a complex geological condition, and provides a method for inversing a crustal stress field of a large underground cavern group by taking a river valley center line or a ridge line as an inversion numerical model boundary to solve the problems that underground cavern group crustal stress measured data is discrete and difficult to accurately predict under the background of deep river valley terrain and multi-fault development. And selecting actual measurement points which are far away from the fault and are in three-dimensional distribution. The method comprises the following steps: acquiring a displacement boundary and a gravitational acceleration magnitude of a three-dimensional numerical model through limited measured data by adopting stepwise multiple linear regression and evolutionary neural network joint inversion, positively loading the displacement boundary and the gravitational acceleration magnitude to a model boundary to obtain a regional crustal stress field, and extracting measured point data for preliminary verification; and simulating caving excavation, and analyzing whether the stress concentration area is consistent with the observed stress type damage position or not. The method integrates the advantages of the two methods, more optimal solutions can be selected, the problem that precision and calculated amount are difficult to consider in stress field prediction of the complex structure motion area is solved, and the method is suitable for crustal stress field prediction of the complex structure area.

The invention discloses a rural small and micro credit risk assessment method based on a multiple linear regression model. The method comprises the steps of collecting credit data and basic information data; the collected data are preprocessed; screening out independent variables which possibly have obvious influence on the credit default risk; constructing a multiple linear regression model; setting a dependent variable as a credit default risk; using data in the training set to solve parameters of the multiple linear regression model through a least square method or other optimization algorithms; a multiple linear regression equation is obtained; the model is optimized; and performing risk assessment on the newly applied rural personal credit by using the trained multiple linear regression model. According to the method, the relation between the independent variables and the dependent variables is analyzed, and the multiple linear regression model is established, so that the credit risk of rural individuals is predicted and evaluated; and financial institutions can be helped to more accurately evaluate the credit risk level of rural individuals.

The invention discloses an electric power cabinet monitoring and early warning method and device based on big data, and the method comprises the steps: collecting the data of an electric power cabinet in real time through arranging a multi-measurement-point and multi-variable sensor in the electric power cabinet; performing normalization processing on the power cabinet data to construct a power cabinet health monitoring data set; performing feature extraction by using AFFC to obtain a local feature matrix, performing feature extraction by using global local discriminant analysis GLDA to obtain a global feature matrix, and splicing and fusing the local feature matrix and the global feature matrix into a new matrix convenient to predict; a time sequence prediction model PowerMama is adopted to predict operation data of the power cabinet, and a Bayesian optimization algorithm is adopted to optimize model hyper-parameters; error correction is carried out on a prediction result of the model through multiple linear regression and RVFL, finally, prediction data are calculated through an empirical formula to obtain a health value, and whether early warning is carried out or not is judged according to the health value. The method can be applied to the modeling process of health monitoring and early warning of the electric power cabinet, and the accuracy and reliability of monitoring and early warning of the electric power cabinet are ensured.

The invention relates to the technical field of ambient air quality forecasting, in particular to an O3 pollution forecasting method and system based on multiple linear regression. The O3 pollution forecasting method based on multiple linear regression comprises the following steps: S1, acquiring data; s2, preprocessing the data, and constructing an O3 pollution case library; s3, typing the O3 pollution cases according to the meteorological elements; s4, screening proper meteorological elements as forecasting factors for each type of O3 pollution case; s5, establishing a step-by-step multiple linear regression model of meteorological data and pollutant concentration for each type of O3 pollution case, and evaluating a regression effect; and S6, obtaining a future day-by-day weather factor forecast result of the high-resolution atmospheric chemical numerical model, and predicting a future O3 pollution condition by using a multiple linear regression model. According to the O3 pollution event forecasting method provided by the invention, the calculation method is simple, the accuracy of the output forecasting result is high, the O3 pollution forecasting effect is effectively improved, an open research framework is provided for O3 pollution forecasting, and powerful support is provided for related researches such as forecasting and evaluation of O3 combined pollution.