252results about How to "Small scale" patented technology

The invention provides an interactive question and answer task processing method based on multi-agent cooperation and a related device, and relates to the technical field of artificial intelligence such as generative large language models and agents. The method comprises the steps of determining a to-be-solved target task according to natural language input of a user; the target task is decomposed into a plurality of sub-target tasks at least including interactive question and answer tasks, each sub-target task is correspondingly issued to each sub-target agent at least including an interactive question and answer agent, and different sub-agents are used for processing different types of sub-tasks; the interactive question-answering agent is controlled to present an interactive graphical user interface corresponding to the interactive question-answering task to the user, an answer result corresponding to the received feedback answer is presented, and the interactive graphical user interface comprises a question and an interactive answer area; an associated sub-target agent in the multiple sub-target agents is controlled to generate a corresponding associated processing result based on an answer result output by the interactive question and answer agent, and the associated sub-target agent is a sub-target agent which depends on the answer result and serves as part of task input information; and determining a target processing result corresponding to the target task based on the association processing result. Through application of the scheme, a better comprehensive task processing effect can be brought under the condition of lower comprehensive cost, especially for an interactive question and answer task in which a user needs to subjectively answer a proposed question and the effect is checked according to an answer result; the interactive questioning and answering agent provides the interactive graphical interface containing the question and the interactive answering area for the user, so that the task requirement of the user can be met more quickly in an interactive answering mode, and the task solving effect is improved.

The invention provides a time-space dynamic graph construction method and system for an engineering construction project, and relates to the field of railway tunnel engineering management.The method comprises the steps that construction data entities are extracted, and an entity set is generated; taking entities in the entity set as nodes to be added into the graph, and configuring attributes for each node; adding a relation edge for each node according to a logic structure between the construction data; adding a time label and a space label to each node so as to form a data graph; associating each entity in the data atlas with a time chain and a space chain to form a data atlas attached to the time-space chain; combining a node merging strategy and a graph neural network to optimize a graph structure; and dynamically modeling dimensional changes of entities and relationships in time by means of a time sequence diagram neural network. According to the method, the dynamic change graph of the relationship between the construction data entities is constructed, so that the spatial-temporal information and the entity relationship of each process are accurately expressed and efficiently associated, and the retrieval efficiency and the management level are favorably improved.

The invention provides an instant message inquiry type task processing method based on multi-agent cooperation and a related device, and relates to the technical field of artificial intelligence such as generative large language models and agents. The method comprises the steps of determining a to-be-solved target task according to natural language input of a user; the target task is decomposed into a plurality of sub-target tasks at least including instant information inquiry tasks, each sub-target task is correspondingly issued to each sub-target agent at least including an instant information inquiry agent, and different sub-agents are used for processing different types of sub-tasks; the instant information inquiry agent is controlled to inquire questions from the inquiry object to obtain instant feedback, and the instant information inquiry agent supports question inquiry in a background operation mode; an associated sub-target agent in the multiple sub-target agents is controlled to generate a corresponding associated processing result based on instant feedback output by the instant information inquiry agent, and the associated sub-target agent is a sub-target agent which depends on the instant feedback and serves as part of task input information; and determining a target processing result corresponding to the target task based on the association processing result. By applying the scheme, a better comprehensive task processing effect can be achieved under the condition that the comprehensive cost is lower, and in particular, an instant information inquiry task which needs to be combined with the instant information to verify whether the actual situation meets the task requirement or not and takes the verification result as instant feedback is obtained; in addition, the instant information inquiry agent also supports question inquiry (namely asynchronous task processing) in a background operation mode, so that the user does not need to stay in a session interface all the time, and other operations of the user are not influenced.

The invention discloses a treatment device and process based on zero discharge of high-concentration coating wastewater, wastewater passes through an adjusting tank and then enters a pretreatment module through a pipeline, the coating wastewater passes through a Fenton tank body, a coagulation tank body and a primary sedimentation tank of the pretreatment module in sequence through the pipeline to be treated, and the coating wastewater is continuously conveyed to a biochemical treatment module; the biochemical treatment module is used for carrying out anaerobic environment treatment through an anaerobic granular sludge bulking bed and then carrying out aerobic environment treatment through an aerobic aeration tank; and introducing the wastewater into a secondary sedimentation tank to separate the formed sludge from water, entering a biochemical tank, carrying out ultrafiltration and reverse osmosis treatment through a deep treatment module, recycling the treated wastewater to a production line, and recycling the generated condensate water and RO fresh water. The adopted wastewater treatment device is combined and optimized by various advanced technologies, so that the treatment efficiency and the water quality are improved, efficient recovery and reutilization of resources are also realized, and the system has good economic benefits and environmental benefits and is suitable for the requirements of modern coating wastewater treatment.

The invention provides a cross-regional air conditioner regulation and control strategy modeling method and a cross-regional air conditioner regulation and control method and system, and is applied to the technical field of intelligent regulation and control of air conditioners. The method comprises the steps that clustering processing is conducted on air conditioner load data of users in all regions, and a clustering result is obtained; constructing a regional cold supply system simulation model corresponding to the clustering cluster based on the users in the same clustering cluster in the clustering result; the operation safety of an actual regional cooling system is considered, modeling is carried out on the regulation and control process of the simulation model based on the Markov decision process, and an optimization strategy model is constructed by taking expected return maximization of a value function corresponding to an operation strategy of the simulation model as a target; and training an optimization strategy model based on simulation operation data of the simulation model. According to the method, the problems that in the process that the DCS participates in power grid load regulation and control, a trial-and-error training-based model is prone to system damage in practical application, and single-model regulation and control cannot guarantee the load regulation and control effect of a whole power grid are solved.

The invention provides a method for characterizing the heterogeneity of a millimeter-level shale oil and gas reservoir. The method mainly solves the problem that the reliability and accuracy of a reservoir evaluation result of an existing volume sampling method are low. The method is characterized by comprising the following steps that S1, shale millimeter-level mineral components are recognized and drilled; s2, based on the obtained powdery sample, oil-containing and non-oil-containing tests are carried out; determining occurrence pore size distribution to carry out reservoir characterization through comparison before and after pumping; s3, on the basis of the obtained powdery sample, carrying out oiliness characterization on different lamina / layered components; and S4, carrying out millimeter-level shale oil reservoir heterogeneity characterization on the basis of the reservoir property and oiliness results of the different strata / layered components. According to the method provided by the invention, the identification precision of the shale formation / stratified structure can be enhanced, millimeter-level fine representation of lithology of different formation / strata is realized, and favorable support is provided for shale oil enrichment mechanism, sweet spot prediction and the like.

The invention provides auxiliary reproduction test tube infant fertilized egg culture equipment which comprises a constant-temperature bottom box and a sealing top box covering the top of the constant-temperature bottom box in a sealing mode, a culture dish cavity is formed in the middle of the top of the constant-temperature bottom box, and a variable culture dish with a variable culture plane is arranged in the culture dish cavity; compared with the prior art, when the fertilized eggs of the test tube baby are cultured, a proper amount of nutrient solution is put into the variable culture dish in a sterile laboratory, the fertilized eggs of the test tube baby are put into the nutrient solution to be cultured, and at the moment, the middle of the culture plane of the variable culture dish is concave downwards to be in a funnel shape; the test tube infant fertilized eggs are always located in the middle of the culture plane, cells start to split along with culture, the culture plane of the variable culture dish is gradually adjusted from a funnel shape to a plane shape along with the increase of the cells, and therefore the situation that the test tube infant fertilized eggs are excessively dispersed after being split is avoided, and stacking of multiple cells can be avoided; the observation condition is influenced.

The invention belongs to the technical field of automobile production line fault diagnosis, and relates to a slide wire power supply fault diagnosis method based on causal inference and knowledge distillation, which comprises the following steps: S1, constructing a first feature model based on a deep neural network, and using a slide wire picture in an automobile production line for training the first feature model; s2, using a variational auto-encoder and the first feature model to carry out a de-confusion operation on the slide wire picture in the automobile production line, and generating an intermediate layer feature map; s3, constructing a second feature model based on the knowledge distillation technology, and training the second feature model; and S4, deploying the second feature model in edge equipment on an automobile production line, and performing carbon deposition fault diagnosis. While the model keeps high diagnosis precision, the scale of the training model can be compressed, the training model can capture correct fault features, the reliability of the output result of the fault diagnosis network model is improved, and the actual requirements of industrial production are met.

The invention relates to a network abnormal behavior detection method based on dynamic data balance and generation, and the method comprises the steps: obtaining original network flow data, inputting the original network flow data into a dynamic abnormal data balance model, and obtaining an enhanced data set; the method comprises the steps of marking original network flow data based on an abnormal data balance model, performing selective undersampling on marked data, adjusting a ratio of normal data to abnormal data, obtaining a balance data set, generating new abnormal data according to the balance data set, and merging the new abnormal data with the balance data set to obtain an enhanced data set; and inputting the enhanced data set into a TimeDiT noise reduction model for denoising to obtain a target data set after noise reduction, inputting the target data set into an LSTM-Transform weighted training model for network abnormal behavior detection, and weighting abnormal data in the target data set in combination with a weighted loss function to obtain a detection result. According to the invention, the network traffic abnormal behavior detection efficiency and accuracy can be improved.

The invention belongs to the field of machine learning and graph data mining, and relates to a consumption financial commodity recommendation method based on graph clustering of granular ball calculation. The method comprises the steps of obtaining a financial transaction network graph data set and performing information extraction on the financial transaction network graph data set to obtain graph data G; carrying out granular ball calculation on the graph data G through a self-adaptive splitting mechanism, and finally generating a plurality of granular balls; edges are added between the pellets according to the adjacency relation between the pellets, and a granulation graph is generated; constructing an objective function of a particle-sphere similarity matrix; solving an objective function of the granular-spherical similarity matrix to obtain the granular-spherical similarity matrix; performing symmetric non-negative on the particle-ball similarity matrix, and performing spectral clustering on the symmetric non-negative particle-ball similarity matrix to obtain a commodity clustering result; according to the method, transaction graph data are preliminarily covered and represented by high-quality granular balls generated through an adaptive splitting mechanism, fine-grained graph nodes are replaced by coarse-grained granular balls to perform a clustering task, global and local features are captured through multi-granularity representation, and thus rapid and accurate node clustering is realized.

The invention discloses a wind power plant fan fault prediction method based on a deep learning algorithm, and the method comprises the following steps: obtaining and inputting fan operation state data, and obtaining a matrix capable of representing the characteristics of the operation state data; reducing the data size scale of a high-frequency signal sequence generated by the fan sensor by using a box line downsampling method; aiming at the fault sequence data of the positive sample, combining prior knowledge and observation data by using a Bayesian multivariate autoregression model; for negative sample data, normal behavior sequence data is mapped to approximate posterior probability distribution of potential variables output by an encoder by using a variational auto-encoder model in combination with an attention mechanism, a decoder samples from the distribution through a re-parameterization technique, and reconstructed data similar to input data distribution is generated; a self-adaptive threshold adjustment strategy is used, and a classification decision can be dynamically optimized by automatically adjusting the threshold of positive and negative reconstruction errors. According to the method, the fan fault prediction precision can be effectively improved.

The invention discloses a VVC coding unit rapid division method and system based on image frequency domain characteristics, and the method comprises the steps: employing a first image frequency domain characteristic, a first classification label and a first weight to train a group of binary classifiers based on a lightweight gradient lifting model, and obtaining a group of initial binary classifiers; performing feature selection through the group of initial binary classifiers, and training the group of initial binary classifiers by adopting the selected features to obtain a group of dimensionality reduction binary classifiers; performing parameter adjustment on the group of dimensionality reduction dichotomous classifiers to reduce the scale of the group of dimensionality reduction dichotomous classifiers to obtain a group of division decision classifiers; initializing online sample data, and deciding the division mode in each division decision classifier according to the online sample data to obtain a group of target division modes; and quickly partitioning the VVC coding unit according to a group of target partitioning modes. According to the invention, the division efficiency and decision accuracy of the coding units are improved, the video quality and code rate are ensured, and the coding time is shortened.

The invention provides a voiceprint coding method, a voiceprint coding network training method and electronic equipment, and relates to the technical field of natural language processing, and the voiceprint coding method comprises the steps: obtaining to-be-processed audio data and target mask data corresponding to the to-be-processed audio data; the target mask data is used for representing an application intention of the to-be-processed audio data; and inputting the to-be-processed audio data and the target mask data into a trained voiceprint coding network, so that the voiceprint coding network fuses and reasones a coding result suitable for the application intention based on the to-be-processed audio data and the target mask data. According to the method and the device, the voiceprint coding network can be helped to better learn convergence, the situation that the convergence effect of non-convergence or different application intentions is some good and some bad is avoided, the same trained voiceprint coding network is adopted to generate the coding result for the to-be-processed audio data of different application intentions, the parameter scale can be reduced, and storage resources are saved.

The invention relates to the technical field of intelligent manufacturing systems, and discloses an optimal scheduling search method for a multi-robot coordinated cooperation system, which comprises the following steps of: constructing a library timing Petri net model of the multi-robot coordinated cooperation system according to a robot resource use condition and a production process procedure of the multi-robot coordinated cooperation system; constructing a state diagram under a steepest excitation strategy based on a library time-assigned Petri net model, wherein the state diagram retains an optimal state sequence corresponding to the shortest processing time; designing a state merging rule in combination with the structure information of the Petri network, removing redundant states which do not belong to the optimal state sequence, and reducing the scale of the state diagram; the optimal scheduling scheme of the system can be obtained by searching the state diagram through global search. According to the method, a timing Petri net model which effectively represents a multi-robot resource conflict relationship and a processing event logic and time relationship is constructed, and a state space containing an optimal processing event sequence is constructed and searched on the basis, so that an optimal scheduling strategy is solved.

The invention provides a table-to-text conversion method, system and device and a medium, and the conversion method comprises the steps: obtaining a first dictionary recording key query information, a to-be-converted data table and a first prompt word corresponding to the key query information; the first prompt word is used for indicating table type data corresponding to the key query information in the retrieval data table; inputting the data table and the first prompt into a language model, and obtaining target table type data through the language model; according to the target table type data, performing storage updating on the first dictionary to obtain a second dictionary; and inputting the second dictionary and a second prompt into the language model to obtain a target generated text, the second prompt being used for indicating to retrieve dictionary structure data corresponding to the key query information in the second dictionary. According to the conversion method, computing resources and reasoning time consumed by converting the table into the text can be reduced, and the generation accuracy of converting the table into the text is improved. The invention relates to the technical field of artificial intelligence.

The invention provides a user intention mining processing method and device and related equipment, and aims to solve the problem of low user intention mining efficiency when self-service voice service intelligent equipment constructs a dialogue system in the traditional technology. The user intention mining processing method comprises the following steps: obtaining an initial to-be-mined text of a to-be-mined user intention, and according to a TF-IDF value, obtaining an initial to-be-mined text of the to-be-mined user intention; the method comprises the steps of obtaining word weights of corresponding lexical units, filtering lexical unit sentence texts corresponding to the lexical units according to the word weights to obtain target lexical unit sentence texts, vectorizing the target lexical unit sentence texts, determining target lexical unit sentence text vectors, clustering all the target lexical unit sentence text vectors, and determining target user intentions according to clusters. According to the user intention mining method and device, repeated corpora and corpora low in importance degree can be removed by filtering the lexical text corresponding to the lexical, the data scale is reduced, the user intention mining efficiency and quality are improved, the user intention mining effect is improved, and the user intention mining method and device can be applied to the field of medical health.

The invention aims to provide subway crew scheduling plan optimization based on a generation-selection two-stage algorithm, relates to the technical field of urban rail transit operation plans, and divides a subway crew scheduling plan into two stages of generation and selection. For the generation stage, constructing a space-time state network, converting crew task generation into a path search problem, and designing an improved Floyd algorithm to generate large-scale alternative crew tasks; for the selection stage, an improved set coverage model is constructed, a greedy algorithm and a genetic algorithm are designed for solving, and finally verification is carried out by taking the Chengdu subway No.5 line as an example. An example analysis result shows that compared with a manual compilation scheme, the compilation method provided by the invention is remarkable in optimization effect, the total number of crew members is reduced by 14.48%, the total on-duty time of the crew members is reduced by 9.39%, and the sum of the continuing time is reduced by 15.79%.

The utility model discloses a half-piece telescopic piece taking mechanism which comprises a bottom mounting plate, a channel, a telescopic air cylinder, a connecting piece, a telescopic plate, a variable pitch winding, a conveying belt and a motor, the channel is formed in the middle of the bottom mounting plate, and the telescopic air cylinder is arranged below the bottom mounting plate along with the channel. A cylinder sliding block on the telescopic cylinder is arranged in the channel and bears a connecting piece, a telescopic plate is horizontally erected on the connecting piece, the front edge of the telescopic plate, the side face of the connecting piece and the front end and the rear end of the bottom mounting plate are provided with a left variable-pitch winding and a right variable-pitch winding which are connected through a transmission shaft in parallel, and a conveying belt is tensioned on the variable-pitch windings; and the transmission shaft is externally connected with a motor. Through the mode, the half-piece telescopic taking mechanism provided by the utility model adopts one air cylinder to simultaneously control two groups of variable pitch windings to stretch out and draw back, and adopts one motor to synchronously drive, so that the scale of equipment is reduced, the number of parts is reduced, and the cost of the equipment is controlled.

The invention discloses a micro-channel reactor and micro-channel reaction equipment, the micro-channel reactor comprises a reaction plate, a support transition plate and a heat exchange plate which are connected in a laminated manner, grooves are processed in the reaction plate to form micro-reaction channels, grooves are processed in the heat exchange plate to form heat exchange channels, and the support transition plate is separated between the reaction plate and the heat exchange plate; the micro-reaction channel comprises at least two micro-channel units and a middle flow channel connected with the adjacent micro-channel units, each micro-channel unit comprises a flow channel inlet, a flow channel outlet and a heart-shaped mixing cavity, an arc-shaped flow baffle and at least one turbulent flow column are arranged in the heart-shaped mixing cavity, the concave side of the arc-shaped flow baffle faces the flow channel inlet, and the convex side of the arc-shaped flow baffle faces the turbulent flow column. And the turbulent flow column is arranged between the arc-shaped flow baffle and the flow channel outlet. Through cooperation of the heart-shaped mixing cavity, the arc-shaped flow baffles and the turbulent flow columns, the particle suspension rate and the mass transfer capacity of the micro-reaction channel are effectively improved, then the reaction efficiency is improved, and the device can be used for achieving continuous preparation of nano-drugs.

The invention provides an intrusion detection system and method for an edge device level lightweight pruning neural network, the scheme provides a lightweight pruning strategy of a neural network, the neural network can be easily deployed on edge devices while the detection performance of the neural network is ensured by reducing the scale of a neural network model, and the detection efficiency of the neural network is improved. The computing pressure of the edge device is effectively reduced, so that the edge terminal device can autonomously detect the abnormal traffic, and the problems that the detection efficiency is low and the detection is easily influenced by a network communication environment because the detection can be carried out only by a cloud in a traditional scheme are effectively solved.

The invention relates to the technical field of particle accelerators, in particular to a compact rotary thin-wall beam transmission vacuum system and a design method. The beam transmission vacuum system comprises: a first transmission unit, one end of which is provided with a first bifurcated thin-wall dipolar iron vacuum chamber to form a first branch and a second branch; one end of the second transmission unit is connected with the second branch, and a second bifurcated thin-wall dipolar iron vacuum chamber and a third bifurcated thin-wall dipolar iron vacuum chamber are sequentially arranged in the second transmission unit to form a third branch, a fourth branch and a fifth branch; the fixed treatment terminal is connected with the first branch; and rotating the treatment terminal to provide the beam to one of the plurality of treatment rooms in an alternative manner. According to the invention, an intensive architecture that a single rotary treatment terminal provides particle beams for a plurality of treatment rooms at the same time is adopted, so that the equipment manufacturing cost is greatly reduced, the equipment utilization rate is improved, and the treatment cost is reduced.

The present application discloses an anti-influenza virus pharmaceutical composition comprising a compound of formula (I) or a pharmaceutically acceptable salt thereof or a compound of formula (II) or a pharmaceutically acceptable salt thereof, wherein R 1 and R 2 are as defined in the specification. The present application also discloses the use of the pharmaceutical composition in the preparation of a medicament for preventing or treating influenza.

The present invention relates to a highly creative patent network identification method based on semantics, comprising the following steps: acquiring a target functional patent set; extracting keywords in patent texts, taking nouns and verbs in the keywords of each patent in the patent set as concept vocabulary of the patent, and also as nodes of a semantic network in a patent semantic memory model; calculating semantic similarity of concept nodes; judging the creativity level of semantic memory: determining a semantic distance according to a path in a fully connected concept semantic network and the comprehensive semantic similarity on the path, judging the creativity level of the fully connected concept semantic network based on the semantic distance, and pruning the network based on the creativity level, thereby minimizing the scale of the concept semantic network on the basis of ensuring high creativity, and obtaining a highly creative semantic network for concept stimulation.

The embodiment of the application relates to the technical field of image processing, and discloses an image comparison method, system, electronic equipment and computer readable storage medium, the method comprising: respectively pre-processing and adaptively binarizing a test image and a template image corresponding to the test image to obtain a first image and a second image; performing target detection on the first image, respectively removing a detected target region in the first image and a region in the second image with the same position as the target region to obtain a third image and a fourth image; extracting feature points in the third image and the fourth image and performing feature point matching to determine matched feature points; performing global binarization on the pre-processed test image and the template image and performing difference processing to obtain a difference image; and obtaining an image comparison result based on the matched feature points and the difference image, so that different elements between images are efficiently identified, elements that do not need to be focused on are excluded, and the workload of a tester during rechecking is reduced.

The invention relates to the technical field of propylene dimerization catalysts, and discloses a propylene dimerization catalyst, a preparation method thereof and a method for preparing 4-methyl-1-pentene through propylene dimerization, the preparation method comprises the following steps: (1) mixing alkali carbonate, graphite fluoride, methylcellulose and potassium stearate, and carrying out molding and molding roasting to obtain a carrier; wherein the mass ratio of the alkali carbonate to the graphite fluoride to the methyl cellulose to the potassium stearate is 100: (0.5-5): (0.1-20): (0.1-30); (2) loading an active metal on the carrier; wherein the active metal is selected from sodium and / or potassium. The catalyst prepared by the preparation method has high propylene conversion per pass and high 4M1P selectivity.

The invention provides a power generation system which comprises a steam generation system and a thermal power generation system. The thermal power generation system comprises a coal-fired boiler, a steam turbine and a generator; the turbine is connected with the generator; the coal-fired boiler comprises a coal-fired boiler heating section and a coal-fired boiler reheater; the steam turbine comprises a high-pressure cylinder and a medium-low-pressure cylinder; the steam generation system comprises a heat storage module, a steam generation module and a feed water heating system; the steam generation module comprises an initial heating section and an initial reheating section. According to the technical scheme, the steam generation system is introduced into an existing or newly-built thermal power generation system, the steam generation system and the coal-fired boiler are connected in series, meanwhile, the bypass system is arranged in a matched mode, high-efficiency combination of the steam generation system and the coal-fired boiler is achieved, and compared with a pure thermal power generation system of the same scale, the scale of the coal-fired boiler is reduced; and the deep peak regulation capability and the rapid load change capability are improved.

The application provides a kind of freight data pruning method, device and equipment, method includes: obtaining freight original data, delete the data of the flight owner pruning range outside of the freight original data;Delete the data in the freight original data that is outside the owner pruning range of freight;Remaining non-airline data is stored in release area;Remaining explicit airline data is stored in non-release area;Remaining implicit airline data is stored in non-release area;Iterate non-release data, migrate non-release data to release area or waiting area;Data in the release area is stored in file as pruned data file, and released to the data preprocessing module in the freight calculation system.The size of the freight data is reduced by deleting and arranging the freight original data, so that the pruned data does not lose and is not redundant.

The invention relates to a YOLO v3 post-processing hardware acceleration method based on a look-up table method, which comprises the following steps of: 1) establishing two look-up tables according to two operators of sigmoid and exp functions involved in a decoding calculation process; 2) analyzing the required storage space according to the quantization bits and the network structure; 3) distributing a corresponding BRAM storage block for the lookup table according to the required storage space; 4) calculating the data to be decoded, and putting a calculation result into a lookup table; 5) inputting to-be-decoded data, putting the to-be-decoded data into the cache unit, and arranging the to-be-decoded data; 6) reading data to be decoded, and searching corresponding calculation data from the lookup table; 7) inputting the calculation data into a parallel calculation unit to obtain decoding data; and 8) putting the decoded data back to the initial position in the cache unit. According to the method, the lookup table is established, the to-be-decoded data in YOLO v3 post-processing is subjected to decoding calculation, post-processing calculation is completed under the condition that few storage resources are used, the hardware scale is remarkably reduced, and the post-processing efficiency is improved.

The present invention discloses a distributed collaborative reliability method for a multi-failure structure based on subject decomposition, which is applied to the field of aircraft engine reliability technology. The method comprises the following steps: first, the various failure modes of the multi-failure structure are disassembled according to the subjects to which they belong, the response analysis of a single subject is carried out, and a distributed proxy model of the response of each subject is established; then, the response of each subject is extracted in linkage by using the collaborative sampling technology, and the distributed collaborative reliability analysis of the multi-failure structure is completed by using the established distributed proxy model; finally, the reliability analysis results of the multi-failure structure are imported into the Copula correlation model, and the correlation between multiple failure modes is evaluated by simulation results. Compared with the prior art, the present invention combines the distributed collaborative proxy model based on subject decomposition with the Copula function that can quantitatively quantify the correlation, which not only accurately quantifies the failure correlation between each failure mode, but also ensures high calculation accuracy and efficiency.