205 results about "Ordinary differential equation" patented technology

The invention discloses a fault diagnosis and detection system for production automation equipment. The fault diagnosis and detection system comprises a data sensing layer which is used for carrying out multi-mode signal acquisition and real-time preprocessing; the feature extraction layer is used for constructing a recursive block convolution module, capturing transient impact features in four time steps by using an L1-layer gating convolution unit, associating a 16-time-step cross-block periodic degradation mode with an L2-layer sparse attention mechanism, aggregating multi-sensor spatial-temporal features by using an L3-layer global context node, and performing multi-scale feature extraction; the causal reasoning layer is used for establishing a physical constraint driven causal graph engine and outputting a fault propagation path with probability weight; the state modeling layer is used for constructing a continuous health evolution model by adopting a Shenchang differential equation, embedding a physical constraint loss function, and performing equipment full life cycle health state prediction and residual service life estimation in combination with a three-stage memory fusion mechanism of LSTM short-term memory, differentiable neural dictionary medium-term memory and knowledge graph long-term memory; and the decision support layer is used for generating a personalized maintenance work order.

The invention discloses a multi-mode emotion continuous recognition method for medical treatment, belongs to the technical field of artificial intelligence and medical treatment information, and mainly aims to simulate the dynamic change process of emotion by establishing a Neural ODEs framework and overcome the static property and discreteness of emotion modeling in a traditional method. Through a causal inference technology, emotional features are separated from individual-independent physiological differences, and the generalization ability across individuals is improved. A self-supervised learning method is utilized, the synergistic effect between the EEG and the eye movement signal is improved through cross-modal contrast learning, and the emotion recognition precision is enhanced. The calculation complexity is reduced through a dynamic sparse attention mechanism, and meanwhile, focusing is performed on a key time slice in emotion recognition. Through multi-task joint learning, the model learns multiple tasks such as emotion intensity regression and tested identity recognition during emotion classification, and the personalized emotion recognition capability is improved.

The invention provides a thyroid cancer auxiliary diagnosis and metastasis risk prediction method based on deep learning, and relates to the technical field of artificial intelligence auxiliary medical treatment, and the method comprises the steps: extracting ultrasonic image multi-scale features through a self-adaptive neural architecture search network, combining clinical examination data, fusing diagnosis and treatment knowledge through a neural symbol inference device, and carrying out the prediction of the metastasis risk. Generating a knowledge enhancement feature map; constructing a feature propagation field by using a dynamic neural field network, solving a dynamic evolution equation, and generating a spatial-temporal feature field representing the dynamic change of focus features; constructing a tumor diffusion kinetic model by using an implicit neural representation network and a nerve ordinary differential equation network, calculating a transition probability based on an optimal transmission algorithm, solving an optimal control equation, and outputting a metastasis risk prediction result of each organ; the thyroid cancer diagnosis accuracy and metastasis risk prediction reliability can be effectively improved, and doctors can be assisted in accurate diagnosis and treatment.

The invention discloses a driving mechanism analysis method of reservoir group scheduling for flood non-consistent evolution, which comprises the following steps: acquiring a smooth reservoir entering flood sequence by utilizing a topologically coupled physical manifold constraint denoising model, and constructing dynamic topological characteristics representing propagation time lag and sensitivity through a hydraulic propagation mechanism-based Figure ordinary differential equation; constructing a structural causal model comprising a scheduling capability index, ectogenic hydrological driving and topological characteristics, and fitting a nonlinear dependency relationship by using a causal generalized additive model; executing anti-fact inference, and calculating a local causal driving index and a global causal cumulative effect index through a dry budget; and generating an optimal scheduling strategy for suppressing variation based on the causal index. According to the method, systematic analysis from data physical restoration to causal mechanism decoupling can be realized, the driving contribution of a scheduling behavior to flood inconsistency is accurately quantified, and decision support is provided for scientific flood control of a drainage basin.

The invention discloses an end-to-end oil reservoir history fitting method based on flow matching, which belongs to the field of petroleum engineering, and comprises the following steps: step 1, collecting and sorting oil reservoir geological parameters and oil-water well production dynamic data, constructing a data set, and carrying out data preprocessing; step 2, constructing a flow matching infrastructure; step 3, constructing an improved U-shaped network for flow matching velocity field prediction; 4, constructing an ordinary differential equation solver to realize data generation; and 5, integrating and packaging the flow matching infrastructure, improving the U-shaped network and an ordinary differential equation solver to obtain a complete flow matching model, and realizing end-to-end dynamic history fitting of the oil reservoir. And directly inputting a production dynamic condition by utilizing the trained end-to-end flow matching model to generate an oil reservoir parameter field sample conforming to the condition. In the process, additional intermediate link conversion is not needed, and dynamic matching and accurate parameter adjustment of the oil reservoir model can be achieved.

The invention discloses a continuous time dynamics prediction method, system, terminal and medium fusing a diffusion model and a graph frequent differential equation, and relates to the technical field of dynamics prediction.The method comprises the steps that a multi-node time sequence is obtained, network structure inference is conducted on the multi-node time sequence through the diffusion model, and a potential graph structure between nodes is obtained; carrying out continuous time dynamic modeling by adopting a Scheng ordinary differential equation, and predicting a node state at any time point; diffusion reconstruction loss, dynamic prediction errors and structure sparsity constraints are constructed, total loss is established, network structure inference based on a diffusion model and dynamic modeling based on a Shenzheng differential equation are coupled based on the total loss, and collaborative training optimization is achieved. According to the method, the potential graph structure of the system can be stably recovered in a complex noise environment, high-precision and continuous prediction can be carried out on dynamic evolution of the potential graph structure, and the limitation that structure inference and continuous time modeling cannot be considered in the prior art is overcome.

The invention relates to the technical field of water resource management and forecasting, in particular to a deep learning model building and forecasting method based on hydrological mechanism fusion. The method specifically comprises the following steps: constructing a snow melting calculation module and a soil calculation module, splicing to form a runoff production model, constructing a confluence calculation module, executing confluence evolution simulation of a calculation result of the runoff production module by using the confluence calculation module, and constructing a confluence model. In confluence model simulation calculation, according to the number of calculation units, a broadcast calculation strategy and an array-based ordinary differential equation solving method are adopted, parallel calculation of the multiple calculation units is achieved, and runoff production calculation results of the multiple units are obtained; and integrating and calculating runoff production calculation results of each unit through a confluence model to obtain a runoff prediction result of the modeled drainage basin after confluence. The method provided by the invention solves the problems of low model construction efficiency and poor practical application effect faced by the application of the deep learning technology in the hydrological model at present.

The invention relates to the technical field of data processing, in particular to a relational database intelligent query method based on machine learning, which comprises the following steps of: processing multi-modal flow data through time sequence alignment, generating a unified semantic representation vector, constructing a dynamic psychological state map, and modeling a psychological state evolution track by utilizing a neural common differential equation mechanism. After user query is received, historical dialogue nodes are retrieved from the graph, enhanced query intention representation is generated, the enhanced query intention representation is converted into an execution plan through a neural symbol inference engine, and a graph neural network is adopted to predict execution cost. And finally, a personalized analysis report is generated by combining a causal discovery algorithm, and system adaptive optimization is realized through feedback signals. According to the method, the problems of inconsistent time sequence semantics and strong context dependency of the multi-modal psychological data are effectively solved, and the query accuracy and the personalized level in a psychological dialogue scene are improved.

The invention discloses a flood peak enhanced physical base flow and residual error correction collaborative runoff prediction method, which belongs to the field of hydrological prediction, and comprises the following steps of: dividing a training set and a verification set according to a proportion, performing oversampling processing on flood peak samples, and constructing a time sequence window; a Xinanjiang model is discretized and expressed by adopting an ordinary differential equation, rainfall and potential evaporation data are input, and intermediate variables are obtained. A physical base flow and residual error correction dual-channel module is constructed, and physical base flow and residual error correction is calculated through two full-connection networks. And calculating a final runoff predicted value by adopting a residual connection structure, taking basic NSE loss as a core, superposing a flood peak sample error weighted item, strengthening flood peak fitting precision, and updating physical parameters and neural network weight through a back propagation algorithm. And verifying the model, and respectively calculating prediction indexes of the training set and the verification set. According to the method, fusion of a traditional hydrological model and a deep learning method is realized, the physical interpretation of the model is enhanced, and the basin runoff prediction precision is improved.

The invention provides a cell development process dynamic modeling method and device based on time sequence single cell transcriptome data and a medium, and relates to the crossing field of bioinformatics and computational biology. The method comprises the following steps: constructing a Shenchang differential equation learning framework; adjusting parameters of the single cell development state change model based on the Shenxuan differential equation learning framework so as to construct a population cell development state change model; obtaining a cell specific gene regulation network and a population cell gene regulation network based on the population cell development state change model so as to predict occurrence opportunity of cell lineage differentiation and a molecular decision mechanism of cell differentiation; therefore, the problems of incomplete modeling mechanism, insufficient noise processing and lack of energy principle in the existing cell development process are solved.

The invention relates to the technical field of ship underwater positioning, in particular to a dynamic space positioning method and system for a sensor chain body of a ship drag chain, and the method comprises the steps: dispersing the drag chain into a plurality of hinged rigid sections in a two-dimensional inertial reference system, connecting the sensor chain body to the tail end, and taking the motion of a ship as a traction point boundary; according to the given traction speed, the initial pitch angle, depth and tension distribution are obtained through static balance; calculating local speeds in the sections according to translation and rotation states of upstream nodes of all the sections, obtaining distributed hydrodynamic loads in combination with fluid parameters, establishing moment balance equations at all the upstream nodes, and forming a second-order ordinary differential equation set with a pitch angle as an unknown quantity; and numerical solution is carried out under a unified time step length, and the mass center positions of each node and a sensor chain body are obtained according to geometric recursion, so that dynamic positioning in an inertial reference system is realized. According to the invention, the precision and reliability of underwater target motion analysis and target tracking can be improved.

The invention relates to the technical field of boiler control, in particular to a multivariable coupling thermal process regulation and control system and method for carbon pollution governing, and the method comprises the steps: collecting multi-source data such as acoustic emission, temperature, humidity and spectrum, and constructing a feature sequence through time mark alignment and wavelet packet enhancement; a heat value characterization quantity is predicted by using a Shenchang differential equation model fused with dynamic gating, a partition equivalent thermal network model is driven on this basis, and accurate prediction of a future time domain temperature field is realized by dynamically correcting thermal resistance and thermal capacity; based on the prediction result, a control instruction is solved through multi-objective optimization under the condition that the active temperature constraint is met; and in combination with heat flow density feedback, a layered reinforcement learning controller is adopted for online compensation of a pre-feedback instruction, and stable and efficient regulation and control of the boiler are achieved.

The invention provides a vehicle track generation method and system capable of quickly responding to sudden interaction in automatic driving, and belongs to the technical field of track generation and motion control in automatic driving. Comprising the following steps: performing feature extraction on aerial view point cloud data, vehicle surrounding image data, high-precision map data and vehicle historical trajectory data to obtain a continuous environment information feature sequence in a time sequence; generating a dynamic self-adaptive anchor point representing the real-time driving environment information of the vehicle based on a continuous environment information feature sequence in a time sequence; modeling a de-noising process of a diffusion model generation track into an evolution process of a track latent variable in a de-noising network by using a Shenchang differential equation, and modulating the evolution process of the track latent variable at an activation level and an operator level of the de-noising network by a dynamic adaptive anchor point; and an ordinary differential equation decoder constructed by adopting an explicit Euler numerical integration method is adopted to carry out gradual reverse reconstruction on the evolution process of the latent variables of the track, and a future track of the vehicle is generated.

The invention discloses a three-dimensional molecule generation method fusing conditional flow matching and Van der Waals radius constraint, which comprises the following steps: processing a molecule training data set, and extracting a total number of atoms and a training element component histogram; based on the optimal transmission path interpolation, combining the sampling time step and the standard Gaussian noise to construct a noise coordinate and a target condition velocity field; the noise coordinates are input into a continuous flow matching prediction model, node features are extracted through affine transformation modulation, a prediction velocity field is obtained, soft atom type distribution is generated, and the expected Van der Waals radius of each atom type is calculated; calculating flow matching loss through a prediction velocity field and a target condition velocity field, calculating a geometric collision penalty term in combination with an expected Van der Waals radius and a noise coordinate, and constructing a total loss function training model parameter; and defining an ordinary differential equation by using the trained parameters for solving, and outputting a three-dimensional molecular structure file. According to the method, atom space overlapping is inhibited, and the physical rationality and chemical effectiveness of generated molecules are improved.

The invention provides a battery temperature prediction method and system based on a Shenchang differential equation. The method comprises the steps of obtaining multi-source operation data in the operation process of a battery system; performing time interpolation processing on the data, and uniformly mapping the data of different sampling frequencies to a continuous time dimension to obtain a continuous time input feature; respectively constructing global features and discrimination features based on the input features, wherein the discrimination features are used for representing key thermal influence factors such as battery calorific value and cooling medium flow; fusing the global features, the discriminant features and the current temperature state of the battery to construct comprehensive features; and inputting the comprehensive characteristics into a thermodynamic model constructed based on a Shenchang differential equation, and solving a continuous evolution process of the battery temperature through numerical integration to realize temperature prediction one by one. According to the method, the thermodynamic continuous evolution law can be followed, and the space coupling characteristic and the multi-working-condition robustness can be considered.

The invention relates to the technical field of multi-modal ophthalmology image analysis, and particularly discloses a multi-modal ophthalmology image analysis method, model and system based on optimal transmission image diffusion and a medium thereof.The method at least comprises the steps that S100, the distance between fundus color photo and OCT image modals is explicitly calculated through an optimal transmission algorithm, and the distance between fundus color photo and OCT image modals is calculated; carrying out collaborative evolution on the features in a continuous time domain in combination with a graph neural network and a Sheng differential equation model; and step S200, applying self-attention and cross attention in parallel, reserving modal specificity with low-layer fine granularity, and progressively fusing the color photo texture and the OCT depth structure in a high layer to realize cross-layer long-range dependent depth semantic fusion. The method not only promotes the leading-edge development of multi-modal medical image analysis, but also provides important scientific basis and technical support for constructing a high-precision and high-robustness intelligent ophthalmology diagnosis system.

The embodiment of the invention relates to a plant metabolite synthesis center and key gene analysis method and device. The method comprises the steps of constructing a partial differential equation, designing two neural network models, setting two ordinary differential equations, setting a data format of a sampling data sequence, designing a loss function LALL and designing a model training process. Intercepting experimental materials and storing the experimental materials; sampling and storing the frozen slices of the experimental material; after sampling is finished, setting sampling data sequences of various observation substances, and performing one-time targeted training on the two models; simulating the temporal and spatial change state of the current substance based on the model parameter set corresponding to each substance, analyzing the synthesis center based on simulation data, and analyzing the key gene by comparing the gene sequencing results of the synthesis center / comparison area of each substance. According to the invention, the positioning accuracy of the synthesis center and the identification accuracy of key gene information can be improved.

The invention discloses a pre-operation CT and intraoperative X-ray image registration method based on meta-learning, and relates to the field of operation image registration, and the method comprises the steps: preprocessing historical pre-operation CT data; constructing a feature extraction sub-model containing a double attention mechanism to mark the region of interest, a multi-branch joint learning multi-task sub-model, and a dynamic evolution sub-model for capturing a dynamic law by means of a neural memory ordinary differential equation; training a fine registration model of the network in a coarse registration stage and a fine registration stage; and subsequently, establishing a verification set by using untrained data, comparing errors and adjusting a parameter strategy by combining three indexes of attitude estimation error, image matching accuracy and model reasoning speed, and outputting a final model for CT (Computed Tomography) of a current patient and real X-ray registration in an operation. According to the method, CT and intraoperative real X-ray image registration can be carried out on different cases through one neural network model, the generalization performance and registration precision of the model are improved, and guarantee is provided for subsequent operation of surgical navigation.

The invention discloses a critical parameter prediction method for a vertical cantilever fluid conveying pipe comprising a water injection pump and a Y-shaped nozzle, and relates to the field of fluid conveying pipe critical parameter calculation. The prediction method is based on an Euler-Bernoulli beam model and a momentum theorem, bending force, centrifugal force, Coriolis force, inertia force, gravity and additional force generated by an elbow are comprehensively considered, and an oscillatory differential equation of the fluid conveying pipe is established. The method comprises the following steps: performing dimensionless processing on an oscillatory differential equation by introducing dimensionless parameters, deducing a characteristic equation, a characteristic function and a characteristic value under a cantilever boundary condition, converting a partial differential equation into an ordinary differential equation set, and performing matrix solution; and finally, accurate prediction values of the critical flow velocity and the critical frequency can be obtained. The method can effectively reflect the influence rule of the nozzle and the concentrated mass on the vibration characteristics of the fluid conveying pipe, and realizes the accurate prediction of the critical parameters of the vertical cantilever containing the concentrated mass belt Y-shaped nozzle fluid conveying pipe.

The invention relates to the field of operation and maintenance management of Internet of Things equipment, in particular to a periodic maintenance task automatic scheduling system and method, and the method comprises the steps: firstly collecting vibration, current and environment signals, and constructing a three-dimensional digital twin map; obtaining a health index and a remaining available life in a preset window through time sequence alignment convolution and an ordinary differential equation recursive network, generating a risk coefficient through index mapping, and driving a reaction-diffusion equation to form a continuous degradation field; the scheduling optimization unit obtains an initial solution through symplectic gradient Hamiltonian-Monte Carlo sampling, and maintenance scheduling data meeting resource constraints are generated through bose sampling, topological bose evolution and dual gaming; the mixed reality terminal displays a risk hotspot and an operation instruction on site, retest data is recorded after maintenance is completed, and reinforcement learning updates a risk assessment and scheduling model on line according to an execution result to form a closed loop; according to the method, accurate quantification of risks, global optimization of scheduling and adaptive feedback of execution are realized, and the fault rate and the maintenance cost can be remarkably reduced.

The invention relates to a zero-sample speech synthesis method and device, computer equipment, a storage medium and a program product, and the method comprises the steps: obtaining a target coding feature according to a reference speech and a target text; inputting the target coding features into a stream matching model to obtain a conditional velocity field and an unconditional velocity field; inputting the target coding feature into a prior model to obtain a prior speech feature; obtaining a prior generation flow field according to the prior voice features and the standard Gaussian noise; calculating a KL divergence value between the priori generated flow field and a preset real generated flow field, and taking a moment when the KL divergence value is smaller than or equal to a preset KL divergence threshold as an initial moment of the priori generated flow field; fusing the conditional velocity field and the unconditional velocity field to obtain a fused velocity field; and inputting the fusion velocity field from the initial moment to the target moment and the priori generated flow field into an ordinary differential equation solver to obtain the target speech features, thereby improving the speech quality of the synthesized speech.

The invention discloses a stay cable analysis digital twinborn model construction method, which comprises the following steps of: constructing a stay cable space three-dimensional vibration motion partial differential equation based on a material linear elasticity hypothesis and a double-coordinate system theory, and setting boundary conditions and initial conditions of the stay cable space three-dimensional vibration motion partial differential equation; a Galerkin multi-mode truncation method is adopted to obtain a displacement function of superposition of an end displacement excitation item and a vibration mode item; deducing a three-way strong coupling ordinary differential equation set through symbolic operation, and solving by using a step-variable Runge-Kutta algorithm to obtain a stay cable analysis digital twin model with stable parameters; structural response data are obtained through the sensor network and calculated, and when the obtained cable force, flexural rigidity and damping ratio exceed threshold values, a model updating mechanism is triggered for updating; and then the updated stay cable analysis digital twin model is obtained. According to the method, the real dynamic characteristics of the stay cable can be restored with high precision, and effective support is provided for structural state evaluation and early warning.

This invention proposes a method for predicting the health status of lithium batteries based on multidimensional features and neural network constant differential equations. The method includes the following steps: S1, preprocessing the capacity data and charging stage operation data collected during lithium battery operation, and constructing features from historical health status data; S2, constructing multidimensional feature inputs for health status prediction based on the charging stage operation data; S3, inputting the multidimensional features into a gated recurrent unit network to fuse and encode the historical health status sequence and constant current charging stage features to obtain a potential feature representation characterizing the battery degradation state; S4, comparing the predicted health status value output by the neural network constant differential equation model with the corresponding actual health status value, calculating the prediction error, and evaluating the prediction accuracy. This application achieves high-precision prediction of lithium battery health status by integrating a multidimensional feature screening mechanism and a continuous-time state evolution modeling method.

The invention discloses an ultra-sparse CBCT (cone beam computed tomography) reconstruction method, system and equipment based on an ordinary differential equation, belongs to CBCT reconstruction in the field of artificial intelligence, and aims to solve the technical problem of low quality of CBCT reconstructed images. The method comprises the following steps: acquiring sample data, preprocessing the data, constructing and training a CBCT-CT nonlinear relation reconstruction model, and performing real-time reconstruction; during preprocessing, converting the three-dimensional image volume data into simulated X-ray projection data, and reconstructing the simulated X-ray projection data by adopting an FDK reconstruction algorithm to obtain an FDK-CBCT image; the CBCT-CT nonlinear relation reconstruction model comprises an encoder, a NODE module and a decoder; in the training process, the CBCT-CT nonlinear relation reconstruction model is trained through the obtained CT sample image and the FDK-CBCT image. In the reconstruction model, through continuous evolution of NODE modeling image features, the model can model a continuous evolution mapping process from a sparse low-quality image to a high-quality CT image during training, so that stripe artifacts and structural distortion do not easily exist in the reconstructed image, and the reconstruction quality is high.

The invention discloses a high-pressure water jet ground breaking depth time history prediction method, and aims to solve the problem that the change of the ground breaking depth along with time cannot be accurately reflected in the prior art. The method comprises the following steps: firstly, obtaining corresponding data of ground breaking depth and time under different conditions through a jet flow ground breaking test, and further performing inversion analysis and constructing a dynamic erosion coefficient function changing along with a dimensionless stress ratio; and then the function is embedded into an ordinary differential equation representing ground breaking dynamics, and a prediction model is established. For a new construction scene, on the premise that jet flow working parameters and soil inherent attributes are known, the model is solved through numerical calculation, and a complete prediction curve that the ground breaking depth develops along with time can be simulated. According to the method, field test requirements can be remarkably reduced, a reliable basis is provided for scheme comparison and selection and parameter optimization in the early stage of construction, and accurate prediction of the ground breaking process is achieved.

An operator learning model generator is provided for training a smooth operator learning model for predicting airflow dynamics in a room used by a controller connected to a heating, ventilation and air conditioning (HVAC) system. The operator learning model generator includes an interface circuit configured to receive a training dataset via a network connected to a simulation computer, wherein the training dataset includes solution trajectories of airflow in the room for various times series of control actions given to the HVAC system, a memory configured to store the smooth operator learning model comprising an auto-encoder and a neural ordinary differential equation, the training dataset, and training instructions for the smooth operator learning model, and a processor configured to train the smooth operator learning model stored in the memory, wherein the training instructions comprise a jerk regularization that enforces smoothness of the dynamics predicted by the smooth operator learning model.

An operator learning model generator is provided for training a smoothed operator learning model for predicting airflow dynamics in a room used by a controller connected to a heating, ventilation, and air conditioning (HVAC) system. The operator learning model generator includes an interface circuit configured to receive a training dataset via a network connected to a simulation computer, wherein the training dataset includes un-trajectories of airflow in the room for various time series of control actions applied to the HVAC system; a memory configured to store the smoothed operator learning model including an autoencoder and a neural ordinary differential equation, the training dataset, and training instructions for the smoothed operator learning model; and a processor configured to train the smoothed operator learning model stored in the memory, wherein the training instructions include jerk regularization that constrains smoothness of dynamics predicted by the smoothed operator learning model.

The invention discloses an environment-friendly gas chemical kinetics calculation method based on a physical information neural network, and the method comprises the steps: constructing an environment-friendly gas chemical reaction kinetics model, constructing a chemical kinetics ordinary differential equation set, and obtaining a corresponding single-hidden-layer physical information neural network architecture; randomly initializing the hidden layer weight and bias and keeping the hidden layer weight and bias unchanged, only setting the output layer weight as a learnable parameter, and embedding a control equation residual error and an initial condition into a loss function; dividing the time domain into a plurality of sub-domains, solving different reaction particles on each sub-domain by adopting different single-layer neural networks, carrying out hard coding on an initial value into the neural networks, taking a final value of each sub-domain after training as an initial value of the next sub-domain, and carrying out training and solving by connecting the sub-domains in series section by section; and constructing a total loss function of the neural network, and carrying out iterative updating on the weight of an output layer until a loss function value is reduced to a given threshold value. According to the method, model calculation can be more efficiently carried out in a high-rigidity multi-reaction coupling system.

The application discloses a kind of friction support friction resistance determination method and determination device, it is related to structure boundary nonlinear analysis technical field, the method includes: obtaining support maximum friction resistance and support sliding speed in set time period;Based on support maximum friction resistance, according to the relationship between friction support friction resistance and support sliding speed, establish the iteration model of friction support friction resistance that friction support friction resistance changes with support sliding speed;Based on the iteration model of friction support friction resistance, according to the change of support sliding speed in set time period, obtain the friction support friction resistance in set time period.Solved in the prior art, using WEN unit to establish first-order rigid ordinary differential equation to carry out numerical calculation, there is the problem that large calculation workload needs to be carried out step by step integration, when integration step is large, the fluctuation of friction resistance calculation result is big.

The application discloses an aero-engine RUL prediction method based on MDGODE, which comprises the following steps: (1) collecting aero-engine performance degradation data and constructing RUL labels; (2) establishing an MDGODE model, including a multi-scale autocorrelation decomposition module, a multi-scale dynamic graph structure learning module, a space-time coupling graph neural ordinary differential equation module and a multi-scale attention fusion module; (3) training the MDGODE model by using the collected aero-engine performance degradation data; (4) extracting the comprehensive space-time representation of the aero-engine performance degradation data to be predicted by using the trained MDGODE, and inputting the comprehensive space-time representation into a regressor to predict the final remaining useful life value of the aero-engine. The MDGODE has strong space-time representation capability and robustness for the complex non-stationary performance degradation process of the aero-engine, and can significantly improve the RUL prediction accuracy of the aero-engine.