1557 results about "Performance index" patented technology

The invention provides a real-time link anomaly detection and sampling method and device based on edge AI driving, and is applied to the technical field of artificial intelligence. Segmenting and aggregating the original link tracking data in each time window through a dynamic time window division mechanism to generate a statistical feature vector of link topology in the time window, the original link tracking data including a link topology relationship, a service calling level and a performance index; inputting the statistical feature vector into an anomaly detection model obtained by pre-training for analysis to obtain a path anomaly probability score; and dynamically adjusting the sampling strategy of the next time window according to the path anomaly probability score. Through edge AI calculation nodes, dynamic time window division, segmented aggregation and dynamic adjustment of a sampling strategy, the real-time performance of anomaly detection and the reliability and practicability of anomaly detection are improved, adaptive sampling is realized, and the sampling precision and efficiency are ensured.

The invention provides a server cluster operation and maintenance method based on multi-source heterogeneous data fusion and a dynamic knowledge graph, and the method comprises the following steps: collecting a performance index, a log text and topological structure data of a server cluster, splicing the performance data and the log data based on a unified time window, and generating a multi-modal feature sequence; and analyzing the sequence by using an unsupervised deep learning model, constructing a dynamic health baseline, and generating a health degree portrait through the deviation with real-time data. When an exception is detected, mapping an exception event into a dynamic topological graph constructed based on a topological structure; analyzing a fault propagation probability between nodes by using a graph neural network algorithm, positioning a root cause node, and generating a disposal strategy to execute disposal operation; and collecting the processed recovery data as a feedback signal, and updating the deep learning model by using incremental learning. The method has the beneficial effects that the fault discovery accuracy is improved, the alarm storm is effectively inhibited, the root cause is directly positioned, and the model self-iteration adaptability is higher.

The invention discloses a process intelligent simulation method and system based on rational number fusion, and belongs to the technical field of high-end equipment manufacturing and artificial intelligence. The method comprises the following steps of: constructing a fusion database used for storing a mapping relationship between process parameters and organization characteristics by taking a mathematical model fusion normal form as a core, taking the mathematical model data as theoretical model data and taking the mathematical model data as industrial field data; constructing a multi-scale AI simulation agent model corrected by the industrial field data, and constructing an intelligent prediction model used for representing an association relationship between organization characteristics and service performance; and finally, receiving a target performance index, carrying out global optimization under double constraints of a physical boundary of a theory and a simulation environment which is corrected by a number by utilizing an AI reverse design engine, and carrying out reverse solution to obtain an optimal process parameter. Through a two-way closed-loop mechanism of a theoretic constraint number and a number correction theoretic, the fundamental problems of distortion of a theoretical model caused by a scale effect and lack of physical constraint with an AI model are solved.

The invention relates to an intelligent customer service self-learning method and system, and the method comprises the steps: collecting the interaction data of a user and an intelligent customer service, and forming a multi-dimensional data set; based on a PID (Proportion Integration Differentiation) controller, processing the performance indexes in the multi-dimensional data set, calculating a current error signal, and generating a corresponding control instruction according to the current error signal so as to adjust the response behavior of the intelligent customer service system in real time; evaluating the system performance data adjusted by the control instruction to obtain evaluation feedback; and according to the evaluation feedback, dynamically adjusting the parameters of the PID controller through a self-adaptive control strategy, and feeding back the adjusted parameters to the PID controller in the step S2. According to the invention, by introducing a closed-loop feedback mechanism based on the PID controller and a parameter adaptive optimization strategy, real-time regulation and control of the response behavior of the intelligent customer service system are realized, and the stability, the response speed and the user satisfaction of the system are remarkably improved.

The invention provides an unmanned aerial vehicle consistency control method based on a Stackelberg-Nash game, and relates to the technical field of multi-agent consistency and game optimization control. The method comprises the following steps: establishing a motion attitude nonlinear dynamic model of each unmanned aerial vehicle in a multi-unmanned aerial vehicle system, and defining a communication network topological relation; constructing a consistency error and a performance index function; the method comprises the following steps: establishing a layered Stackelberg-Nash game mechanism with a plurality of participants; utilizing a Bellman optimality principle to construct a coupling HJB equation to solve an optimization control strategy of the leader and the follower; and constructing a single evaluation network to estimate the optimization control strategy of the leader and the follower in each execution so as to realize an optimization control target. A favorable tool is provided for analyzing a series of control problems of master-slave consistency of multiple unmanned aerial vehicles in the control field, and the reliability of a control system can be enhanced to a certain extent.

The invention belongs to the technical field of urban rail vehicle detection and maintenance, and discloses a full-process optimization method and system for polygonal wear of a metro vehicle wheel. The method comprises the following steps: firstly, constructing a digital twin-driven train rigid-flexible coupling dynamic model, carrying out global sensitivity analysis, establishing a sensitivity index model, screening key dynamic performance indexes, and carrying out batch simulation to construct a dynamic response database; feature extraction and classification model training are carried out on the index data, multi-layer wavelet packet decomposition is carried out on the one-dimensional vibration signals, and a multi-channel feature vector is constructed and input into a one-dimensional residual network model; inputting actually acquired data into the trained model, calculating a relative close degree to generate a comprehensive index and a grading result, and generating turning repair suggestions based on grading; meanwhile, multi-source monitoring data are collected, a long-short-term memory network is used for predicting the abrasion evolution trend, finally, turning repair suggestions and trends are integrated, an accounting model and an evaluation system are constructed, and an optimal maintenance decision is generated through a multi-target optimization algorithm.

The invention relates to the technical field of machine tool performance analysis, and provides a machine tool functional part performance analysis method and system based on big data. Multi-source operation information, including a vibration signal, a temperature signal, a motor current signal, an acoustic emission signal and working condition information, of functional parts of a machine tool is collected, and machine tool operation performance indexes are determined based on the information; and when any index exceeds a normal interval under the current working condition, the system can judge that the functional part of the machine tool is preliminarily abnormal, multi-dimensional abnormal information is constructed according to the working condition information, the vibration information and the temperature information, the fault risk level is determined according to the multi-dimensional abnormal information, and finally early warning information is sent and user feedback is acquired. Therefore, the problem of false alarm caused by non-fault factors such as tool wear in the prior art is effectively solved, and the difficulty that the credibility of an operator to early warning information is reduced is avoided.

The invention relates to the field of nonlinear system control, and provides a preset time reinforcement learning method and system of a continuous nonlinear system, and an electronic device, and the method comprises the steps: constructing a zero-sum game framework based on a kinetic model and a performance index of the nonlinear system; determining a value function and a Hamiltonian function based on a zero-sum game framework; applying a preset neural network model to carry out approximation on the value function, and determining an approximation error; based on the Hamiltonian function and the approximation error, an approximate optimal control strategy and a worst interference strategy are determined; constructing a Lyapunov function based on the value function and the weight error of the value function; and based on a Lyapunov function, an approximate optimal control strategy and a worst interference strategy, a reinforcement learning result is verified. The method and the device are used for overcoming the defects that convergence time cannot be dynamically adjusted, parameter complexity is high and robustness is insufficient in the prior art, and the scheme of the invention can meet dual requirements of a continuous nonlinear system on dynamic convergence and anti-interference performance.

The invention relates to the technical field of parameter optimization, in particular to an automatic kernel network parameter optimization method, which comprises the steps of constructing an enhanced deep Q network model, and integrating the enhanced deep Q network model with a priority playback buffer area, a meta learning module, a Bayesian optimizer and a neural architecture search module; using performance index data to train an enhanced deep Q network model, the training process including using a priority playback buffer to store and sample empirical data, using a meta-learning module to perform task adaptation, and monitoring training indexes of multiple dimensions to evaluate the convergence state of the model; selecting a kernel parameter adjustment action according to the current state through the trained enhanced deep Q network model; executing the selected kernel parameter adjustment action, and evaluating a parameter adjustment effect based on the multi-target reward function; and updating the enhanced deep Q network model according to an evaluation result, wherein the priority playback buffer area and the Bayesian optimizer are utilized in the updating process.

The invention discloses an extended-range hybrid propulsion double-source dynamic coupling energy management method, which comprises the following steps: carrying out global physical modeling on a double-source power system and a flight scene, and establishing a double-source dynamic coupling model; designing a reinforcement learning physical constraint reward function, performing optimization training on each coefficient of the reward function by adopting a QMPSO algorithm, and outputting an optimized reward function coefficient; a qualified double-source dynamic coupling model is verified, and a power distribution coefficient is optimized; outputting the optimal power distribution coefficient of the battery and the range extender; the superiority of the dual-source power cooperative control strategy in the aspects of flight economy, operation stability and system life guarantee is verified through multi-dimensional comparative analysis of each performance index. Cooperative power distribution of the battery and the range extender is achieved through dynamic coupling modeling and reinforcement learning, the flight scene load requirement is met, the system energy efficiency is improved, and the service life of parts is prolonged.

The invention discloses a numerical control machine tool vibration suppression self-adaptive control system and method, and relates to the technical field of intelligent vibration control, and the method comprises the steps: building a current-modal dynamic mapping relation between an electrical drive characteristic and a mechanical structure modal response based on a vibration state feature vector; real-time machine tool modal state vectors are obtained through online recursive estimation; the machine tool modal state vector is used as a boundary condition to be injected into the virtual prediction model; solving to obtain an optimal control parameter sequence and a corresponding vibration prediction result in a future time domain by taking multi-performance index collaborative optimization as a target through a rolling optimization control strategy; translating the control parameter sequence into a specific execution instruction and issuing the specific execution instruction; monitoring an execution process in real time and recording actual response data; according to the method, the accuracy of vibration prediction and the real-time performance of control response are improved by establishing the dynamic mapping relation from the electromagnetic driving characteristics of the servo main shaft and the feed motor to the dynamic response of the machine tool structure.

The invention relates to the technical field of air conditioner fan blade design optimization, and discloses an air conditioner fan blade optimization method and system based on a BP neural network and a GA algorithm. The method comprises the following steps: obtaining initial geometric parameters and performance data of a fan blade, and cleaning and standardizing the initial geometric parameters and the performance data to form a standard data set; a BP neural network is used for training to obtain a fan blade performance prediction model; a genetic algorithm is applied to optimize the prediction model, and a new design parameter population is generated through genetic operations such as selection, crossover and variation; the optimized parameters are input into a CAD system to generate a candidate fan blade model, numerical simulation is carried out, and performance indexes of the candidate fan blade model are calculated; and screening excellent individuals based on a multi-objective optimization method, iteratively executing optimization and simulation processes until convergence, and finally outputting an optimal fan blade design. According to the method, the fast prediction of the neural network and the global search capability of the genetic algorithm are combined, the dependence of traditional optimization on high-frequency numerical simulation is reduced, and the design efficiency and quality are improved.

The invention provides a method, a system and equipment for improving the computing performance stability of a hardware platform and a medium, and belongs to the technical field of computer system performance optimization. The method comprises the following steps: acquiring architecture characteristic data of a bottom hardware platform through a hardware detection tool, and generating and loading a first-stage system kernel parameter configuration based on the architecture characteristic data; reading the architecture characteristic data, carrying out behavior analysis and type identification on the running process based on the architecture characteristic data, and generating a second-level process scheduling strategy according to the behavior analysis and type identification; reading cache structure information in the architecture characteristic data, and driving a file system to intelligently prefetch and reconstruct a storage layout of memory data based on the cache structure information; and continuously collecting performance index flow data when the system runs, performing real-time analysis on the performance index flow data by using a performance degradation model, generating a feedback control instruction according to an analysis result, and dynamically correcting the kernel parameter configuration of the first-stage system and the scheduling strategy of the second-stage process.

The invention discloses a k8s heterogeneous resource scheduling method, system and device based on intelligent sensing and a medium, belongs to the technical field of cloud computing and resource scheduling, and aims to solve the technical problems that a traditional scheduler is weak in sensing capacity, extensive in scheduling decision, low in resource utilization rate and high in resource utilization rate in a heterogeneous environment. According to the technical scheme, the method comprises the steps that a multi-dimensional resource sensing layer is constructed, specifically, real-time collection and convergence of heterogeneous hardware dynamic performance indexes are achieved by deploying an expanded monitoring equipment plug-in, and fine-grained runtime data of hardware including a CPU, an FPGA and an AI acceleration card are abstracted into a standardized index data set in a unified mode; constructing a node dynamic resource portrait: constructing the dynamic resource portrait based on the standardized index data set through a feature fusion and modeling technology, and generating a quantitative capability evaluation vector for each computing node in the cluster; and intelligent scheduling decision making: through a decision engine based on reinforcement learning, obtaining an optimal scheduling target according to the resource demand characteristics of the Pod to be scheduled and the dynamic resource portraits of the nodes.

The invention discloses a wireless power transmission coil optimization method and a related system, which can realize automation of coil structure parameters and multi-target global optimization by acquiring a coil geometric parameter space, constructing a comprehensive optimization function and performing iterative search in the coil geometric parameter space. The problems that in traditional design, the number of simulation iterations is large, design efficiency is low, local optimum is prone to occurring, and multiple performance indexes are difficult to balance are effectively solved, coil design efficiency and precision are remarkably improved, and dependence on artificial experience is reduced. Therefore, the number of manual intervention and simulation is remarkably reduced, the coil design efficiency is improved, and the prototype development period of the WPT system is shortened. Besides, iterative search is carried out in the parameter space, so that the whole design space can be effectively explored, a locally optimal solution trap can be jumped out, and a globally optimal or approximately globally optimal coil structure parameter combination can be obtained more possibly.

The invention provides a laser remelting process parameter optimization method and system based on a multi-objective optimization algorithm. The method comprises the steps that the range of laser remelting process parameters on the surface of a cladding layer is limited; designing a process parameter combination by using an ELHS method, carrying out a laser remelting experiment by using different process parameter combinations on the premise of keeping the surface quality of the cladding layer consistent, and collecting performance index data after remelting; establishing a nonlinear mapping model between the process parameters and the performance indexes by using a PSO-XGBoost model; a Pareto optimal solution set is obtained through population and individual initialization, non-dominated sorting, congestion degree calculation, optimal solution calculation and global optimization of process parameters by adopting an MOEDO algorithm based on a nonlinear mapping model; and a CRITIC-TOPSIS decision system is utilized to carry out evaluation sorting on the Pareto optimal solution set, and an optimal process parameter combination is screened out. According to the method, the influence of the laser power, the scanning speed and the lap joint rate on the quality and performance of the laser remelting surface can be considered at the same time, and the limitation of traditional single process parameter optimization is broken through.

The invention discloses an airborne radar system and method oriented to a signal transmitting device, and belongs to the technical field of airborne radar signal processing. Received radar task instructions are analyzed, target characteristic parameters, environment constraint conditions and performance indexes are extracted, and mapping relations between task requirements and transmitting waveforms, power and time sequence parameters are established; based on the mapping relation, the transmitting device resources are modeled into a power, frequency spectrum and time sequence three-dimensional state space, and the resource margin and the conflict risk are monitored and predicted in real time; matching a current task situation with a historical strategy library in combination with a resource state, and selecting a historical strategy with the highest similarity as a basic launching scheme; optimizing a resource allocation demand of the basic scheme according to a time sequence and a priority sequence, and introducing a resource buffer mechanism and dynamic priority adjustment to solve a multi-task resource conflict; based on real-time environment data, a basic scheme is decomposed into independently adjustable strategy units, and after optimization and recombination, a transmitting strategy adaptive to a specific scene is generated.

The invention relates to an ORC heat exchanger optimization design method and system based on deep learning. The method comprises the steps that S1, original data samples are expanded based on a data enhancement method; s2, screening key input features of the data samples; s3, synthesizing minority class samples to balance a sample data set; s4, a physical information neural network model is constructed and trained, and heat exchanger performance indexes under different structure parameter combinations are predicted based on the trained model; s5, optimizing the structural parameters of the heat exchanger by adopting a multi-objective coevolution optimization algorithm; and S6, simulation verification is conducted, and the optimal plate heat exchanger design scheme of the target scene is obtained. Through three technical breakthroughs of data enhancement driven by physical constraints, neural network architecture embedded in thermotechnical physics and multi-target collaborative optimization guided by forward distance, systematic technical obstacles in design of the ORC heat exchanger are solved, and an unexpected synergistic effect is generated.

The embodiment of the invention provides a federated learning contribution evaluation method and device, and the method comprises the steps: carrying out the grouping of a plurality of edge computing devices, and obtaining a plurality of sub-federated learning sets; and for the target federated learning sub-set, aggregating model update information corresponding to each edge computing device in the target federated learning sub-set, and determining a collaborative contribution value of the target federated learning sub-set based on the performance index of the updated global model on the common test set. Through a first linear programming solver, according to the collaborative contribution values of the multiple federated learning sub-sets, obtaining the maximum loss value corresponding to all the federated learning sub-sets and optimizing the maximum loss value to obtain the minimized maximum loss value, and through a second linear programming solver, obtaining the maximum loss value corresponding to all the federated learning sub-sets; and according to the maximum loss value after all the sub federated learning sets are minimized and the reference contribution values corresponding to the plurality of edge computing devices, target contribution vectors corresponding to the plurality of edge computing devices are determined, and the contribution degree of each edge computing device in the training process is accurately quantified.

The invention provides a one-dimensional pneumatic design method and device for an axial flow compressor, and belongs to the field of axial flow compressor pneumatic design. The method comprises the following steps: taking values of a plurality of design variables as the state of a reinforcement learning agent; the intelligent agent outputs the adjustment amount of the design variable according to the state, and the adjustment amount serves as the action executed by the intelligent agent; applying the action to the value of the current design variable to obtain an updated design variable; utilizing a one-dimensional inverse problem design program to generate a one-dimensional pneumatic design scheme of the gas compressor; utilizing a one-dimensional normal problem analysis program to output performance indexes; constructing a reward function according to the performance indexes; based on feedback provided by the reward function, a depth deterministic strategy gradient algorithm is adopted to train the intelligent agent; and performing one-dimensional pneumatic design of the gas compressor by using the trained intelligent agent. According to the method and device provided by the invention, the problems that the one-dimensional design of the axial flow compressor depends on experience, the efficiency is low, automatic optimization is difficult and the response is slow can be solved.

The invention discloses a standard system applicability evaluation method and system based on multi-source data, and relates to the field of standardization, and the method comprises the steps: collecting the historical operation data of equipment, and dividing the equipment into an experiment group equipment group and a control group equipment group; the method comprises the following steps: preprocessing historical operation data of equipment, and respectively constructing a performance index value sequence for quantitatively reflecting the achievement condition of a target standard for a technical target for an experimental group equipment group and a control group equipment group; and on the basis of the performance index numerical value sequences of the experimental group equipment group and the control group equipment group, a net effect value and statistical confidence of a target standard are calculated by adopting a double difference model, and a unit model and a geographical climate region are added into the double difference model as fixed effect control variables. According to the method, the corrected net effect value and the intermediary centrality score are fused into the comprehensive index, so that multi-dimensional dynamic evaluation combining data driving, causal identification and knowledge value of standard applicability is realized.

The invention discloses an AI infrastructure performance detection method and device and a storage medium, and belongs to the technical field of data processing. The method comprises the steps that according to chip information of container nodes, dynamic instrumentation is conducted on a kernel layer and a calculation layer by expanding a Burkley packet filter, first performance indexes of the kernel layer and the calculation layer are collected, a hardware management library function is called, second performance indexes of a chip hardware layer are collected, and on the basis of a control group mechanism, the kernel layer and the calculation layer are subjected to dynamic instrumentation; and obtaining meta-information of the business process group in the container node, constructing an association relationship between the first performance index and the business process group and between the second performance index and the business process group through association marking according to the meta-information, and performing association analysis on the first performance index and the second performance index based on the association relationship to obtain a performance detection result of the business process group. According to the method, the performance parameters are collected through a non-intrusive scheme, the performance indexes of different service processes are determined through a service association mode, and the accuracy of AI performance problem positioning is improved.

The invention discloses a few-sample inductance core surface defect detection method based on model interaction, and belongs to the technical field of machine vision and industrial defect detection. The method comprises the following steps: S1, data acquisition and image preprocessing are carried out, and normal samples, labeled samples and unlabeled samples are constructed; s2, constructing an unsupervised statistical model based on statistical learning; s3, constructing a supervised semantic segmentation model; s4, inputting an inductance core image to be detected into the unsupervised statistical model and the supervised semantic segmentation model at the same time for processing, and generating a segmentation result; s5, detecting result differences are quantified; s6, performing parameter updating on the unsupervised statistical model; s7, generating a pseudo label based on an unsupervised statistical model; s8, carrying out weight updating on the supervised semantic segmentation model; and S9, inputting the processed to-be-detected images into the updated unsupervised statistical model and supervised semantic segmentation model in batches for detection to obtain a detection result, and analyzing and calculating system performance indexes.

The invention discloses a multi-dimensional layered current limiting method based on spatio-temporal feature fusion. The method comprises the following steps: acquiring a hardware limit speed, and generating a global quota based on a reinforcement learning model; calculating a variable coefficient, and if the variable coefficient exceeds a preset critical value, introducing a conservative coefficient and generating a weight factor through nonlinear function mapping to suppress the micro network jitter; constructing a priority factor matrix based on the service priority and the service type, and obtaining a service priority factor; correcting the average bandwidth of the node by integrating the multi-dimensional dynamic weight factor and the service priority factor to obtain a suggested speed, inputting a historical performance index into the LSTM model to predict the load of the next period, and if the historical performance index exceeds a critical value, triggering connection migration before executing current limiting to realize active avoidance; otherwise, comparing and selecting the minimum value of the global quota, the suggested speed and the hardware limit speed as the final current-limiting speed. The problems of current limiting strategy lag and wide oscillation can be solved, and the bandwidth utilization rate and the system stability are improved.

The invention discloses an intelligent fault injection and performance quantification system and method for a helicopter engineering simulator, and belongs to the technical field of flight simulation and testing, and the system comprises a hierarchical combinable fault model library module which is used for the flexible construction from a part level to a system level to a composite fault; the intelligent fault injection management module is used for realizing an intelligent fault injection strategy; the multi-dimensional performance index quantification module is used for collecting data before and after fault injection in real time and setting a performance evaluation index system; the automatic test and visual analysis module is used for comparing various quantitative indexes of different control laws or different parameters of the same control law in the same fault scene to generate a comprehensive evaluation report; according to the intelligent fault injection and performance quantification system and method for the helicopter engineering simulator, efficient, objective and deep testing of robustness, stability and efficiency of an advanced flight control law in a special condition state is realized through a hierarchical fault model, an intelligent injection strategy and automatic quantitative evaluation.

The invention discloses an intelligent driving evaluation method and equipment. The method comprises the following steps: acquiring environment perception data recorded by a real vehicle and a corresponding recorded vehicle pose; performing data transformation on the environment perception data according to a pose difference between the vehicle model pose and the recorded vehicle pose so as to generate transformation perception data corresponding to a vehicle model view angle; generating a prediction track based on the transformation perception data, iteratively updating the pose of the vehicle model according to the prediction track, and recording dynamic evaluation data; the dynamic evaluation data comprises an iteratively updated vehicle model pose, transformation perception data and a prediction track; and determining an evaluation performance index of the intelligent driving system based on the dynamic evaluation data. Therefore, a dynamic closed-loop evaluation mechanism under a real data condition is constructed, self-adaptive association of perception input and a vehicle motion state is realized, and an intelligent driving system can generate continuous decision feedback in an evaluation process, so that the time sequence consistency and stability of the system in dynamic control are accurately reflected.

The invention discloses a reinforcement learning-based cluster spacecraft multi-target intelligent cooperative tracking method. The method comprises the steps of establishing a relative motion relationship between a tracking spacecraft and a target spacecraft through a nonlinear orbit kinetic equation; designing a double-layer game framework, constructing a non-zero sum game in the cluster to drive cooperation, and introducing a zero and maximum and minimum game between the cluster and a target to describe a confrontation relationship; based on communication topology and relative state information, defining a local error term and a performance index function of the tracking spacecraft and the target spacecraft, and defining an optimization target of each agent under cooperation and confrontation; and iteratively updating the value function and the control law. According to the invention, collaborative tracking can be realized without defining a system model. The method can be widely applied to the field of cluster control.

The invention provides a flight path optimization method and system based on an improved particle swarm optimization algorithm, and belongs to the technical field of intelligent optimization algorithms and aircraft flight path optimizing.The method comprises the steps that concerned performance indexes in the flight process of an aircraft are obtained to construct a cost function; the cost function is sampled, sampling points of the cost function serve as particles, the improved particle swarm optimization is adopted to optimize the cost function, and a global optimal position is obtained and serves as a final track optimization result; the improved particle swarm algorithm comprises the following steps: carrying out particle initialization by adopting a method for assigning a particle initial value, carrying out random team distribution on each particle by adopting a Monte Carlo method, carrying out first-time updating on a global optimal particle with a minimum adaptive value by using a gradient descent method, and carrying out second-time updating on a global optimal particle with a minimum adaptive value according to the optimal position of each particle in the team and the optimal position of the particle in the team. And the speed and the position of the particle are updated for the second time based on the second-order consistency theory. According to the method, the convergence speed of the algorithm is improved, and falling into a local optimal solution is avoided.

The invention relates to the technical field of environment adaptability testing, and discloses an identification key performance comprehensive environment adaptability testing system. The system comprises a multi-environment factor acquisition and processing module for acquiring data and performing normalization preprocessing; the environment scene dynamic modeling module is used for constructing a multi-dimensional association graph and updating a topological structure; the performance index evaluation module evaluates a performance degradation index in a composite environment by means of a spatial-temporal feature fusion algorithm; the failure mode prediction module is used for generating a potential failure mode under multi-environment coupling according to the performance degradation trend and the stress accumulation effect; the environment tolerance analysis module is used for integrating data to establish a virtual model and outputting a tolerance residual error of a specific environment section; the test scheme optimization module is used for generating a self-adaptive test sequence according to the residual error and the map; and the environment scene simulation control module is used for regulating and controlling parameters of the test cabin in combination with multiple information. The system can comprehensively and accurately evaluate the performance and endurance capability of equipment in a composite environment, and has a dynamic adjustment characteristic.

The invention discloses a glacier material balance simulation method and system based on feature interaction, and belongs to the technical field of glacier hydrology and climate change monitoring, and the method comprises the steps: sequentially carrying out the uniform format processing and slope feature enhancement of a multi-source data set of a glacier, and dividing the multi-source data set into a simulation data set and an observation data set; training a model based on a trans-attention Transform encoder framework by using the simulation data set to obtain a pre-training model; when one-glacier-leaving cross validation is carried out on the pre-trained model, multi-stage fine tuning training is carried out by using the observation data set to obtain a plurality of fine-tuned models; performing model integration based on performance index screening on the fine-tuned models, and constructing an integrated simulation model; and preprocessing the meteorological dynamic characteristics and the static topographic characteristics of the target glacier, inputting the preprocessed meteorological dynamic characteristics and static topographic characteristics into the integrated simulation model, and carrying out glacier material balance simulation to obtain a glacier material balance simulation result. According to the method, the simulation uncertainty is reduced, and the high-precision simulation of the glacier material balance is realized.