169 results about "Nonlinear prediction" patented technology

The invention relates to the technical field of temperature equalization control, and discloses a temperature equalization control method and device for a liquid cooling over-charging system. The method comprises the following steps: carrying out grid division on the liquid cooling overcharge system, inputting thermophysical parameters, and obtaining a temperature field calculation matrix through finite difference time domain analysis; establishing a two-layer distributed control network of a station-level control layer and a pile-level control layer based on the temperature field calculation matrix; acquiring real-time temperature data of the two layers of distributed control networks, and performing temperature field mapping to obtain temperature field distribution data; performing linear prediction and nonlinear prediction calculation on the temperature field distribution data to obtain a temperature change trend and a temperature extreme point; the target temperature is calculated according to the temperature change trend and the temperature extreme point, the cascade PID controller is adopted to adjust the rotating speed of the cooling liquid pump, and the temperature balance control parameters are obtained, station-level and pile-level cooperative control is achieved, cooling resources among the multiple charging piles are reasonably distributed, and the overall cooling efficiency of the system is improved.

The invention discloses a method for intelligently regulating and controlling production parameters in a fruit concentrated juice production process, which comprises the following steps of: acquiring multi-dimensional process parameters such as temperature, pressure, flow, concentration, equipment state and the like in real time through a multi-channel sensor network, and forming a standardized data sequence after filtering, normalization and drift correction; extracting stage features by using technologies such as a sliding window and Fourier transform, and inputting the stage features into the lightweight classification model to realize production stage identification; in combination with an identification result, dynamically calling a corresponding multi-target optimization sub-model, and realizing nonlinear prediction and optimal solution selection of process parameter setting by adopting an LSTM and a multi-target genetic algorithm; on the basis of real-time feedback, the performance of the model is automatically evaluated, self-adaptive adjustment and optimization of the optimization algorithm are achieved through reinforcement learning and an incremental updating mechanism, multi-target collaborative optimization, self-adaptive adjustment and model switching in the production process can be achieved, and the consistency of production efficiency and product quality is improved.

The invention relates to a mold 3D analogue simulation analysis method, which comprises the following steps: acquiring a three-dimensional CAD model of a mold, carrying out preprocessing and grid division, encrypting grids in a key area, calculating a stress value by utilizing finite element analysis, optimizing the grids through iterative calculation until a convergence requirement is met, and obtaining a stress distribution condition. A support vector machine regression algorithm is adopted to establish a nonlinear prediction model of stress characteristics and fatigue life, mold structure optimization is carried out, an optimization scheme is converted into a CAD model, a machining program is generated, accurate prediction and automatic optimization design of the fatigue life of the mold are achieved, the service life of the mold is prolonged, and the reliability of the mold is improved. And important technical support is provided for 3D analogue simulation analysis of mold design and manufacturing.

The invention discloses a climate mode deviation correction method based on ensemble Kalman filtering and deep learning, and the method comprises the steps: obtaining first climate historical simulation data and future climate estimation data in a research region, and obtaining historical observation data corresponding to climate variables; performing deviation correction on the first climate history simulation data point by point by adopting an ensemble filtering method; carrying out lag processing on the first climate history simulation data; constructing a long short-term memory network model; performing feature engineering processing on future climate estimation data; and performing deviation correction on future climate estimation data by using the average deviation of the Kalman gain sequence and the historical sequence of each time period in the future. According to the method, the dynamic correction capability of the ensemble Kalman filtering and the nonlinear prediction advantage of the deep learning model are combined, the correction precision of climate mode simulation data is improved, and effective deviation correction is carried out on future climate estimation data.

The invention discloses an extradosed cable-stayed bridge cable force optimization method, device and system and a storage medium. The method comprises the steps that S1, cable force and bending strain energy training samples of an extradosed cable-stayed bridge are obtained; s2, optimizing SVM parameters under the cable force and bending strain energy training samples of the extradosed cable-stayed bridge by adopting an IGWO algorithm; and S3, taking the cable force value after secondary tensioning as a to-be-optimized parameter, carrying out iterative optimization by using an IGWO algorithm, taking the cable force combination output after evolution of each generation as an input vector of an SVM for nonlinear prediction, outputting a population fitness value under the current cable force, and repeatedly reducing the time cost when the optimization model carries out fitness evaluation so as to improve the fitness evaluation accuracy. And IGWO-based combination optimization is realized. By the adoption of the technical scheme, the calculation efficiency and calculation precision of the finished cable force optimization of the extradosed cable-stayed bridge are improved.

The invention discloses an energy shaft heat exchange efficiency optimization method based on stratum thermophysical property intelligent analysis, and the method comprises the steps: constructing a structured thermophysical property parameter database through integrating laboratory testing, on-site exploration and literature data, and covering key parameters such as a heat conductivity coefficient, specific heat capacity, a thermal diffusion coefficient and the like; a heat transfer model is verified and expanded by combining a reduced scale physical experiment and multi-parameter coupling numerical simulation; machine learning algorithms such as a random forest and a neural network are utilized to establish a nonlinear prediction model of the thermophysical parameters and the heat exchange efficiency of the energy shaft, the contribution degree of the parameters is quantified, and an adaptability threshold value is defined. Through similarity matching of drilling exploration data and a database, the optimal stratum depth is recommended, and finally a cloud intelligent platform is integrated, so that real-time data updating, online calculation and construction suggestions are realized. According to the method, the precision of stratum suitability evaluation in energy shaft ground source heat pump system development is remarkably improved, and the geothermal energy development efficiency is remarkably improved.

The invention relates to the technical field of solar heat utilization, and discloses an electric energy conversion and power regulation and control method based on a solar heat exchange coupling system, which comprises the following steps: calculating the phase change latent heat release rate and pressure and temperature sensitivity of a working medium in real time through a nonlinear prediction model, and establishing a compensation factor to dynamically correct the fusion weight of temperature and pressure signals; the shape memory alloy runner is driven to adjust the branch angle in a self-adaptive mode within the range of 45-75 degrees; constructing an energy potential matching matrix of the temperature gradient of the heat storage module and the output voltage of the power generation system, and combining a pulse type energy release strategy to maintain power stability; and controlling adjacent flow channel branches to generate a phase difference based on pressure fluctuation spectrum characteristics to realize fluctuation offset. According to the method, through closed-loop control of thermodynamic parameter compensation and flow channel dynamic adjustment and space-time collaborative optimization of energy potential matching and pulse release, continuous and stable power generation under the intermittent irradiation condition is achieved, the overall energy efficiency of the system is improved, and operation is more stable.

The invention discloses a PINN-based magnetic levitation vehicle nonlinear predictive control method and device and a medium, and relates to the field of rail transit, and the predictive control method comprises the following steps: S1, constructing a dynamic model; s2, learning and approaching unknown dynamic and time-varying parameters in the dynamic model by adopting a physical information neural network; s3, designing an optimization cost function meeting system input and output constraints based on the unknown dynamic state of the dynamic model predicted by the physical information neural network; and S4, constructing a step-by-step variable terminal constraint set to process input time lag. In a controller design and theoretical analysis process, a non-linear dynamic form of a system is completely reserved, and a stepping variable terminal constraint set suitable for input time delay is constructed, so that the controller can still maintain stability and dynamic performance under the condition that a system state obviously deviates from a balance point. According to the method, the operation safety and the control precision of the maglev vehicle under complex working conditions such as parameter drift and time lag disturbance are effectively improved.

The invention discloses a stratified fuel cell temperature control method based on adaptive model-free predictive control. The method comprises the steps that firstly, an upper-layer decision maker determines the optimal stack temperature under different working conditions based on a polarization curve of a stack, and the optimal stack temperature serves as the optimal reference temperature to be output to a lower-layer controller; in the lower layer controller, based on real-time input and output data of battery operation, nonlinear prediction of the stack temperature is realized by introducing an auxiliary slack variable. And then an optimal control variable is obtained by solving an optimization problem with constraints in each execution period, and a water pump and a radiator are driven to complete optimal control of the temperature of the galvanic pile. Compared with a traditional control method, the method has the advantages that the dependency on the model is reduced; compared with a traditional model prediction control method, the method has the advantages of being low in calculation complexity, low in requirement for controller hardware and the like, and the problems that the proton exchange membrane fuel cell is high in nonlinearity and coupling performance and large in control difficulty are solved to a certain extent.

The invention relates to the technical field of bridge safety monitoring, and particularly discloses a cable-stayed bridge cable force unbalance vortex vibration early warning system and method based on an intelligent calculation model, and the system comprises a multi-source data collection module, a phase-space reconstruction module, a vortex vibration mode decoupling module, a dynamic threshold setting module, a nonlinear prediction module and an early warning decision module. The vibration signals are mapped to a multi-dimensional phase space according to the phase space reconstruction theory, and multi-order frequency band vortex vibration modal decoupling is achieved in combination with density clustering analysis; establishing a multi-dimensional threshold hypersurface by adopting a support vector machine, and dynamically adjusting a judgment threshold according to the environmental parameters and the structural state; short-term high-precision prediction and medium-and-long-term trend prediction are realized by using a local linearization prediction model; a wind-vortex vibration mapping relation is established through the generative adversarial network; the self-adaptive filtering technology is adopted to eliminate traffic load interference, and the problems that in the prior art, cable force unbalance vortex vibration cannot be accurately recognized, early warning is not timely, and the false alarm rate is high are effectively solved.

The invention discloses a safety risk assessment method and system for a power generation enterprise, and relates to the technical field of enterprise safety assessment, and the method comprises the steps: collecting the equipment data and environment data of the power generation enterprise through a sensor, and carrying out the data preprocessing; performing batch and hierarchical analysis on the preprocessed data, extracting multi-dimensional features, and forming a comprehensive feature set through feature optimization; respectively processing the comprehensive feature set by using a linear model and a nonlinear model, and outputting a prediction result; and carrying out dynamic combination on linear and nonlinear prediction results, and outputting a final risk assessment result. According to the invention, through the multi-level data processing and dynamic combination model, the linear and non-linear relationship in the power generation enterprise equipment and environment data can be comprehensively and accurately captured, so that the accurate assessment of the equipment safety risk is realized. Compared with a traditional method, the accuracy and the real-time performance of risk assessment are greatly improved.

The invention belongs to the field of automatic control of hydroelectric generating sets, and particularly discloses a primary frequency modulation optimization control method and system based on power opening nonlinear prediction.The method comprises the steps that frequency deviation is converted into primary frequency modulation power variable quantity, the power variable quantity and a basic power set point of a set are added, and a dynamic power target is obtained; integrating the power deviation signal to obtain a power integration opening reference instruction; taking the dynamic power target and the unit water head as input of a feed-forward model, and obtaining a feed-forward dominant opening instruction; the opening degree deviation value is input into a PID controller, and a feedback opening degree correction instruction is generated; and a guide vane opening given value is obtained based on the feed-forward dominant opening instruction and the feedback opening correction instruction and serves as a given signal of a guide vane position control loop. According to the invention, through nonlinear prediction and a unique feedback structure, high self-adaption to the working condition change of the unit is realized, and the rapidity, consistency and robustness of the primary frequency modulation response of the unit are remarkably improved.

The invention relates to the technical field of market trend prediction, and discloses a market trend prediction system driven by macroeconomic indicators. An index acquisition module of the system dynamically acquires core economic indexes such as GDP growth rate, CPI, PMI and currency supply; the data preprocessing module is used for carrying out layered noise reduction processing on the multi-source heterogeneous data; the feature engineering module constructs a market sensitive feature set through spatio-temporal feature fusion; the prediction model building module is used for building a multi-layer nonlinear prediction model based on a deep belief network; the dynamic adjustment module adopts reinforcement learning to optimize a decision threshold value and combines a Markov chain to carry out state transition planning; and the feedback iteration module analyzes and predicts deviation through Bayesian filtering and realizes strategy updating. According to the method, deep learning and reinforcement learning technologies are creatively fused, the prediction precision is remarkably improved through a dynamic calibration mechanism, and the method can be widely applied to the macroeconomic analysis fields of financial investment, industrial planning and the like.

The invention relates to the technical field of particle size measurement in the ore grinding production process. The ore grinding granularity soft measurement method comprises the steps of analyzing a time sequence characteristic matrix based on a step-by-step regularization characteristic sorting method, forming an optimized input characteristic matrix, obtaining a linear prediction value based on the optimized input characteristic matrix, and calculating the ore grinding granularity according to the linear prediction value. Performing error calculation on the linear predicted value and the actual measurement value to obtain a nonlinear predicted value, combining the linear predicted value and the nonlinear predicted value according to the weight to generate a preliminary soft measurement model, performing global optimization on the combined weight of the preliminary soft measurement model through a multi-objective optimization algorithm to generate an optimized soft measurement model, and performing soft measurement on the optimal soft measurement model. When the statistical property exceeds a set threshold value, a dynamic correction mechanism is triggered, and an updated soft measurement model is obtained according to the dynamic correction mechanism. The method has the effect of meeting the high-precision prediction requirement under the dynamic working condition.

The invention discloses a time sequence data missing value filling method and electronic equipment, and the method comprises the steps: obtaining to-be-filled time sequence data (having at least one time dimension missing value) for a business scene and multiple groups of reference time sequence data of the same type, and carrying out the similarity calculation of the to-be-filled time sequence data and the multiple groups of reference time sequence data; obtaining a first similar attention matrix between the multiple groups of reference time sequence data and the to-be-filled time sequence data; according to the similarity between each group of reference time sequence data and the to-be-filled time sequence data, performing correlation calculation on each reference value and each missing value in the corresponding reference time sequence data to obtain a first time sequence attention matrix between the multiple groups of reference time sequence data and the to-be-filled time sequence data, and according to the two attention matrixes and to-be-filled time series data, obtaining to-be-predicted time series data, inputting the to-be-predicted time series data into the trained nonlinear prediction model to fill each missing value, and obtaining filling time series data for the to-be-filled time series data.

The invention provides an unmanned aerial vehicle flight control method and system based on a multi-constraint optimization nonlinear prediction model, and the method is characterized in that the method comprises the steps: obtaining multi-mode unmanned aerial vehicle state data and multi-mode flight environment monitoring data which are collected in real time through a multi-mode sensor; acquiring control input including pitching, rolling and thrust motion for controlling the unmanned aerial vehicle; taking the multi-modal unmanned aerial vehicle state data, the multi-modal flight environment monitoring data and the control input as the input of a pre-trained nonlinear prediction model, outputting a yaw control quantity for adjusting the control input, and generating a control instruction for controlling the flight of the unmanned aerial vehicle by using the yaw control quantity and the control input; wherein the nonlinear prediction model takes multiple constraints including a dynamic model constraint, a reference control input constraint and a state constraint as a training target in a training process. According to the invention, high-precision stable control of the unmanned aerial vehicle can be realized.

The invention relates to the field of petrochemical engineering intelligent early warning, and discloses a risk prediction simulation early warning method and system suitable for petrochemical engineering key equipment, and the method comprises the following steps: S1, obtaining the operation state data and environmental factor data of the key equipment through dynamic simulation software; s2, performing cleaning and normalization processing on the data set, and then performing integration; s3, constructing a combined nonlinear prediction model, and performing risk parameter prediction by inputting the complete data set; s4, setting a risk early warning threshold value and an early warning mechanism; s5, updating model parameters, and dynamically optimizing the prediction model; the system comprises a data acquisition module, a data processing module, a risk prediction module, an early warning module and an updating module. According to the method, through a combined model of the recursive random forest and the graph neural network, the equipment dynamic simulation data and the multi-dimensional environmental factors are deeply fused, and accurate and three-dimensional prediction of the potential risk of the equipment is realized.

The invention relates to the technical field of power management control, in particular to a power management control system of a thermal infrared detection system. The power supply conversion and distribution unit is used for converting an external power supply into multiple paths of voltage and distributing the voltage for the first time; the voltage monitoring stability control unit monitors the power supply voltage state of each module in the system in real time; the current protection current limiting unit monitors a power supply current state in real time; the dynamic load regulation unit uses an entropy weight optimization load regulation technology to monitor the entropy change of load fluctuation and the power supply of a priority weight dynamic regulation module in real time; and the redundant power supply switching unit predicts the state change of the main and standby power supplies by using a nonlinear predictive switching optimization technology to optimize a switching path, and performs power supply switching according to the switching path and the switching time. The power supply management control system of the thermal infrared detection system dynamically distributes power supply resources through an entropy weight optimization load adjusting technology, and seamless switching of a main power supply and a standby power supply is realized through a nonlinear prediction switching optimization technology.

The invention relates to the technical field of tunnel excavation, in particular to a prediction method and device for composite stratum tunnel support parameters, and the method comprises the steps: obtaining three-dimensional numerical model calculation parameters; sampling and combining the support parameters and the relationship between the tunnel and the stratum to obtain a three-dimensional numerical simulation calculation working condition group; establishing a three-dimensional numerical model to obtain a control effect of surrounding rock deformation under each three-dimensional numerical simulation calculation working condition; determining the sensitivity of different support parameters to the control effect, and obtaining the influence weight of the different support parameters to the control effect; establishing a prediction model of the support parameters, and adjusting the calculation parameters of the three-dimensional numerical model to obtain a nonlinear prediction function of the support parameters; and predicting and optimizing the support parameters to obtain support parameters meeting preset conditions. Therefore, the problems of unstable surrounding rock, support damage, cost increase and the like caused by support design misalignment possibly caused by exploration errors caused by complex strata in related technologies are solved.

The invention relates to the technical field of SCR denitration systems, and particularly provides an SCR denitration system outlet NOx concentration distribution PDF prediction method. The method comprises the following steps: S1, acquiring NOx concentrations of F different actual point locations of an outlet of the SCR denitration system and historical data of each input variable influencing a NOx concentration distribution probability density function of the outlet of the SCR denitration system, and storing the acquired information to construct a historical data set; s2, estimating a NOx concentration distribution probability density function of the outlet of the SCR denitration system according to the obtained historical data set; s3, representing the probability density function, estimated in the S2, of the NOx concentration distribution at the outlet of the SCR denitration system by using a primary function; and S4, establishing a nonlinear prediction model between the input variable and the first n-1 weight vectors, and predicting the NOx concentration distribution probability density function at the outlet of the SCR denitration system at the next moment.

The invention relates to the technical field of data analysis, in particular to a newborn health data analysis system which comprises a physical sign data construction module, a trend recognition module, a weight distribution module, a nonlinear modeling module and a prediction curve output module. According to the method, the growth cycle of the newborn is subdivided into continuous stages with different physiological meanings, the change rates of the sign data between the adjacent stages are deeply calculated and compared, the dynamic trends such as acceleration, stability or slowing down of body weight and height changes can be accurately recognized, and then quantitative weights are given to the different growth trends; according to the method, the positive growth situation is more evaluated in subsequent analysis, the growth and slowdown situation is correspondingly adjusted, a nonlinear prediction model is constructed on the basis, the non-uniform-speed natural law of growth and development of the newborn can be fit, the staged trend can be dynamically fused into long-term change track prediction, and the prediction accuracy of the growth and development of the newborn is improved. And the health conditions of the newborn in different developmental window periods are disclosed.

The invention discloses a cross-domain coupling control method for an air suspension and an active stabilizer bar. The cross-domain coupling control method comprises the steps that a signal input layer collects and fuses data and transmits the data to a decision-making layer; the decision-making layer forms a control instruction based on a model predictive control algorithm, and comprises the steps of constructing an automobile three-degree-of-freedom coupling dynamic model, and iteratively solving a cost function minimum value in a rolling time domain to obtain the control instruction; the three-degree-of-freedom coupling dynamic model quantifies multi-dimensional motion association through a stiffness matrix off-diagonal term, can accurately predict the cross influence of air pressure adjustment of the air suspension on the roll motion, and provides a nonlinear prediction basis for model prediction control. According to the invention, by cooperating with the multi-dimensional dynamic signal and the dynamic arbitration control logic, the complex composite working condition is adapted, and the cooperative optimization of the vertical comfort, the roll stability and the pitching dynamic characteristic of the vehicle is realized.

The invention discloses a business opportunity recommendation method and device for B-type enterprises, equipment, a medium and a product, and relates to the field of data processing. The business opportunity recommendation method for B-type enterprises comprises the following steps: acquiring association relationship information, industry and commerce information and annual report information of each B-type enterprise in a customer relationship management system; obtaining product data of N historical bidding items with determined bidding results; performing feature extraction on the data to generate a feature set, and constructing a sample data set; and training a nonlinear prediction model based on the sample data set, predicting the bid reference probability of the enterprise for each target bid invitation project, and carrying out project recommendation. According to the application, the association relationship information, the industry and commerce information, the annual report information and the product data of the bid invitation project are used for training and learning, key customers and potential opportunities are mined, the nonlinear prediction model is constructed, then the bid invitation business opportunity is analyzed and predicted, the bid parametric probability is obtained, the business opportunity recommendation for B-type enterprises is given, and the business opportunity recommendation efficiency is improved. And comprehensive mining and quantitative analysis of business opportunities are realized.

The invention relates to the technical field of automatic control, and discloses a suction force self-adaptive adjusting method based on a suction cup base, comprising the following steps: collecting current attitude disturbance information of to-be-adsorbed objects including a lamp, glass, a steel plate, a plastic box body and a wood material plate, the attitude disturbance information comprises a pitch angle, a roll angle, an angular velocity and a vertical acceleration; estimating the offset of the gravity center of the to-be-adsorbed object relative to the center of the sucker array based on the attitude disturbance information; according to the offset, target adsorption force of the object to be adsorbed is determined, and distribution is carried out according to a set load distribution weight; the invention further discloses a suction force self-adaptive adjusting system based on the suction cup base. The system comprises a posture sensing module; an offset calculation module; an adsorption force distribution module; and an adsorption control module. According to the invention, dynamic coordination and accurate tracking control of multi-sucker adsorption force are realized by fusing attitude sensing, adsorption modeling and nonlinear predictive control.

The application relates to the technical field of intelligent control of refrigeration equipment, and discloses an intelligent energy-saving control method and system for a refrigeration display cabinet. The method comprises the following steps: collecting temperature distribution and passenger flow data in the refrigeration display cabinet through a multi-parameter sensor network, inputting the data into an ARIMA model after sliding average filtering processing, and predicting a refrigeration load fluctuation trend; a dynamic energy efficiency ratio indicator is established based on the ratio of compressor power to the predicted value of the load, and the energy-saving effect is quantified; the compressor frequency and the fan rotating speed are adjusted in combination with a nonlinear prediction control algorithm, and a cooperative control instruction is generated; the influence of the instruction on the system load is analyzed through a refrigerant flow tendency function, the defrosting cycle is optimized synchronously, an energy-saving control strategy is formed, and the strategy is executed. The application improves the predictability and cooperativeness of energy efficiency management of the refrigeration display cabinet.

The invention relates to an integrated state estimation and motion control method for an automatic driving vehicle, and the method comprises the steps: building an implicit mapping function between a vehicle-mounted sensor measurement signal and a longitudinal lateral vehicle speed, determining the input and output of a state estimator based on a long short-term memory network, and constructing a state estimation loss; establishing a nonlinear prediction model for trajectory tracking control, and depicting a trajectory tracking control optimization problem under a rolling time domain framework; the control quantity output by the model prediction controller based on the long-short-term memory network is projected to a constraint space, the control quantity meeting constraints acts on the nonlinear prediction model oriented to trajectory tracking control, a state quantity in a prediction time domain is obtained, and optimization target loss is constructed; and constructing a joint loss function to carry out integrated training, deploying on a real vehicle platform after training is finished, and carrying out state estimation and motion control on the automatic driving vehicle. Compared with the prior art, the method has the advantages that estimation precision and trajectory tracking performance are both considered, and safety and reliability are high.

The invention discloses an SP-URNet-based marine heterogeneous troposphere atmospheric waveguide propagation loss space-time prediction algorithm, which comprises the following steps: step 1, parameterization calculation of an atmospheric waveguide atmospheric correction refractive index M and waveguide propagation loss image data calculation; step 2, spatial feature extraction modeling of a three-dimensional convolution automatic encoder; a U-TCN module formed by a time convolution network TCN performs modeling on beyond visual range propagation loss time features; a fourth step of integrating time and space features of a three-dimensional convolution automatic decoder; and a fifth step of establishing an SP-URNet prediction network model. According to the algorithm disclosed by the invention, the defect that space-time prediction and nonlinear prediction cannot be carried out on offshore non-uniform troposphere atmospheric waveguide propagation loss data in the prior art is overcome.

The invention discloses a surface roughness prediction method for a selective laser melting additive manufacturing part, and belongs to the technical field of additive manufacturing. According to the method, different roughness prediction models are constructed for the first time according to the relation between the inclination direction of a printed workpiece and the scraping direction of a scraper; the prediction precision of the surface roughness of the workpiece prepared by the SLM process is improved, and the constructed model is a polynomial model. Compared with a traditional model, on one hand, the model considers the change relation of the surface roughness along with the inclination direction under the two conditions of forward scraping and reverse scraping, and the prediction precision is improved; on the other hand, compared with a traditional linear model, fitting of the nonlinear relation is enhanced through the model; compared with an artificial neural network and other black-box nonlinear prediction models, the model has an explicit interpretable expression, and can be directly applied by engineers conveniently. The method has certain universality and is suitable for different SLM printing process parameters, printing shapes and printing materials.

The invention relates to the field of data processing, and provides a data center short-term power load prediction method, system and device and a medium, and the method comprises the steps: obtaining a to-be-predicted time period, and obtaining time series data according to the to-be-predicted time period; inputting the time sequence data into a preset SARIMA and BiLSTM composite model to obtain a linear predicted value and a linear residual sequence; normalizing the linear residual sequence to obtain a data set, and generating a nonlinear predicted value and a nonlinear residual sequence according to the data set; and dynamically combining the linear predicted value and the nonlinear predicted value into a load predicted value, and outputting the load predicted value and a nonlinear residual sequence. According to the method, the SARIMA model and the BiLSTM model are combined, the accuracy of data center load prediction can be improved, and the method is suitable for complex data center load prediction tasks.

Disclosed in the present disclosure are a charge and discharge capacity correction method and device, a storage medium, and an electronic device. The method comprises: acquiring X*Y sets of test data generated, under Y types of temperature variation parameters, for each battery among X batteries to be tested; determining loss of full discharge and / or loss of full charge corresponding to each set of test data, concatenating the loss of full discharge and / or the loss of full charge as target values with the corresponding first key features to generate a training dataset, and fitting model parameters on the basis of on the training dataset to obtain a nonlinear prediction model; predicting, on the basis of second key features of a target battery and the nonlinear prediction model, target loss of full discharge and / or target loss of full charge corresponding to the target battery under a current state of charge and a current temperature variation condition; and using the target loss of full discharge to correct the initial discharge capacity of the target battery upon a temperature variation and / or using the target loss of full charge to correct the initial charge capacity of the target battery upon the temperature variation.