8311 results about "Aero engine" patented technology

A multi-scale hybrid attention mechanism modeling method for aero-engine remaining useful life prediction belongs to the field of health management and prediction technology for aero-engines. Firstly, preprocess the data to obtain the sample, set the RUL label, and obtain the true value of the remaining useful life of the sample. Secondly, a multi-scale hybrid attention mechanism model consisting of position encoding layer, feature extraction layer, and regression prediction layer is constructed. Thirdly, train the model, and make the difference between the predicted value output by the model and the true value of the remaining useful life by minimizing the loss function until it reaches the stop standard. Finally, use the trained model to predict the remaining useful life. The method can achieve full fusion of information from different time steps of a single sample, taking into account the correlation between all samples.

An aero-engine augmented reality virtual-real fusion method based on depth prior scene reconstruction comprises the following steps: firstly, collecting data of an aero-engine look-around RGB image and a depth image, calculating a camera frame pose by using an SFM algorithm and obtaining a sparse point cloud, and optimizing the camera pose by using an ICP algorithm and the point cloud converted from the depth image to obtain an aligned prior dense point cloud; gaussian points are initialized based on the priori dense point cloud and the sparse point cloud, and random generation of 3D Gaussian is limited by using the boundary of the dense point cloud as geometric constraint; through the three-dimensional reconstruction of the adjacent multi-view enhancement strategy, the spatial and visual consistency is improved, and an aero-engine model is reconstructed; then understanding the reconstructed aero-engine model based on semantic segmentation, identifying and marking core components, and finally performing virtual-real fusion visualization on the reconstructed aero-engine through augmented reality to guide training, assembling and maintenance operations. According to the invention, rapid high-quality three-dimensional reconstruction and augmented reality virtual-real fusion visualization of the aero-engine are realized.

The invention relates to an aviation turbine blade service damage monitoring method based on digital twinning, belongs to the technical field of aero-engines, and solves the problems that an existing detection algorithm is high in calculation complexity and low in efficiency and precision. Determining a to-be-monitored turbine blade physical entity, and collecting turbine blade environment information; a digital twin is constructed on the basis of a physical entity, the turbine blade three-dimensional model construction module constructs a turbine blade three-dimensional model according to the physical entity, and the turbine blade operation environment simulation module performs environment simulation on the model according to real-time load, rotation speed and environment temperature data of a turbine blade. And the turbine blade defect evolution prediction module identifies blade surface defects of the model at each moment by using an intelligent defect detection algorithm to obtain the category, position information and size information of the defects, and performs evolution simulation and danger coefficient analysis. According to the invention, real-time on-line, high-precision and high-efficiency detection of the surface defects of the aviation turbine blade is realized, and the service life of the turbine blade is prolonged.

The invention provides an aero-engine state monitoring method and device based on sound and vibration fusion and a computer readable storage medium, and relates to the technical field of aero-engine state monitoring. The method comprises the following steps: acquiring signals respectively acquired by a vibration sensor and a sound sensor; respectively intercepting a vibration signal low-frequency component and a sound signal high-frequency component based on the frequency response characteristic difference of the sensor; performing normalization processing on the intercepted signal to eliminate amplitude difference; constructing a transition region through an interpolation method, and splicing the continuous mixed frequency spectrum to obtain a sound-vibration fusion spectrum; and establishing a health benchmark based on the normal state fusion spectrum, and realizing abnormity monitoring and alarm through characteristic difference analysis. Advantages and characteristics of a low-frequency band of the vibration sensor and a high-frequency band of the sound sensor are fully utilized, frequency response limitation of a traditional single sensor is broken through, deep fusion of sound and vibration signals is achieved, the effective detection frequency range is remarkably widened, and accuracy and robustness of recognition of early faults such as aero-engine blade breakage are improved.

The invention relates to the technical field of simulation model optimization, and discloses an aero-engine model Bayesian optimization method for quantizing uncertainty, and the method comprises the steps: building a probability mapping relation from a component index to an output response through constructing a Bayesian neural network agent model based on a probability weight coefficient; and by taking the difference between the output response and the corresponding complete machine test data as a multi-objective loss function and taking the minimization of the multi-objective loss function as an optimization objective, optimizing the component indexes by adopting a Bayesian optimization method based on a Gaussian process to obtain an optimal component index combination. Not only is a nonlinear relationship between high-dimensional parameters and simulation-test deviation accurately modeled through a neural network, but also efficient search of a parameter space is realized through a Gaussian process. The technical problems that when a traditional optimization method is used for processing the high-dimensional, strong-nonlinearity and multi-parameter coupling complex optimization problem of the aero-engine, the calculation efficiency is low, local optimum is prone to occurring, and result uncertainty cannot be quantified are solved.

The invention relates to the technical field of aero-engine welding, in particular to a clamp and method for a combustion chamber casing welding mounting base. The clamp comprises a bottom plate and a positioning ring arranged on the top surface of the bottom plate; a positioning spigot is formed in the top surface of the positioning ring and is used for positioning an inner hole of a flange edge at the lower end of the combustion chamber casing; a plurality of pressing hooks are uniformly distributed on the positioning ring close to the edge; a plurality of supporting columns are arranged on the top face of the bottom plate, and a jacking air injection device is arranged on the top of each supporting column and used for jacking an inner molded surface, corresponding to the welding portion of the mounting base, of a barrel of the combustion chamber casing and injecting inert gas to the inner molded surface of the jacking portion. By means of the clamp and the method, deformation of the combustion chamber casing welding installation base is effectively controlled, the stability of the product welding quality is improved, the welding clamp is easy and convenient to operate, the welding method is efficient, and the labor intensity of operators is relieved.

The invention discloses a rapid simulation method for infrared radiation characteristics of an aero-engine exhaust system based on a radial basis function neural network, and belongs to the technical field of aero-engines. The method comprises the steps of establishing an aero-engine exhaust system geometric model; flow field calculation is carried out, and aero-engine exhaust system infrared radiation characteristic simulation flow field parameters are obtained; calculating intrinsic infrared radiation characteristics of the aero-engine exhaust system; calculating the infrared radiation characteristics of the coupling background environment infrared radiation and the atmospheric effect of the aero-engine exhaust system; constructing a nonlinear association database; and training the RBF neural network model to obtain the RBF neural network-based aero-engine exhaust system infrared radiation characteristic rapid simulation model. According to the method, the remarkably improved calculation precision and the abundant and clear distribution details of the infrared radiation brightness are replaced by the acceptable additional calculation amount.

The invention discloses a thermal barrier coating multi-dimensional terahertz nondestructive testing method and system based on an adaptive optimization mechanism, and the method comprises the steps: constructing a matrix sample library, and preparing thermal barrier coating samples with different thicknesses, porosities and uniformity; obtaining terahertz detection data of three dimensions of geometric dimension stability, microstructure integrity and material structure uniformity of the thermal barrier coating; establishing a multi-parameter correction model based on surface roughness, and performing feature extraction, fusion analysis and error compensation on the detection data by adopting a multi-modal integration algorithm; an adaptive optimization model is established through a deep learning algorithm, and continuous iterative optimization of the detection system is realized in combination with a feedback correction mechanism; the method is applied to an engine blade thermal barrier coating, an actual blade coating is detected, detection data are collected for system optimization, system parameters and models are updated, and system applicability and robustness are improved. The method can be widely applied to the field of nondestructive testing of coating structures such as aero-engine blade thermal barrier coatings.

The invention belongs to the field of aero-engine bearings, and provides a method and system for predicting the remaining service life of an aero-engine bearing, and the method comprises the steps: carrying out the processing of an original vibration signal collected in the operation process of the engine bearing through a Pearson correlation analysis method, carrying out feature extraction to obtain a plurality of feature sequences of common bearing RUL prediction statistics; smooth processing and cumulative transformation are carried out on the statistical feature sequence, monotonicity and tendency values are calculated, screening is carried out, and a screened cumulative feature sequence is obtained; and inputting the screened accumulated feature sequence into an attention full convolutional network (AFCN) model based on physical information to predict a life ratio, and calculating a residual service life prediction value through the life ratio. According to the method, through the full convolutional network fusing the bearing physical degradation mechanism and the attention mechanism, the key feature capturing capability and prediction precision in the long-time-sequence degradation process are improved, and technical support is provided for safe operation and maintenance of an aero-engine.

The invention discloses an aero-engine control system and method based on self-adaptive specified interference cancellation, and belongs to the field of aero-engine control. A disturbance affine form nonlinear mathematical model of an aero-engine is obtained through system identification, a fixed-time disturbance observer is designed to estimate the lumped interference of the system in real time, and the disturbance of the aero-engine is estimated in real time; and a self-adaptive specified interference elimination composite controller is constructed based on a nonlinear backstepping method and a dynamic inverse method, so that accurate control on the rotating speed of the engine is realized. The system adjusts the control quantity in real time based on a backstepping method and a dynamic inverse method, and the controller adopts a non-smooth instruction filter and a self-adaptive dynamic weight distribution mechanism, so that the uncertainty of the system is effectively compensated. The method can effectively cope with uncertainty caused by system parameter perturbation, unmodeled dynamics and external load fluctuation, gives consideration to dynamic and static performance, has high control precision, good anti-interference capability and closed-loop stability, and is suitable for aeroengine rotating speed control under complex working conditions.

A front engine attachment system for an engine having an engine pylon with a nose having a male clevis and a cylindrical stud, two links that are fastened to the engine by a second ball-joint connection about a second axis, a first shaft establishing a first ball-joint connection of the links to the male clevis about a first axis, wherein the first axis and the second axis are in the same vertical plane, and wherein the cylindrical stud is mounted so as to be able to move, via an annular linear connection, with respect to the front casing.

The invention relates to the technical field of aero-engines, and discloses an automatic design method for aero-engine turbine blades, which analyzes design requirements through a language large model, combines a retrieval enhancement technology and a turbine blade expert knowledge base, performs interdisciplinary coupling verification by utilizing a step-by-step reasoning template, and generates and optimizes part design schemes and parameters. And then calling parametric modeling and an AI simulation agent model to carry out multi-physics field prediction, comparing a result with a requirement, if the result meets the requirement, outputting design, otherwise, automatically iterating and adjusting parameters until the parameters reach the standard or reach the maximum number of iterations. According to the method, end-to-end intelligent closed-loop design from design requirements to design results can be realized, manual intervention is reduced, a design scheme meeting performance requirements can be quickly generated, the design efficiency can be improved, the design cost can be reduced, and the design quality can be improved.

The invention discloses a physical information fused aero-engine residual life prediction method, and belongs to the field of neural network residual life prediction. The method comprises the following steps: acquiring sensor data of the whole process from engine simulation operation to fault, and performing standardization and windowing preprocessing; establishing a time-space dual-channel multi-layer perceptron model, extracting time dimension and feature dimension information of the signal, performing self-attention fusion with original data, completing mapping to a life prediction value, and calculating an error with a real life; establishing a physical information neural network model, learning a hidden partial differential equation among a predicted life value, time and a hidden state, and performing error calculation with an equation in an equilibrium state; and performing self-attention fusion with the life error to obtain comprehensive loss so as to continuously train the model until the error is minimum, and finishing final life prediction. Physical information is fused on the basis of the multi-layer perceptron, the complexity of the model is simplified, and the prediction precision of the residual life of the engine is improved.

The invention provides a DLH-IHBA-based adaptive cycle engine control law optimization method, and belongs to the technical field of aero-engine control, and the method comprises the steps: building an adaptive cycle engine model, and determining an optimization variable based on the adaptive cycle engine model; according to the control mode of each self-adaptive cycle engine, constraint conditions and an objective function based on optimization variables are determined, the control modes comprise a steady state control mode and a transition state control mode, and the steady state control mode comprises a minimum fuel consumption control mode, a maximum thrust control mode and a minimum turbine front temperature control mode; and based on the objective function and the constraint condition, optimizing the control rule of each control mode by adopting a multi-dimensional learning prey strategy fused with a badger optimization algorithm to obtain an optimal control variable, and adopting Tent mapping as initial particle swarm position mapping. According to the scheme, the convergence speed of engine control rule optimization is increased, and the optimization effect and the engine performance are improved.

The invention discloses a tenon morphology contour detection method and a contour tolerance, tooth pitch and cross-rod distance evaluation method in the technical field of aero-engine turbine blade detection, and the method achieves the spatial scanning of the tenon morphology contour through a four-axis coordinate device and a confocal spectrum sensor, collects data points, and can achieve the non-contact detection of the tenon morphology contour. The actual contour of the appearance contour of the tenon is obtained, the detection efficiency is higher, meanwhile, the surface of the tenon cannot be damaged, high-precision and high-efficiency detection of the appearance contour of the tenon is achieved, and the defects that current tenon measurement adopts manual operation, precision is not high, and digitization cannot be achieved are overcome. The detection requirements of large size curvature, high precision and complex evaluation parameters of the blade tenon of the aero-engine can be met at the same time.

An aircraft engine (10) has: a turbine (15) including a turbine rotor (15C) rotatable about a central axis (A); a scroll case (20) having an inlet (22) fluidly connected to a source of combustion gases and an outlet (23) fluidly connected to the turbine (15), and a conduit (21) extending around the central axis (A) from the inlet (22) to the outlet (23), the conduit (21) spiraling towards the central axis (A); a bearing housing (30) extending around the central axis (A); an exhaust case (15B) disposed downstream of the turbine (15); and a turbine support case (40) secured to the bearing housing (30; 130) and to the exhaust case (15B), the turbine support case (40) having spokes (44) distributed around the central axis (A) and extending along a direction having an axial component relative to the central axis (A), the spokes (44) extending through the conduit (21) of the scroll case (20) and radially supported by the bearing housing (30).

The invention provides an aero-engine wide-range component performance self-adaptive correction method and device, and the method comprises the steps: building an aero-engine component-level nonlinear model according to the aero-thermal characteristics of components of an aero-engine; a component characteristic self-adaptive correction factor is introduced to adjust the model performance, matching of a model simulation result and a target measurement parameter is taken as an optimization target, and component performance matching is converted into a self-adaptive optimization problem; establishing a curved surface fitting database, and constructing an adaptive correction factor curved surface fitting model through a moving least square method; the characteristics of the model component are adjusted through the self-adaptive correction factor curved surface, so that the output result of the aero-engine component-level simulation model is kept consistent with the measurement parameters under the large-range working condition, and the large-range correction of the component characteristic diagram is realized. According to the method, the simulation output of the corrected model can be kept consistent with the target engine within a large working condition range, and the deviation degree of the actual characteristics can be accurately represented through the self-adaptive correction result.

The invention discloses an engine residual service life prediction method and system based on space-time state selection, and belongs to the field of equipment residual service life prediction. According to the method, multiple technologies such as a time sequence-space double-branch coding and hierarchical fusion mechanism, a selective state space model, a cross-layer residual jump connection and parameter sharing mechanism and an efficient self-attention mechanism are integrated, and an STSSFormer network model is constructed to predict the residual service life of the aero-engine; the system mainly comprises a data selection and preprocessing module, an input sample construction module, a model training module and a residual service life prediction module. According to the method, the feature expression and fusion capability is comprehensively enhanced, and the method has remarkable advantages in the aspects of prediction accuracy of the remaining service life, model robustness and engineering practicability.

The invention discloses an aero-engine group health evaluation method based on multi-working-condition dynamic clustering, and belongs to the field of aero-engine health state evaluation. The method comprises the following steps: firstly, carrying out clustering analysis on set parameters in engine operation data, and carrying out merging processing on small-scale abnormal clusters to obtain a working condition category division result; secondly, constructing a health baseline data set, carrying out standardized preprocessing on sample data in a working condition category division result, and carrying out nonlinear dimensionality reduction to obtain a low-dimensional feature data set; thirdly, performing clustering analysis on the low-dimensional feature data set by adopting a Gaussian mixture model, and calculating an average mahalanobis distance between a sample of each clustering category and a health reference center to obtain multi-level health levels corresponding to different clustering categories; and finally, through fusing the membership soft probability and the sample individual mahalanobis distance, constructing a continuous health score and obtaining a health grade determination interval. According to the method, health state characteristics under different working conditions can be effectively identified, individual difference modeling and group transverse comparison evaluation are supported, and the accuracy is improved.

The invention discloses a gas compressor blade mean camber line design method, a gas compressor blade, a gas compressor and an aero-engine, and the method comprises the steps: S1, obtaining known design data, including an inlet blade angle theta in, an outlet blade angle theta out, a mean camber line starting point coordinate, a mean camber line end point abscissa, and turning angles delta theta 1, delta theta 2 and delta theta 4 of a first section arc, a second section arc and a fourth section arc, and abscissas of all tangency points; and S2, each section of arc is calculated through a geometric analysis method, a mean camber line is constructed after circle center coordinates, arc radiuses and tangent point coordinates of each section of arc are calculated, and the mean camber line is formed by sequentially and tangentially connecting four sections of arcs according to the sequence of convex, concave, convex and concave. The gas compressor blade mean camber line design method is good in adaptability and multiple in controllable point in the high Mach number state; therefore, the requirements of an advanced compressor are met; design parameters are greatly reduced, the optimizing period is greatly shortened, the adjusting efficiency is high, and the time is short.

The invention relates to a turbine blade global temperature field reconstruction method based on a multi-modal physical constraint network, and belongs to the technical field of aero-engine thermal management. Aiming at the problems of insufficient global heat conduction path modeling, lack of physical rules and blank region differentiation perception, carrying out normalization and position coding on sparse temperature measurement points to form a Transform encoder input sequence; extracting features through an encoder and compressing the features into global feature vectors through self-attention pooling; decoding the image into a temperature field image by adopting a U-Net generator fused with jump connection; a multi-scale discriminator is constructed, a semantic weighting mechanism is introduced, and differentiated weights are distributed to cooling holes, tenons and pressure surface areas; a physical constraint loss and local energy conservation loss are constructed based on a heat conduction equation, and a weighted training model is combined with confrontation loss and temperature error loss. The method is used for providing high-precision temperature distribution data support for turbine blade structure optimization design, cooling system efficiency evaluation and thermal fatigue prevention.

The invention discloses an intelligent aero-engine bearing fault migration diagnosis method based on multi-source data and an attention mechanism, and the method comprises the steps: automatically learning the importance difference of different modes in different fault states through an attention weight, and achieving the dynamic optimization combination of mode features; meanwhile, an attention mechanism is utilized to capture deep correlation characteristics among multi-modal data of the aero-engine bearing part, space-time coupling relations among heterogeneous signals such as vibration, temperature and current are excavated, and an attention weight is utilized to automatically suppress modal contribution polluted by noise, so that noise robustness is enhanced; according to the method, the weight difference under different modes and different fault states can be automatically learned, the deep correlation of the modes is captured, the noise pollution is inhibited, and the robustness of the model is enhanced.

The invention discloses an aero-engine residual service life prediction method, belongs to the field of aero-engine residual service life prediction, and aims to solve the problems of an existing aero-engine RUL prediction model. According to the method, prediction is carried out through a parallel space-time Transform model, and the parallel space-time Transform model comprises a time attention module TAM, a space attention module SAM, a space-time feature fusion device and a support vector machine MLP; the TAM and the SAM are arranged in parallel, and input samples are respectively input into the TAM and the SAM; obtaining a time sequence enhancement feature through TAM; obtaining spatial enhancement features through SAM; fusing the time sequence enhancement features and the spatial enhancement features by using a spatial-temporal feature fusion device; and the support vector machine MLP predicts the remaining service life of the aero-engine according to the fusion features output by the spatial-temporal feature fusion device.

A spatiotemporal dynamic system soft measurement method for automatically determining a partial differential equation structure, belonging to the technical field of the soft measurement of neural networks. The method comprises: first, constructing a loss function used for training a coupled physics-informed neural network having a recurrent prediction mechanism, so as to obtain solutions and source items that meet a partial differential equation used for describing a spatiotemporal industrial process; second, using an automatic differential method to obtain a differential operator candidate library, and selecting an appropriate partial differential equation structure from the differential operator candidate library to accurately describe the spatiotemporal industrial process; and finally, using a heat diffusion phenomenon and an actual vibration process to verify a soft measurement result. The CPINNRP-AIC provided in the present invention is applicable to a soft measurement method for multiple types of dynamic systems having spatiotemporal dependency features, comprising a heat diffusion phenomena in an actual industrial process, a fluctuation phenomena in an actual vibration process, etc. The present invention can realize the effective acquisition of key variable values during the operation of high-end complex equipment, such as an aero-engine, thereby providing assurance for a good control performance and safe operation stability of high-end industrial equipment, and has practical engineering application significance.

The invention discloses an aero-engine system demand servitization collaborative management method, which comprises the steps of constructing a semantic mapping rule of an aero-engine demand document based on an OSLC specification, and converting an unstructured document into a standardized data model; standardized access of elements in the demand document is achieved through resource identification and a servitization interface, and a Web-based demand document interoperation mechanism is constructed; multidisciplinary collaborative design is carried out based on a demand document interoperation mechanism, and a demand document is updated in real time to form a complete design demand document; constructing an intelligent change analysis mechanism based on project tracking to realize multi-version comparison and change propagation path visualization of the design requirement document; constructing a fine-grained version evolution and conflict management mechanism based on the demand entry influence network, and executing demand version merging and conflict automatic detection in a parallel development scene; according to the method, aero-engine system demand document entry level collaborative editing and standardized service interface can be realized, and the development efficiency is remarkably improved.

The invention belongs to the technical field of material surface plating, and particularly relates to an aero-engine blade and a preparation method thereof. According to the preparation method, the component nano silicon carbide of the blade material is subjected to modification treatment, meanwhile, the carbon fiber composite material is introduced for common use, and the composite coating is formed on the surface through spraying treatment, so that the aero-engine blade is prepared, the cold and heat cycle resistance is effectively improved, and meanwhile, good erosion resistance is obtained.

The invention provides an aero-engine small sample fault diagnosis method for agency attention enhancement diffusion, and belongs to the technical field of aero-engine gas circuit fault diagnosis. According to the method, the proxy attention is added on the basis of the DDIM, so that the sample generation can be accelerated, the sample generation quality is obviously improved, and no extra training is needed. Inputting a small amount of pre-processed collected sensor signal data into the agent attention enhanced denoising diffusion implicit model for data enhancement to generate high-quality sample data so as to make up for the deficiency of an original data set and improve the performance of the model under the condition of scarce data; the expanded data set is used as a training set, the original data set is used as a test set for model training, the test set is used for testing the performance and accuracy of the model after training is completed, and a final aero-engine fault diagnosis model is established. According to the method, the problem of insufficient data in fault diagnosis is solved, and the accuracy and robustness of the model are improved.

The invention belongs to the technical field of intelligent fault diagnosis, and discloses an aero-engine bearing fault diagnosis method based on clustering enhancement domain generalization. Firstly, a time domain vibration signal is converted into frequency domain representation through fast Fourier transform, a two-stage convolutional neural network architecture comprising a domain alignment encoder and a classification encoder is constructed, and cross-working-condition feature alignment under adversarial training is realized by using a domain discriminator; introducing a multi-source domain maximum mean difference statistical alignment strategy and a clustering enhanced triple loss mechanism, and synchronously optimizing intra-class feature compactness and inter-class separability through pseudo label clustering center anchoring and dynamic interval constraint; and gradient inversion adversarial training and multi-modal feature fusion are combined. The method provided by the invention can effectively improve the accuracy and robustness of generalization judgment when the aero-engine bearing fault diagnosis lacks target domain data.

The invention discloses an aero-engine missing value filling method based on multi-scale time sequence and attribute feature extraction. Firstly, for data collected by each sensor of an aero-engine, a temporary replacement value of a missing value is generated by adopting linear interpolation; extracting a plurality of significant cycles of the aero-engine sequence data as a time scale, decomposing the sequence into trend terms and season terms according to the significant scale, and splicing all the trend terms and season terms in the time dimension; then, in-scale and inter-scale time sequence dependence is captured in a time dimension by using cross-scale graph convolution so as to carry out missing value filling in time sequence. In the attribute dimension, local neighborhood information is accumulated by adopting a cross-attribute graph volume, global attribute features are calculated by utilizing a relational network, node features are updated, and attribute association is supplemented on the basis of a time sequence filling result. And finally, aggregating the node features of a specific scale through a maximum pooling layer to represent the features, and calculating by adopting two linear layers and an activation function to obtain a final filling result.

The invention belongs to the technical field of aero-engine state monitoring and intelligent fault diagnosis, and discloses a multi-modal information fusion bearing fault diagnosis method based on self-supervised learning. The method comprises the following steps: firstly, through mask reconstruction self-supervision pre-training, extracting stable feature representation insensitive to mask disturbance from an unlabeled multi-modal signal, and dynamically updating each modal feature reference point by using an index moving average algorithm; in a downstream fault diagnosis task, a multi-modal joint decision model comprising a pre-training encoder, a single-modal classifier and a fusion classifier is constructed, and adaptive weighted fusion of multi-modal decision is realized through contribution degree calculation based on a cooperative game Shapley value in combination with a deviation degree of modal features and a reference point. According to the method, the dependence of the deep neural network on fault labeling data is effectively reduced, the accuracy and robustness of the diagnosis system in a multi-modal signal diagnosis scene are improved through a dynamic fusion mechanism, and the method is suitable for industrial scenes with limited sample label resources.