30 results about "Multi objective model" patented technology

The invention relates to a multi-distribution-center open type vehicle path intelligent optimization method and system, and belongs to the technical field of logistics distribution optimization and intelligent transportation, and the method comprises the steps: firstly obtaining the input data of a multi-distribution-center vehicle path optimization problem, selecting a multi-distribution-center processing strategy according to the problem scale and constraint conditions, and carrying out the optimization of the multi-distribution-center vehicle path; a vehicle path optimization model is constructed, the vehicle path optimization model comprises a single-target model and a multi-target model, a multi-algorithm collaborative optimization framework is adopted for solving, and the multi-algorithm collaborative optimization framework comprises an ant colony algorithm, a variable neighborhood search optimization ant colony algorithm and a non-dominated sorting genetic algorithm; and outputting an optimal vehicle path scheme, wherein the optimal vehicle path scheme comprises a distribution route, a distribution sequence and a corresponding objective function value of each vehicle. According to the method, strategy adaptive selection and algorithm collaborative optimization are carried out, global exploration, local optimization and multi-target equalization are carried out by combining the advantages of the ant colony algorithm, the variable neighborhood search algorithm and the non-dominated sorting genetic algorithm, and the method is good in reproducibility, high in scene adaptability and high in decision support capability.

The invention belongs to the technical field of intelligent manufacturing and industrial scheduling, and provides a high-altitude platform multi-test task production scheduling method based on a clustering algorithm and multi-objective optimization, and the method comprises the steps: automatically calculating the exclusive resource demands of all working condition points in a plurality of aero-engine test tasks based on a multi-parameter coupling model; for each task, dividing a plurality of work packages by adopting a clustering algorithm based on the multi-dimensional features containing exclusive resource requirements in the task; a multi-objective model of multiple optimization objectives is constructed, all the work packages are jointly sorted globally, and the optimization objectives comprise the equipment utilization rate; and finally, under the condition that constraint of resource capacity, mutual exclusion of test cabins and task continuity is satisfied, allocating an available tester and a continuous time window to each work package, and generating an initial production scheduling plan. According to the method, the production scheduling efficiency and the resource utilization rate are effectively improved, the plan robustness is enhanced, and the method is suitable for high-complexity aero-engine test scheduling scenes.

The application provides a multi-objective robust optimization method, system, storage medium and electronic equipment for production task planning of a multi-agent collaborative platform, and relates to the technical field of production task planning of a multi-agent collaborative platform. First, according to the production task planning resources of the multi-agent collaborative platform and a single-batch overseas order, a production task planning model with a manufacturing enterprise agent as the core is constructed under the premise of determining the sea transportation time. Then, an infinity norm ball uncertain set is designed for the sea transportation time of a large ship, a robust quadratic multi-objective model for cross-regional multi-agent production task planning is constructed, and the total delivery time deviation and total delivery cost multi-objective of the single-batch overseas order are optimized. The model considers the sea transportation plan prepared in advance by a shipping company agent and the long and uncertain sea transportation time. In addition, the model is converted into an equivalent model, a two-stage hybrid heuristic algorithm is designed for solving, and a reasonable and feasible production task planning suggestion is given for the single-batch overseas order.

The application provides a robot dance automatic generation method and system based on music feature analysis, and relates to the technical field of robot control. First, a music feature spectrum covering rhythm, energy and other dimensions is constructed to convert abstract music into structured information understandable by machines, and then a dance semantic label sequence bound to a time axis is generated to provide accurate basis for action selection. By combining with a forward-looking window to predict future music features, the current and future candidate actions are filtered through a multi-objective model to realize the dual matching of action and music micro-rhythm and macro-structure. The finally generated control instruction sequence directly drives the physical robot, which breaks the dependence on video materials, realizes the automatic generation of dance with creativity and artistic expression, and improves the generation efficiency and adaptive flexibility.

The invention discloses a permanent magnet synchronous motor multi-target model prediction control method based on parallel optimization, which relates to the field of motor control, and sequentially comprises the following steps: establishing a permanent magnet synchronous motor mathematical model, performing Euler discretization-based model prediction torque control, and selecting an optimal vector based on a comprehensive optimization mechanism. Compared with the prior art, the optimal vector is selected on the basis of a comprehensive optimization mechanism, so that the control system adaptively switches the priority of multiple targets under high-speed and low-speed working conditions so as to realize multi-dimensional variable global optimization and rapid dynamic coordination, and the control is enabled to meet the performance requirements of preliminary constraint conditions, so that the control efficiency is improved. Ripples of torque and flux linkage are reduced, unstable operation of the motor and extra noise interference are overcome, and the control precision and steady-state performance of a control system are improved.

The application discloses a kind of adaptive compensation method and related device for three-phase current imbalance and harmonic, belong to power system technical field;The method is based on the instantaneous reactive power theory and the quick separation and instruction generation of fundamental wave positive sequence component and unbalance compensation component of sliding discrete fourier transform;Multi-objective model predictive current control with embedded repeated learning correction mechanism to achieve high-precision tracking of compensation current instruction and system circulation suppression;Multi-objective weight factor online dynamic adjustment mechanism based on fuzzy reasoning, according to the adaptive balance between the control emphasis of tracking accuracy, circulation suppression and switching loss according to the real-time operating state of the system;And, adaptive closed-loop management architecture based on the above module cooperation, drive active power electronic converter to generate compensation current, realize the comprehensive management of three-phase imbalance and harmonic and global optimization of system performance.

The embodiments of the present disclosure disclose a method and device for training and predicting a response duration prediction model, a medium and a product. The method comprises: obtaining a set of sample data from a sample set as a training set, wherein the sample data comprises feature information of a sample service request and a real response duration of the sample service request; training a plurality of initial multi-objective models based on the sample data in the training set to obtain a plurality of multi-objective models, wherein the learning objectives of the multi-objective models comprise a probability that a service request response duration is within a predetermined range and a predicted response duration of a service request whose response duration is within the predetermined range, and each multi-objective model corresponds to a different predetermined range. The technical solution can more accurately predict the response duration of a service request.

The application discloses an intelligent scheduling multi-objective optimization method based on a pulse propagation algorithm, relates to the field of manufacturing scheduling, and comprises the following steps: a scheduling data preparation stage, which is used for making a pre-decision for the schedulable resources in a pool and generating data of an input model; a multi-objective model establishment stage, which describes scheduling rules and optimization targets in a mathematical modeling mode; and a pulse propagation algorithm stage, which solves the above multi-objective model by designing an epsilon-constraint and a pulse propagation algorithm. The application greatly reduces the work burden of a planner, and the batch decision and specific scheduling details can be automatically completed by an embedded advanced model and intelligent algorithm. The intelligent decision mechanism not only improves work efficiency, but also ensures the accuracy and rationality of the scheduling plan.

This invention belongs to the field of power grid investment optimization technology, and relates to a regional power grid investment optimization method based on a multi-objective programming model. It includes the following steps: Step S1: Considering the decoupling requirements between regional power grid investment and electricity generation, a multi-dimensional parameter system covering investment, electricity generation, safety, and green / low-carbon parameters is constructed; Step S2: Based on the multi-dimensional parameter system, a multi-objective programming model is constructed to maximize the net present value of investment, maximize the power grid safety margin, and maximize the investment-electricity decoupling degree; Step S3: An improved multi-objective particle swarm optimization algorithm is used to solve the model, and the Pareto optimal solution set is output to obtain the optimal investment scheme. This invention quantifies the decoupling relationship between investment and electricity generation through a multi-dimensional parameter system, and optimizes the balance between economic efficiency, power supply safety, and resource allocation efficiency using a multi-objective model, solving the problems of excessive coupling between investment and electricity generation and insufficient functional value mining in existing planning.

The application provides a transformer area energy storage system operation regulation method and device, and belongs to the technical field of power system regulation. The method comprises the following steps: collecting transformer area historical data and constructing a historical database; training a prediction model based on the historical database, inputting real-time data of the transformer area into the prediction model for ultra-short-term prediction, and outputting future power output and load demand prediction values; taking the power output and load demand prediction values as the basis, taking the elimination of line overload, three-phase imbalance and voltage out-of-limit as the optimization target, considering the service life of the energy storage battery and the electricity economy, constructing a multi-objective model and solving the model to obtain an instruction sequence; issuing the instruction sequence to the transformer area energy storage system for execution; collecting real-time data; calculating the execution deviation according to the transformer area actual data, and adaptively updating and correcting the parameters of the prediction model and the multi-objective model. The application solves the transformer area power quality problem, prolongs the service life of the energy storage battery, and reduces the operation cost through intelligent prediction and optimization regulation.

The invention belongs to the technical field of intelligent control of a light storage system, and particularly relates to a light storage integrated intelligent operation method and system based on deep learning and multi-target model prediction control. And based on the photovoltaic output prediction value and the user load prediction value, a multi-target model prediction controller (M-MPC) is utilized to solve a multi-target optimization problem including economic cost calculation and battery attenuation cost calculation, and an optimal charging and discharging power sequence of the energy storage system is obtained. According to the technical scheme, through the synergistic effect of deep learning model prediction and multi-objective optimization control, the full life cycle operation cost of the energy storage system is reduced, the photovoltaic self-generation and self-use rate is improved, the impact on a power grid is reduced, a full-automatic closed-loop control system is realized, and the autonomy and intelligence of the optical storage system are improved.

This invention provides a method, system, and storage medium for self-optimization of process parameters in a stenter. The method includes: constructing a multi-objective model with the goal of minimizing fabric weight deviation, width deviation, and unit energy consumption, where the decision variables are temperature, machine speed, overfeed, and fan frequency; establishing a surrogate model to represent the mapping relationship between variables and objectives, and normalizing the parameter space; initializing the current solution and the Pareto front archive; generating M candidate solutions in the neighborhood of the current solution, evaluating and updating the front using the surrogate model; if the hypervolume increment of the front is lower than the threshold for N consecutive times, and the candidate solutions are too clustered, then triggering a restart; if the number of solutions in the archive is greater than or equal to 2, then selecting two parent solutions using the inverse roulette wheel based on the distribution density, generating a first type of restart point through recombination and mutation, and using a small radius; otherwise, generating a second type of restart point through global random sampling, using a large radius; setting the current solution as the restart point; looping until the termination condition is met, and outputting the Pareto front as the set of optimization parameters.

The application discloses a kind of permanent magnet synchronous motor multi-objective model prediction control methods based on parallel optimization, it relates to motor control field, successively include the following steps: establishing permanent magnet synchronous motor mathematical model, model prediction torque control based on Euler discretization and optimal vector based on integrated optimization mechanism selection. Compared with prior art, the optimal vector based on integrated optimization mechanism selection introduced in the application makes the control system self-adaptive switching priority of multi-objective under high-speed and low-speed working conditions, to realize global optimization and fast dynamic coordination of multi-dimensional variable, and makes the performance requirement under the performance requirement of meeting preliminary constraint condition, reduces the ripple of torque and flux linkage, overcomes motor operation instability and additional noise interference, and improves the control precision and steady-state performance of control system.

The invention discloses a resource recall method, a multi-target model training method and device, electronic equipment and a computer readable storage medium. The resource recall method comprises the steps that a first user vector corresponding to a first target and a second user vector corresponding to a second target in a multi-target model are determined, the multi-target model is a recall model of a multi-tower structure, and the first target and the second target are different recall targets of the multi-target model; for each service resource in a service resource library, determining a first resource vector corresponding to the first target and a second resource vector corresponding to the second target in the multi-target model; multiplication fusion is carried out based on the first resource vector, the first user vector, the second resource vector and the second user vector to obtain a fusion score, and the fusion score is a non-negative value; and recalling the service resources according to the fusion score of each service resource. According to the scheme, multiplication fusion between any two recall targets can be achieved, and the recall effect is helped to be improved.

The application discloses a multi-target model prioritization framework and a marker combination screening method, introduces a NSGA-III multi-criteria optimization algorithm as a core innovation, and establishes a set of marker combination screening strategies with biological significance and classification performance. For a single biological feature, a basic model is constructed by using a full sRNA expression profile, and a classification performance is taken as a core index, and an optimal model is screened by using the NSGA-III. Multiple biological features and multiple groups of models are integrated and crossed to form multiple groups of evaluation models, and a processing model balanced and optimal for multiple biological features is screened by using the NSGA-III. For each biological problem, model building, redundant feature elimination and multi-dimensional screening operations are performed, and the significance of a marker in corresponding biological classification is detected, and only sRNAs with statistically significant differences are reserved as effective markers of the biological problem. Finally, the markers screened for each biological problem are combined, and a core marker combination capable of simultaneously solving all preset biological problems is formed.

The application discloses a kind of multi-objective control methods of three-level inverter based on model prediction using optimized pulse width modulation, current error, switching number, midpoint potential offset and the difference between selected switch state and optimized pulse width modulation switch state are weighted to obtain new optimization function, and the optimal vector considering multiple optimization targets is selected by rolling optimization, so as to adjust the switch state of three-level inverter in real time.The method of the patent combines the optimized pulse width modulation of three-level inverter with multi-objective model prediction algorithm, which can make the inverter output have good low-order harmonic characteristics, current fast tracking and midpoint potential balancing ability under dynamic at low switching frequency.

The invention discloses an electrical cabinet PLC control system, and relates to the technical field of control systems. The system comprises a multi-dimensional data sensing module, a three-dimensional dynamic thermal network digital twinning module, a model parameter online learning module, a multi-target model prediction control module and an execution driving module which are connected in sequence. According to the system, a three-dimensional dynamic thermal network digital twinborn model in an electrical cabinet is constructed to realize full-space high-fidelity simulation and prediction of a temperature field; model parameters are dynamically corrected through an online learning mechanism, and long-term precision is guaranteed; and a model prediction control framework is adopted to solve a multi-objective optimization problem which comprehensively considers temperature safety, energy consumption and control smoothness, and an optimal fan control instruction is generated. The problems of local overheating blind area, single control target, model mismatch, response lag and the like in the prior art are solved, refined, adaptive and prospective intelligent management of the internal thermal environment of the electrical cabinet is realized, and the reliability, the energy efficiency and the economical efficiency of the system are improved.

The present application relates to the technical field of comprehensive energy system optimization operation, and discloses a cascade water-light-storage multi-objective medium-term scheduling method considering water inflow and photovoltaic uncertainty. A cascade water-light-storage medium-term complementary power generation model is established by taking the maximum system total power generation and the minimum system residual load variance as the target and combining various types of unit output constraints, thereby guaranteeing the economy, safety and stability of the system. The vibration area constraint of the water turbine unit and the power transmission constraint of the direct current tie line are considered, thereby guaranteeing the safe operation of the cascade water turbine unit and fully playing the power optimization role of the direct current tie line. In view of the seasonal change of natural water inflow and the daily scale fluctuation of photovoltaic output, the information gap decision theory is used to construct a scheduling model considering water and light uncertainty, so that the scheduling method can better avoid the risk brought by water and light uncertainty. For the multi-objective model constructed, the epsilon constraint method is used for solving, and the compromise solution is selected based on the fuzzy decision method, so that the comprehensive satisfaction is maximized.

The application discloses a wireless power transmission system multi-parameter collaborative optimization method based on a VPSR-PSO algorithm, and belongs to the technical field of wireless power transmission, and comprises the following steps: step 1: according to the primary side input voltage, the primary side input current, the primary side output current, the primary side compensation inductance, the primary side compensation inductance internal resistance, the primary side coil self-induction internal resistance and the primary side coil self-induction of the system, the secondary side output current, the secondary side coil self-induction, the primary side coil series capacitor, the secondary side coil self-induction internal resistance and the secondary side coil series capacitor, and the mutual inductance between the primary side coil and the secondary side coil; step 2: constructing a target model according to the primary side compensation inductance, the mutual inductance between the primary side coil and the secondary side coil and the equivalent load resistance; and establishing the constraint condition of the target model; the application constructs a multi-objective model for simultaneously optimizing transmission efficiency and output power, and realizes efficient search and balanced regulation and control.

The application provides a kind of urban environment performance prediction method and system based on multi-modal fusion and attention enhancement, wherein the method comprises collecting image data and numerical data, generating a variety of urban environment performance distribution truth value map;Preprocess multi-modal data to get image map and numerical feature vector, pair the image map and numerical feature vector with the truth value map to form a multi-modal data set.Construct a multi-objective model based on attention-enhanced conditional generative adversarial network, the generator includes a double-path encoder, which can extract spatial features based on image maps and physical features based on numerical feature vectors;The image encoding path adopts the U-Net downsampling structure containing the convolution block attention module, and the numerical encoding path adopts the multilayer perceptron;The multi-head output layer outputs the predicted multi-urban environment performance distribution map.After training the model, input the target area data, and output three types of prediction distribution map.The application improves the urban environment performance prediction effect.

The application belongs to the technical field of intelligent manufacturing and industrial scheduling, and provides a high-altitude table multi-test task scheduling method based on a clustering algorithm and multi-objective optimization, which comprises the following steps: automatically calculating the exclusive resource demand of each working condition point in a plurality of aero-engine test tasks based on a multi-parameter coupling model; for each task, a plurality of work packages are divided by using a clustering algorithm based on multi-dimensional features containing exclusive resource demand; a multi-objective model of multi-optimization objectives is constructed, and all work packages are jointly sorted globally, wherein the optimization objectives include equipment utilization; finally, under the constraints of resource capacity, test cabin mutual exclusion and task continuity, available test devices and continuous time windows are allocated to each work package to generate an initial scheduling plan. The application effectively improves scheduling efficiency and resource utilization, enhances plan robustness, and is suitable for high-complexity aero-engine test scheduling scenarios.

The application provides a micro-grid multi-target scheduling optimization control method, and the method comprises the following steps: data acquisition and time domain division: collecting micro-grid core operation data according to a set period; combining data error distribution, dividing a future scheduling period into high and low uncertainty time domains, which correspond to time periods with predicted error exceeding a first threshold value and a second threshold value respectively; hierarchical optimization framework construction: constructing a day-ahead plan layer, an intra-day rolling correction layer and a real-time adjustment layer three-layer framework, adopting time scales in descending order, and realizing initial scheduling, dynamic correction and fast response equipment millisecond to second level power compensation respectively; multi-target weight self-adaptive adjustment: constructing a multi-target model of cost, carbon emission and power fluctuation minimization in the intra-day correction layer, adjusting the weight according to the time domain type, increasing the power fluctuation weight to suppress the impact through the high uncertainty time domain, and increasing the cost and carbon emission weight through the low uncertainty time domain.

The application discloses a dry / wet state conversion automatic control method and system for improving deep peak regulation capacity of a thermal power unit. Firstly, a supercritical combined heat and power unit is taken as a research object and difficulties of dry / wet state conversion of the supercritical combined heat and power unit under deep peak regulation demand are analyzed; then, a dry / wet state conversion automatic control strategy and system are designed for the supercritical combined heat and power unit in combination with a multi-objective model predictive control algorithm. Finally, the feasibility of the dry / wet state conversion automatic control method is verified by relying on a simulation platform. In the analysis of the research object, the supercritical combined heat and power unit in the dry state and the wet state are both simplified into different four-input four-output systems, so that the dynamic characteristics of the supercritical combined heat and power unit are more accurately represented. In addition, the multi-objective model predictive control algorithm is constructed by comprehensively considering the power generation cost, carbon transaction cost, smoothness of the manipulated variable and load tracking error of the unit, so that the unit realizes the improvement of the deep peak regulation capacity on the basis of low carbon, economy and stable operation.

The invention discloses a panoramic intelligent rehabilitation management system for burn patients, and relates to the technical field of medical health informatization. Comprising a multi-target coupling modeling module, a multi-source state sensing module, a conflict identification calculation module, an intervention priority regulation and control module, a feedback calibration analysis module and a dynamic closed-loop control module, a rehabilitation stage multi-target model containing a coupling relationship among a skin healing target, a joint flexibility recovery target and a nerve regeneration target is constructed, a sensitive intervention window is identified according to a physiological change rule of each target in a rehabilitation period, and a target conflict mapping matrix with a time sequence attribute is generated. Through multi-target coupling modeling and a dynamic conflict regulation and control mechanism, intelligent cooperative control over multi-target intervention in the whole burn rehabilitation process is achieved, intervention safety and individual adaptability are improved, closed-loop optimization capacity is achieved, rehabilitation efficiency is remarkably improved, medical risks are reduced, and wide clinical application prospects are achieved.

This invention relates to the field of ultra-large area flooring construction technology, and discloses a method and system for precise jointing treatment of ultra-large area floors based on a genetic algorithm. The method includes: acquiring multi-source measured data reflecting the construction conditions and state of the flooring; using the multi-source measured data as input, constructing a multi-objective model with jointing parameters as variables and comprehensive performance including crack resistance, smoothness, construction feasibility, and durability as optimization objectives; solving the model using a genetic algorithm to output an optimized jointing scheme containing joint coordinate information; locating and cutting the joints according to the joint coordinate information in the optimized jointing scheme; acquiring new measured data during construction and comparing it with the data or model prediction values ​​from step S1; and triggering adjustments to the optimized jointing scheme or the multi-objective model based on the comparison results. The beneficial effect of this invention is to improve the overall performance and service life of the flooring.

The invention relates to the technical field of power grid dispatching, in particular to a power consumption anomaly detection method based on time-frequency behavior mismatch analysis, which comprises the following steps of: 1, extracting a multi-modal feature and discovering a dynamic frequency band; step 2, constructing a hierarchical graph convolution variation auto-encoder model; 3, introducing dynamic hierarchy center constraint and map guidance; step 4, multi-objective model training and optimization; step 5, performing hierarchical classification and time-frequency consistency anomaly detection; the method aims at solving the technical problem that in the prior art, dynamic evolution of industry electricity utilization characteristics cannot be captured, fine-grained user electricity utilization behavior modes can be deeply mined through linkage analysis of multi-dimensional data, and powerful technical support is provided for more accurate and intelligent user behavior analysis.

The present application belongs to the technical field of virtual power plant power market bidding decision, and particularly relates to a virtual power plant robust-opportunity bidding method and system based on IGDT. The method comprises the following steps: constructing a multi-objective model based on power plant data, integrating electricity price, maximum power generation capacity, cost, and carbon emission coefficient time series sub-models, and setting price uncertainty parameters; taking profit maximization and carbon emission minimization as objectives, and generating a Pareto frontier solution set by using an epsilon constraint method; and calculating strategy membership weight through fuzzy multi-attribute decision, and screening an optimal scheme. The present application takes into account robust guarantee and opportunity income under electricity price fluctuation, realizes economic and environmental benefit synergy, improves the scientific nature, flexibility and system overall operation efficiency of virtual power plant bidding decision, and is suitable for virtual power plant operation optimization in the field of power system automation.

The application provides a multi-target model training method and device, an electronic device and a storage medium. The method comprises: obtaining sample features, wherein the sample features comprise sample user features, sample material features and sample cross features; inputting the sample features into a multi-target model to obtain a plurality of predicted scores of the sample features; determining a plurality of loss values of the sample features based on the plurality of predicted scores of the sample features; determining the correlation between a plurality of recommended targets of the multi-target model according to the plurality of loss values; adjusting the weights corresponding to the plurality of recommended targets and / or modifying the structure of the multi-target model according to the correlation; and iteratively training the multi-target model using the sample features based on the weights corresponding to the plurality of recommended targets to obtain a trained multi-target model. Through the application, the effect of multi-task learning can be enhanced.

This invention discloses a method for constructing a photovoltaic-electric vehicle coupled safety domain in a distribution network and related products, belonging to the field of distribution network coordination and optimization technology. This method establishes a multi-objective optimization model of carrying capacity with both distributed photovoltaic carrying capacity and electric vehicle carrying capacity as dual objectives, incorporating second-order cone relaxation power flow constraints of the distribution network. Based on the Epsilon-constraint method, the multi-objective model is transformed into multiple single-objective sub-problems for solution, obtaining the Pareto optimal solution set. Mapped to a two-dimensional plane with the dual carrying capacity as coordinate axes, a continuous photovoltaic-electric vehicle coupled safety domain is constructed based on its boundary points. This invention handles nonlinear power flow constraints through second-order cone relaxation and overcomes the shortcomings of traditional weighted methods in handling non-convex Pareto fronts using the Epsilon-constraint method, accurately constructing a continuous coupled safety domain, thereby effectively improving the distribution network's comprehensive capacity to accommodate distributed energy resources.

The invention discloses an extreme environment-oriented space adaptive control method, which comprises the following steps: 1, multi-source heterogeneous data synchronous acquisition and feature extraction, specifically, deploying and integrating multiple types of sensing units, forming an asynchronous sensing network and acquiring an original data stream in real time: 2, data fusion and unified state vector construction, specifically, configuring an edge computing unit, and constructing a unified state vector; the method comprises the following steps: receiving an original data stream, performing space-time alignment, abnormal value detection and cleaning, and generating unified state description for decision making; 3, based on digital twinning multi-dimensional dynamic prediction, inputting the state vector into a plurality of prediction models running in parallel, and deducing core indexes in a future short period; 4, multi-target model predictive control MPC optimization solution is carried out; 5, cooperative distribution and safety verification of control instructions are carried out; and 6, performing closed-loop execution and multi-granularity feedback learning. According to the invention, upgrading from environment regulation and control to human factor guarantee is realized, dynamic balance under multi-target conflicts is satisfied, and predictability and self-evolution ability of the system are endowed.