246 results about "Genetic algorithm" patented technology

The invention relates to the technical field of atmospheric dust pollution prevention and environmental protection, and discloses a multi-objective optimization layout method for dust monitoring points of a bulk cargo port, which comprises the following steps: processing historical meteorological data and port geographic information, and calculating the comprehensive evaluation concentration of each candidate grid point in combination with a pollutant diffusion model; constructing a multi-target nonlinear mixed integer programming model taking maximization of environment sensitive point coverage and minimization of concentration interpolation deviation as target functions, wherein the model comprehensively considers multiple reality constraints; solving the model by adopting an improved genetic algorithm to obtain an optimal solution set capable of forming tradeoff among different targets; and carrying out quantitative evaluation on the solution set through preset monitoring area coverage rate and monitoring accuracy indexes, and determining an optimal monitoring point position layout scheme. According to the invention, a scientific and quantitative optimized layout scheme can be provided for bulk cargo port dust monitoring, and the reliability and spatial representativeness of a monitoring network are improved.

The invention relates to a tunnel construction progress model generation method based on artificial intelligence. The method comprises the following steps: acquiring multi-source heterogeneous data such as tunnel field equipment operation and geological change, and performing multi-modal fusion to form a unified data set; based on this, a particle filter algorithm is used to correct equipment positioning deviation, and a real-time position optimization result is generated. Comparing the time and space with the progress plan, and identifying and quantifying deviation points through a critical path method and a deviation analysis algorithm to form deviation data. And constructing a construction progress model by combining construction basic parameters and adopting a genetic algorithm, generating an adjustment scheme by taking a construction period and resources as targets, and obtaining an optimal scheme through compliance screening and fitness calculation iterative optimization. By the adoption of the method, efficient integration of heterogeneous data can be achieved, the equipment positioning precision is improved to the centimeter level, multi-dimensional quantification of progress deviation is achieved, progress deviation recognition and resource allocation efficiency is improved, and a technical scheme is provided for tunnel intelligent construction.

The invention discloses a cross-regional computing power resource collaborative allocation method based on computing power centers, and relates to the technical field of computing power resource scheduling and optimizing.The cross-regional computing power resource collaborative allocation method comprises the steps that real-time load data, historical task execution data and network delay data of all computing power centers are collected, and a regional load feature database is constructed; predicting the load demand of each computing power center in a future time window by using a long short-term memory network model to generate a load prediction value; calculating a resource gap coefficient and a resource margin coefficient of each region according to the load prediction value and the current resource capacity, identifying a resource insufficient region and a resource surplus region, and generating a resource collaborative matching matrix between the regions; and optimizing and solving the cross-regional task allocation scheme by adopting an improved genetic algorithm to generate an optimal resource allocation strategy, and allocating the to-be-processed task to a corresponding computing power center according to the optimal resource allocation strategy. According to the method, the cooperative utilization rate and the distribution efficiency of the computing power resources in the cross-regional scene are effectively improved.

The invention relates to the technical field of water conservancy projects, and discloses a water conservancy project water quality detection method and system based on artificial intelligence, and the method comprises the steps: collecting first multi-source data for a water conservancy project, carrying out the alignment of water quality parameter data, remote sensing image data and meteorological and hydrological data in the first multi-source data based on a timestamp, and obtaining second multi-source data; performing data preprocessing and feature extraction processing on the second multi-source data to obtain target feature data; designing a multi-task space-time diagram convolutional network, performing parameter optimization by adopting a genetic algorithm, and constructing a water quality detection model; inputting the target characteristic data into a water quality detection model, and outputting a water quality detection result through the water quality detection model; when the water quality detection result determines that the water quality is abnormal, generating a pollution diffusion simulation map based on a space-time diagram structure and a water quality diffusion rule, and providing emergency decision suggestions according to a water conservancy project scheduling scheme; the accuracy and functional integrity of water quality detection are improved.

The invention discloses an inference task collaborative scheduling system and method oriented to multiple terminals of a swan gap. The inference task collaborative scheduling system comprises a communication module Broker, a system monitoring module SystemProfilter, a scheduling module Scheduler and an inference task execution module Worker. According to the method, a structured resource state vector is constructed based on an NDK native interface so as to comprehensively represent the real-time availability of equipment; a lightweight MQTT protocol is adopted to support low-overhead and high-robustness cross-terminal state synchronization and task distribution; a comprehensive load scoring mechanism fusing task priorities and dynamic weights is designed, a multi-objective optimization problem based on a non-dominated sorting genetic algorithm (NSGA-II) is introduced, task delay is minimized in a combined mode, terminal loads are balanced, and energy consumption is controlled; meanwhile, the execution time delay is efficiently estimated in combination with a proxy model based on linear regression, and the scheduling overhead caused by real reasoning and calling is avoided; the whole architecture is deeply adaptive to a swan-mong system, and is compatible with an Android platform through modular packaging and unified communication interface design, and efficient, self-adaptive and cross-platform collaborative scheduling oriented to a swan-mong multi-terminal reasoning task is realized for the first time.

The invention provides a titanium tetrachloride boiling chlorination process optimization method based on a causal model and electronic equipment, and the method comprises the steps: constructing a generation mechanism between structural equation model expression variables based on the causal relationship between boiling chlorination key process parameters and result variables; the effect of external intervention on the TiCl4 yield and unit cost is simulated through causal inference, and a multi-target optimization model with the minimization of the unit product manufacturing cost and the maximization of the TiCl4 yield as targets is constructed in combination with the structural model and Monte Carlo sampling estimation expectation; and iteratively solving the optimization model by adopting a causal-based non-dominated sorting genetic algorithm, and obtaining a Pareto optimal solution set meeting variable constraint conditions through operations such as causal variable classification, dynamic penalty weighting, non-dominated sorting and sensitive driving disturbance. According to the method, a causal modeling and optimization integrated framework suitable for the boiling chlorination process is constructed, personalized process strategy generation and production operation decision making are supported, and the raw material utilization rate and the process operation economy are improved.

The invention provides an electronic current transformer operation data calculation system, and relates to the technical field of data processing, and the system comprises a data processing module which is used for carrying out the sliding time window scanning of an equipment dependence adjacency matrix, calculating the local reachable density under a dynamic neighbor topological distance through a local outlier factor algorithm, if it is detected that the harmonic total distortion rate gradient enters a statistical hypothesis test rejection domain or the winding temperature rise rate exceeds a material thermal aging critical threshold, extracting a multi-dimensional abnormal feature vector set; the risk quantitative index generation module is used for generating a risk quantitative index group from the multi-dimensional abnormal feature vector set through a pre-trained fault propagation probability model; and the processing instruction set generation module is used for establishing a multi-objective optimization function based on the risk quantification index group, performing non-dominated sorting evolution on a processing instruction chromosome by adopting an NSGA-II genetic algorithm, screening a dynamic optimization instruction sequence matched with a real-time load fluctuation coefficient through a Pareto frontier solution set, and generating a structured processing instruction set. The operation reliability of the power system is improved.

The invention relates to the technical field of intelligent power grids, in particular to an urban power distribution network whole-process scene chain closed-loop monitoring method and system fusing digital twinning. The method comprises the following steps of: fusing a weighted evidence theory and a dynamic time bending algorithm to acquire multi-source data, and constructing a physical mechanism-data driven hybrid enhanced digital twinborn model; based on the model, abnormity is researched and judged through an improved isolated forest algorithm, grading alarms are generated, simulation deduction is conducted through Monte Carlo-Latin hypercube sampling, an optimal strategy is screened through a non-dominated sorting genetic algorithm III with uncertainty, and instructions are executed after graph neural network topology verification. Feedback is formed by the collection result, and the strategy is optimized through meta-learning and Bayesian optimization calibration model. The system comprises six cooperation units, an intelligent algorithm and a digital twinning technology are integrated, the power distribution network abnormity identification precision, decision scientificity and adaptive capacity are improved, and safe and efficient operation is guaranteed.

The invention discloses a generative adversarial network architecture search method and system and an image generation method, and belongs to the technical field of network architecture search. The searching method comprises the following steps: performing single-path sampling on a pre-constructed generator super network according to a parameter quantity constraint range to obtain an effective subnetwork; training the generator super-net by adopting a complexity adaptive learning rate optimization strategy to obtain a pre-trained generator super-net; adversarial training is carried out on the generator hypernet and the discriminator to obtain a pre-trained discriminator; generating a generator super-network candidate architecture through a genetic algorithm in the early stage of the evolution stage and through a covariance matrix self-adaptive evolution strategy in the later stage of the evolution stage; and performing multi-target non-dominated sorting on the generator super-network candidate architecture, updating an effective sub-network and keeping a Pareto optimal solution to obtain a searched optimal generator architecture and further obtain a searched optimal generative adversarial network architecture. The method not only ensures the search quality, but also improves the calculation efficiency.

The invention discloses a method for evaluating the coordinated mining degree of coal and allogeneic symbiotic bauxite based on production progress planning, which comprises the following steps of: constructing a space coordinate system, and dividing a coal seam and allogeneic symbiotic bauxite into three-dimensional ore blocks; based on multi-objective 0-1 integer programming, establishing a coal and allogeneic symbiotic bauxite coordinated mining mathematical model, and determining an optimization objective and constraint conditions; a genetic algorithm is adopted to intelligently solve the model, and an approximate Pareto optimal solution set is obtained, so that an optimal production progress scheme in a specific period is formed; and based on the optimal production progress scheme, constructing a coordinated mining degree evaluation index system, and performing quantitative evaluation on the coordination degree of the actual mining scheme. According to the method, through production progress planning and intelligent optimization, space-time conflicts in the mining process of the coal mine and the allosymbiotic bauxite can be effectively avoided, comprehensive balance of economic benefits, safe production and environmental protection is achieved, and a scientific basis is provided for optimization and sustainable development of a mine production scheme.

The application discloses a high-pressure diaphragm pump one-way valve structure multi-objective optimization method based on digital twinning, and belongs to the technical field of pump valve optimization design; the application collects geometric size parameters and material properties of a high-pressure diaphragm pump one-way valve, and establishes a simulation model; an Isight and ANSYS joint simulation method is used to generate sample points and calculate response values; an agent model is constructed according to response values of each group of sample points, calculation efficiency is improved, and a digital twinning model is constructed; a one-way valve structure multi-objective optimization model is established by taking the maximum equivalent stress of a valve core and the minimum maximum flow velocity of a valve gap flow field as objective functions, a genetic algorithm is used for solving, the best structure parameter combination of the one-way valve impact resistance performance is obtained, and finally, result verification is carried out; the application can realize high-precision simulation of a one-way valve operating state and solving of optimal structure parameters of impact resistance performance, thereby guiding one-way valve structure design, reducing product research and development time cost, and improving service life.

The invention belongs to the technical field of crossing of high polymer materials and artificial intelligence, and discloses a method for optimizing the proportion of a nano-composite flame-retardant master batch in engineering plastic based on machine learning. The method is used for solving the problems that a traditional experience trial and error method is low in efficiency in multi-target performance collaborative optimization, high-dimensional nonlinear parameter space search is difficult, and microscopic coupling effect modeling is missing. According to the method, a multi-dimensional input feature set containing material composition and process parameters is constructed, six key performance indexes are combined to form training data, a mixed model formed by cascading a multi-layer perceptron and Gaussian process regression is trained, an improved non-dominated sorting genetic algorithm (NSGA-II) is adopted for multi-target global optimization, and an optimal ratio meeting preset constraints is obtained. The method is an industrial internet technology system service, and solves the technical problem that multi-target performance is difficult to collaboratively optimize due to the fact that a traditional experience trial-and-error method cannot perform modeling and searching on a high-dimensional nonlinear parameter space of a nano-composite flame-retardant system.

The invention provides a traffic data base construction and safety management method and system for vehicle-road cooperation. The method comprises the steps of firstly collecting traffic multi-source data to construct a traffic data base, then predicting an effective sensing distance of a vehicle based on a CNN model and determining a dynamic blind area, then fusing roadside global data and vehicle sensing data in a cross-view manner, supplementing a blind area target to generate enhanced sensing data, and finally, carrying out dynamic blind area detection. And then a blind area target collision risk is evaluated in combination with relative motion parameters and road semantics, a potential conflict area is identified through an LSTM algorithm, and finally an optimal passing instruction considering safety and efficiency is generated by adopting a multi-target genetic algorithm. Closed-loop management of the vehicle-road cooperation system from data input to safe output and efficiency optimization is achieved, the problems that multi-source data has no unified carrier, a sensing blind area is uncontrollable, conflicts are difficult to recognize and the like are solved, and the system safety is improved.

One embodiment of the invention discloses a method and device for optimizing network anti-virus indexes. The method comprises following steps: obtaining anti-virus indexes of terminals in a network, wherein the anti-virus index of each terminal in the network comprises at least one kind of information as follows: virus infection and anti-virus capability information; optimizing the anti-virus indexes of terminals in a network by means of the genetic algorithm to obtain the optimized anti-virus indexes of terminals in the network; obtaining the optimized network anti-virus indexes based on the optimized anti-virus indexes of terminals in the network. One embodiment of the invention also discloses a device for optimizing network anti-virus indexes.

The invention relates to the technical field of bridge structure engineering, in particular to a new and old bridge joint vibration disturbance control method, which comprises the following steps: S1, arranging a sensor at a new and old bridge joint, and collecting vibration data of the part; according to the method, a multi-source information identification model is constructed by fusing a physical mechanism and deep learning, robust identification of a vibration source and dynamic reconstruction of a transmission path are realized in combination with vibration transmission entropy and Granger causal test, an accurate basis is provided for subsequent vibration reduction scheme design, and an adaptive scheme is screened based on vibration characteristics, so that the accuracy of vibration reduction is improved. A four-dimensional coupling model is constructed through finite element simulation, an improved genetic algorithm is adopted to solve a Pareto optimal solution under the constraint of cooperative work performance of new and old bridges, parameters are selected according to engineering priorities, and cooperative optimization of the vibration reduction effect, structural safety, cost control and durability is achieved. Therefore, the accuracy and engineering applicability of vibration disturbance control at the joint of the new bridge and the old bridge are remarkably improved.

The present application relates to a kind of methods for improving iron ore sinter low temperature reduction pulverization index, belong to iron ore sinter processing technical field.The method includes: collecting finished iron ore sinter as target sample, obtaining the initial sinter low temperature reduction pulverization index of target sample, original chemical composition and its proportion;Hyperbolic space of sinter low temperature reduction pulverization index is constructed, and coarse proportioning matrix is calculated;According to coarse proportioning matrix, multi-dimensional variable solution group is calculated using genetic algorithm;According to preset gradient quantity, the optimal solution under each temperature gradient interval is filtered in multi-dimensional variable solution group, and temperature gradient solution group is generated comprehensively;According to temperature gradient solution group, the optimal sintering material proportioning scheme and the combination of optimal parameters under each temperature gradient interval are calculated, and the optimal sintering material proportioning scheme and the combination of optimal parameters are applied in low temperature reduction pulverization process.The present application improves control precision, and improves the improvement effect of iron ore sinter low temperature reduction pulverization index.

The invention provides a laser powder bed melting method for preparing a high-toughness TC4 titanium alloy based on machine learning. The method comprises the steps that performance data of the TC4 titanium alloy prepared through different SLM process parameters are collected; constructing a hybrid expert (MoE) machine learning prediction model framework; classifying the TC4 data by adopting a K-means clustering algorithm, and taking a clustering center as an initial weight of an input layer and a first layer of the gating network; presetting a TC4 performance prediction model through the gating network and the plurality of expert networks after clustering information initialization; performing small-range iteration through large-step network search in combination with a Bayesian optimization method so as to determine an optimal model structure and complete model training; the trained performance prediction model and a genetic algorithm are used for carrying out backstepping to obtain SLM printing parameters of the high-toughness TC4 alloy; and SLM forming is carried out, and the high-toughness TC4 titanium alloy is prepared. According to the method, a calculation framework which is high in precision and suitable for exploring a high-unknown characteristic space is constructed, and far-reaching influences on titanium alloy additive manufacturing and process optimization of other alloy systems are achieved.

The invention discloses a high-voltage circuit breaker short-circuit breaking direct test loop parameter self-tuning method, and belongs to the technical field of power system high-voltage electrical equipment tests. According to the method, an equivalent test loop is firstly established, mathematical modeling is carried out, in order to facilitate subsequent optimization, test loop elements are subjected to per unit, and the model is revised; and establishing a conversion relation formula between the dimensionless parameters and the dimensional parameters. Taking a dimensionless parameter as a decision variable, taking a differential equation corresponding to the model as a constraint condition, taking the sum of absolute values of differences between an obtained value and a standard value as a value function, and calculating a minimum value of the value function by applying a third-generation genetic algorithm; and finally, performing simulation verification on an optimization result. According to the invention, the working efficiency can be greatly improved, and more circuit breaker test tasks can be carried out within the same time.

The invention discloses a virtual synchronous machine key parameter optimization method giving consideration to transient power angle stability and short-circuit current suppression. The method comprises the following steps: establishing a VSG dynamic model; analyzing and calculating VSG short-circuit current and transient power angle stability respectively; analyzing key parameters influencing VSG short-circuit current and transient power angle stability by using small signal modeling to obtain a key parameter configuration range; according to the key parameter configuration range and the requirements for short-circuit current suppression and transient power angle stability, a VSG parameter optimization model is designed, and an improved genetic algorithm IGA is used for solving. And it is ensured that short-circuit current is suppressed during the optimized VSG fault period, and the transient power angle is kept stable. The invention aims to realize the effects of transient stability improvement and short-circuit current suppression only by optimizing parameters without adding extra strategies.

The invention discloses a space target monitoring constellation configuration optimization method and system considering complex constraints, and belongs to the technical field of aerospace mission design and optimization. The method comprises the following steps: firstly, constructing a discrete orbit modal library meeting regression orbit dynamic resonance conditions; constructing generalized hybrid design variables consisting of integer indexes and real number fine tuning quantities on the basis of the library; establishing an optimization model taking the space volume coverage rate, the maximum revisit time and the system construction cost as targets and taking illumination, dynamics and maneuvering capability as constraints; performing rapid analysis and coarse screening on invalid links through track geometry; and finally, performing global optimization by using an improved non-dominated sorting genetic algorithm to obtain a Pareto optimal constellation configuration set. According to the method, accurate evaluation of the three-dimensional space target coverage efficiency is realized, the physical feasibility and long-term stability of a configuration scheme are ensured, and a high-dimensional multi-target optimization problem is efficiently solved.

The invention provides a method for synchronously inverting unsaturated soil solute reaction parameters, and belongs to the technical field of software development. The method comprises the following steps: establishing an initial model for simulating chain reaction migration of solutes in unsaturated soil based on HYDRUS-1D software, and generating a corresponding input file; based on observation data of the one-dimensional vertical infiltration test, determining a plurality of solute reaction parameters to be synchronously inverted and an initial value range thereof; adopting a genetic algorithm to randomly generate an initial population containing multiple groups of parameter combinations in the initial value range; performing solute transport simulation on each group of parameter combination in the population, and automatically extracting a simulation result; calculating a fitness value corresponding to each parameter combination based on the observation data and the simulation result obtained in the step S4; and iteratively optimizing, and judging whether a termination condition of the genetic algorithm is met or not. By optimizing a software running program and adjusting automatic extraction and processing of calculation parameters, efficient and continuous soil solute transport analysis is realized.

The invention discloses a non-full-length beam steel bar material breaking optimization method based on a hybrid optimization algorithm, and aims to solve the problem that an existing non-full-length beam steel bar material breaking method cannot balance the steel bar utilization rate and the calculation efficiency. The method comprises the following steps: for required beam steel bars under the same beam steel bar diameter, dividing the required beam steel bars into two groups according to the length of the beam steel bars; for required beam steel bars with the length larger than 12 m, a cut excess material splicing method is adopted, an optimized mathematical model of steel bar excess materials is established, and the number of used raw material steel bars and the division length of the raw material steel bars are calculated and determined through a genetic algorithm; and for required beam steel bars with the length smaller than 12 m, directly cutting from a single raw material steel bar or combining and processing the raw material steel bars with different specifications, listing all cutting modes, calculating steel bar excess materials corresponding to the cutting modes, and minimizing the total steel bar excess materials by the integer linear programming model to obtain a steel bar broken material combination scheme.

The invention discloses a flexible interconnection and energy storage collaborative planning method for a low-voltage distribution transformer area under high-proportion photovoltaic access, and the method comprises the steps: building a structure-function two-dimensional cluster division model, dividing a distribution transformer area cluster through an electrical distance, a voltage balance degree and an active power balance degree, and reducing the dimensionality of coordinated planning; carrying out connectivity analysis on the transformer areas in the cluster, judging interconnection requirements by taking the maximum net load rate of the transformer and the minimum net load of the transformer areas as feasibility indexes, and generating a candidate scheme set; establishing a power distribution area interconnection device-energy storage double-layer planning model, minimizing equipment capacity configuration at an upper layer according to annual comprehensive investment cost, and formulating a collaborative operation strategy at a lower layer according to minimization of operation cost and maximization of new energy consumption; a hierarchical solution strategy and an improved genetic algorithm for cluster division are adopted to improve the convergence speed and precision, it is ensured that an optimal planning scheme meeting economical efficiency and operation adaptability is obtained, the problem that the influence of factors cannot be comprehensively considered in a single planning dimension is solved, and the actual operation requirement is met.

The invention belongs to the technical field of CFD (computational fluid dynamics) parameter calibration, and discloses a CFD parameter adaptive calibration method and system based on measured data and a double-agent model, and the method comprises the steps: obtaining a CFD input parameter sample, inputting the CFD input parameter sample into a CFD solver, and obtaining an initial simulation result; determining an error evaluation index according to the initial simulation result based on a target actual measurement data result; constructing a double-agent model based on a Kriging model and a radial basis function neural network by taking a CFD input parameter sample as an independent variable and an error evaluation index as a dependent variable; the double-agent model is trained, the trained double-agent model takes the error evaluation index as fitness, and CFD input parameter values are obtained based on a genetic algorithm; the CFD input parameter values are input into the CFD solver for a simulation experiment, a calibrated simulation result is output, the reliability and generalization ability of prediction are improved through a double-agent model, a high-fidelity simulation result is output through the CFD solver, and the number of times of calling the CFD solver is reduced while the calibration precision is guaranteed.

The invention discloses a method for optimizing key structure parameters of a deep well electric submersible pump based on performance simulation, and relates to the technical field of design optimization of electric submersible pumps, a three-dimensional geometric model of a deep well submersible centrifugal pump is built in advance, the three-dimensional geometric model comprises an impeller, a guide shell, a pump shaft, a pump shell, an upper connector, a lower connector and a full-flow-channel structure, and initial structure parameters are calibrated; and establishing a centrifugal pump simulation model based on a computational fluid dynamics technology, performing fluid domain extraction, grid division and grid independence verification on the three-dimensional geometric model, and setting fluid attributes, boundary conditions and a turbulence model. According to the method, a closed-loop iteration framework for simulation, optimization, evaluation and feedback is constructed by adopting a mode of coupling a computational fluid dynamics simulation technology and a genetic algorithm, the limitation of local parameter optimization in the prior art is broken through, systematic and collaborative optimization of key structure parameters of the submersible centrifugal pump is realized, and the method is suitable for large-scale popularization and application. And the efficiency of the optimization process and the final optimization effect are obviously improved.

The invention discloses a multi-objective optimization method and system based on building full life cycle energy consumption prediction, and belongs to the technical field of building energy saving and intelligent construction. Comprising the steps of constructing a physical-data fused building digital twin model, executing multi-time scale energy consumption prediction, solving a multi-objective optimization problem and recommending a dynamic optimal strategy. A physical information neural network is adopted to embed the building heat conduction equation into a neural network loss function, and deep fusion modeling of physical constraint and monitoring data is achieved. And a layered prediction architecture is designed, and different prediction models are adopted for a short term, a middle term and a long term and fusion output is carried out. And solving three-objective optimization of energy consumption, comfort and cost by adopting a non-dominated sorting genetic algorithm to obtain a Pareto optimal solution set. And screening an optimal scheme from the solution set for recommendation in combination with the situation information and the user preference. According to the method, the energy consumption prediction precision and the physical interpretability are effectively improved, and multi-target collaborative optimization and personalized strategy recommendation are realized.

The invention relates to the technical field of gallium oxide crystal preparation, in particular to a gallium oxide edge-defined film-fed crystal growth quality prediction method based on artificial intelligence. Obtaining multi-source data of gallium oxide edge-defined film-fed crystal growth, wherein the multi-source data comprises process parameters and dynamic data; multi-modal data features are obtained based on data feature extraction of the multi-source data; inputting the multi-modal data characteristics into a multi-modal fusion prediction model to obtain gallium oxide edge-defined film-fed crystal growth quality prediction data; and obtaining optimized process parameters through a genetic algorithm based on the gallium oxide edge-defined film-fed crystal growth quality prediction data. According to the method, stage features are extracted respectively, the process state of each stage can be evaluated in real time, the process root of the final quality problem is traced, the situation that the crystal growth condition cannot be predicted by depending on experience in a traditional method is avoided, comprehensive prediction of crystal growth is achieved, process parameters are fed back, and optimization of the process parameters is achieved.

The invention provides a train bearing full life cycle adaptive optimization predictive maintenance method and system, and the method comprises the steps: obtaining the operation data of a train bearing, and carrying out the preprocessing; extracting a numerical index of the preprocessed operation data; constructing a digital geometric model of the train bearing, constructing a high-fidelity physical twinborn body, and constructing a data twinborn body according to the preprocessed operation data; performing parallel prediction on the numerical index based on the physical twinborn and the data twinborn to obtain a probabilistic prediction result, performing iterative fusion on the probabilistic prediction result through a combination rule to obtain a comprehensive RUL prediction result, and coordinating the data twinborn by adopting a federated average algorithm; and taking the minimization of the total expected cost as a target function, and carrying out global optimization by adopting a genetic algorithm in combination with a maintenance plan and a comprehensive RUL prediction result, so as to output an optimal maintenance decision. According to the invention, timely early warning can be carried out, and the confidence of the prediction result is improved.

The invention discloses a cross-domain collaborative multi-task load balancing method and system which are used for a multi-domain edge core fusion network, and the method comprises the steps: constructing a communication model and a calculation model, respectively depicting the transmission rate and time delay of a task on a main / standby path and the resource distribution between the task and a calculation node, automatically switching to an alternative path through a fault recovery model by utilizing a node / link availability variable when the main path fails; on this basis, a multi-constraint optimization model is established with throughput maximization, load balancing optimization and fault recovery cost minimization as targets, and a joint optimization framework based on a graph neural network and a non-dominated sorting genetic algorithm is proposed; and a non-dominated sorting genetic algorithm is guided to perform population initialization and directed evolution, and a Pareto optimal scheduling strategy is output in combination with a constraint repair mechanism, so that the performance of cross-domain task scheduling, the resource utilization balance and the fault recovery robustness are improved.

The invention relates to the field of motor and gear transmission systems, in particular to a method for optimizing design parameters of a transmission gear in an electric drive system.The method includes the steps that firstly, a two-dimensional finite element model of a permanent magnet synchronous motor is established, rotor stepped skewed slots and material magnetic saturation characteristics are accurately simulated, and an external characteristic MAP is generated; then calculating electromagnetic force density based on a Maxwell stress tensor method, mapping the electromagnetic force density to a multi-body dynamic model to construct a transverse coupling model, extracting an ECE reduced-order model based on a permanent magnet synchronous motor two-dimensional finite element model, forming a torsional vibration model in combination with a control algorithm, integrating a rigid-flexible coupling mechanical system, and establishing an electromechanical-rigid-flexible coupling model; and finally, through sensitivity analysis and a response surface model, with vibration acceleration and torsion amplitude as targets and gear strength as constraints, a Pareto optimal solution is solved by adopting a genetic algorithm, electromechanical coupling simulation precision is greatly improved, system vibration is effectively reduced, gear transmission reliability is enhanced, and the method is suitable for design of a high-dynamic-performance electric drive system.