329 results about "System level" patented technology

The invention discloses an automatic scheduling method and system for ship unloading equipment, and relates to the technical field of port automation. According to the method, a high-precision digital twinborn model for ship unloading operation is constructed, physical equipment is abstracted into a digital intelligent agent with an autonomous decision-making capability, real-time multi-dimensional data and historical data are utilized to perform deep fusion to drive system synchronization, and a future multi-step scheduling strategy is deduced in a parallel simulation manner in a virtual space based on rolling time domain control, so that the real-time multi-dimensional data and historical data are subjected to real-time multi-dimensional data synchronization driving system synchronization is realized. Dynamic evaluation and optimization are carried out by adopting a multi-objective evolutionary algorithm combined with a cooperative game mechanism, and conflicts and cooperation among equipment are effectively coordinated by defining an individual utility function and introducing cooperative game negotiation and a meta-controller to dynamically adjust target weights, so that system-level global optimal scheduling is realized under multiple objectives of efficiency, energy consumption, safety and the like, and the scheduling efficiency is improved. The intellectualization, the self-adaptability and the comprehensive operation benefit of port ship unloading operation are comprehensively improved.

The invention provides an energy storage battery state simulation and prediction system and method based on digital twinning, and aims to solve the problems that an existing energy storage system is inaccurate in state modeling, insufficient in sensing granularity, unexplained in prediction, lagged in response and the like. According to the method, an equivalent thermal model, an electrochemical model and an aging mechanism model are adopted for modeling a battery, and a self-adaptive gating parameter fusion mechanism and data characteristics are introduced, so that cross-scale state mapping and characteristic reconstruction from a battery cell to a system level are realized; generating a baseline trajectory by using an electric-thermal-aging coupling relationship, realizing multi-time-domain closed-loop prediction by combining a data-driven residual correction mechanism, and identifying potential faults and risks in advance through a multi-time-domain anomaly judgment system; and constructing a three-dimensional topology model to dynamically display the state parameters, generating a graded alarm signal and providing operation suggestions. The system constructed by the invention has high precision, interpretability and prediction and visualization capabilities, and can significantly improve the intelligent operation and maintenance level of the energy storage battery system.

The invention relates to the technical field of chip testing, and discloses a clock reset system-level verification method and device based on general verification methodology, and the method comprises the steps: firstly analyzing a clock topological relation defined in a system control unit architecture document, and generating a clock reset information table; on the basis of the information table, an executable verification environment component and a virtual interface component are automatically generated through a script, the verification environment component comprises an excitation forwarding and processing component and can generate clock and reset signals matched with framework definition, and the virtual interface component can generate actual clock and reset waveforms; and finally, constructing a verification platform based on the components, calling the excitation sequence in the parameterized test sequence library, and carrying out system-level clock reset verification on the digital chip. And meanwhile, the parameterized test sequence library supports flexible adjustment of a verification scene and ensures that a test case fits a clock frequency defined by an architecture document, and a reset mechanism can improve the efficiency, accuracy and reliability of digital chip clock reset system-level verification.

The invention discloses a multi-unmanned-aerial-vehicle cooperative hoisting method and system, and the method comprises the steps: firstly, enabling each unmanned aerial vehicle to operate an extended state observer, regarding internal and external disturbances (such as airflow, unknown load parameters, internal coupling force and the like) as a lumped disturbance, and carrying out the real-time estimation; and then, through a communication network operation consensus algorithm between the unmanned aerial vehicles, fusing the local disturbance estimation values of the unmanned aerial vehicles into a global consistent system-level disturbance estimation. And finally, each unmanned aerial vehicle actively counteracts the influence of disturbance by using the accurate disturbance estimation value in a feedforward compensation controller, and accurately tracks the respective target trajectory in combination with feedback control. According to the method, active observation of disturbance, distributed fusion and feed-forward compensation are combined, dependence on an accurate system dynamic model is eliminated, and trajectory tracking accuracy, stability and stability of the system in a complex environment are remarkably improved.

The invention discloses a cable-stayed bridge cross brace optimization system based on system reliability and an intelligent algorithm, which relates to the technical field of bridge engineering, and comprises a multi-source parameter input module used for collecting and processing data such as a main beam section, stay cable parameters, a strain sequence, a vibration sequence, a satellite cloud picture, a traffic monitoring flow, laser point cloud and the like; and outputting the structured design data, the monitoring data flow, the dynamic load spectrum, the probability distribution model and the construction error correction parameters. According to the invention, all-dimensional data such as design, monitoring, load, materials and construction errors are integrated through the multi-source parameter input module, and multi-level and dynamic reliability evaluation is carried out on the component, the subsystem and the system level by using the system reliability analysis module, so that the component failure probability, the system reliability index time sequence and the like can be output; therefore, the real reliability level of the cross brace of the cable-stayed bridge in the whole life cycle is reflected more accurately, and the one-sidedness of a traditional method is avoided.

The invention relates to a four-body coupling vehicle base vibration noise prediction optimization method and system, and relates to the technical field of rail transit operation and maintenance optimization, and the method comprises the steps: obtaining a vehicle base multi-physics field correlation monitoring data set; carrying out system level assembly in a multi-physics field co-simulation environment to generate a coupled system state parameter matrix; generating sound ray bending trajectory data; loading the vehicle operation condition time sequence data to a wave equation solver, and outputting vibration noise propagation characteristic field distribution data; building a network topology structure to form a prediction model, and executing a back propagation algorithm to train network parameters to a convergence state; designing a vehicle scheduling scheme chromosome coding structure to generate a candidate solution population; and performing selection, crossover and variation genetic operations on the primary solution set, and outputting a vehicle base operation and maintenance scheduling real-time optimization scheme. The method has the beneficial effects that the precision and generalization ability of vibration noise prediction in the future time period are greatly improved, and the fundamental transformation from passive vibration isolation treatment to active prediction optimization is realized.

The invention relates to the technical field of calculation, and discloses a slag metal recovery process optimization method based on digital twinning, which comprises a data acquisition module, a data driving model construction module, a digital twinning construction module, a synchronous operation module, an online calibration module, a simulation optimization module, an online operation module and a model self-learning module. According to the method, through prospective simulation optimization, the recovery rate of each batch of materials is directly pushed to the theoretical limit; cost reduction and benefit increase are realized from the system level through a hybrid model and multi-objective optimization; through digital twin and automatic execution, process standardization and intelligent control are realized, and the stability and consistency of product quality are significantly improved. By adjusting model parameters and process constraints, smelteries with different scales and different raw material sources can be rapidly adapted, universality is high, standardization and productization are easy, and the method has high commercial expansion potential and huge market space.

The invention relates to the technical field of supply chain risk management, and particularly discloses a comprehensive risk early warning method and system fusing a supply chain graph and machine learning, and the method comprises the steps: collecting supply chain multi-modal heterogeneous data and prior risk knowledge, dynamically constructing and updating a sequential supply chain knowledge graph, and carrying out the early warning of the risk of a supply chain. Performing node-level, edge-level and system-level multi-level anomaly detection, generating an anomaly score and a network vulnerability index, when the anomaly score exceeds a dynamic threshold value, deducing risk propagation and node sweep probability by improving an SEIR model, calculating a dynamic fusion weight in combination with data source authority and the like, and performing weighted fusion on multi-dimensional indexes to generate a comprehensive risk score, and dynamically adjusting a threshold value to generate graded early warning, an optimization model, a map and a priori knowledge base. According to the method, the defects of lag, isolation and stiffness of a traditional method can be overcome, risk perception in advance, comprehensive coverage and accurate early warning are achieved, the method has the self-evolution capacity, the method adapts to dynamic changes of a supply chain, and powerful support is provided for safety and stability of an industrial chain.

The invention discloses a laser wireless energy transfer dynamic MPPT control method based on an RL-PSO hybrid algorithm and a reconfigurable array system, and aims to solve the problems of power oscillation and mismatch loss caused by light spot offset of a photovoltaic array under laser dynamic irradiation. According to the method, reinforcement learning (RL) and particle swarm optimization (PSO) are fused, dynamic parameters such as the light spot moving speed and irradiance are sensed in real time through the RL, the inertia weight and learning factors of the PSO are adjusted in a self-adaptive mode, and collaborative optimization of global search and local tracking is achieved. According to the system level, a reconfigurable photovoltaic array is designed, and according to data of a light spot position sensor, battery series-parallel topology is dynamically adjusted through a switch matrix, and current matching is optimized. According to the method, double-loop control is adopted, wherein an outer-layer RL decision module dynamically switches PSO working modes according to the environment, and an inner-layer PSO module optimizes the working voltage. The system efficiency in a dynamic scene can be improved by 15%-30%, mismatch loss is reduced by 40% or above, and the method is suitable for unsteady-state energy supply scenes such as unmanned aerial vehicles and mobile robots.

The invention discloses a heat dissipation control method, device and system based on an array chip and a medium. The method comprises the steps that the basic valve opening degree is determined based on the temperature value of any partition and a valve opening degree mapping table; determining a target valve opening degree of each electric valve based on the basic valve opening degree and a spray coverage overlapping model, and sending the target valve opening degree to each electric valve; calculating a target total flow based on all target valve opening degrees, adjusting the rotating speed of a liquid supply pump through a frequency converter, and enabling a measured value of a flow sensor to be the target total flow; determining a target pressure value based on the saturation temperature of the cooling liquid, and adjusting the power of the vacuum pump or the three-way vacuum electromagnetic valve to enable the pressure value of the evaporation cavity to be the target pressure value. According to the method, three-layer linkage logic of partition precise temperature control, system flow coordination and global pressure setting is established, scattered devices are integrated into a whole, overall adjustment of the system level is achieved during heat dissipation control, instructions do not need to be sent frequently to control each valve, and the electric energy consumption of the system is reduced.

The invention discloses an architecture system and method for large-scale task allocation, and belongs to the field of spaceflight measurement and control, and the system comprises a large-scale hardware device which is used for deploying processing units with different performances and various heterogeneous physical communication link resources; the hardware resource dynamic modeling and visualization framework is used for realizing a dynamic modeling system based on multi-source heterogeneous hardware topology perception; the resource topology awareness database captures and synchronizes system deployment changes by maintaining the dynamic topological relation of hardware resources, presents the life cycle state of the hardware resources, and supports system-level resource situation visualization and decision making; a versioning management engine of component arrangement is applied, a multi-version executable unit is packaged based on an atomization component, and an application instance is completed through a combined modeling component; and deploying a scheduling decision system for deploying a scheduling decision. The method can adapt to task deployment requirements of a current large-scale spaceflight measurement and control system.

The invention discloses a branch prediction unit power consumption management method and device, and the method comprises the steps: setting a multi-stage branch predictor and a low-power-consumption control logic coupled with the multi-stage branch predictor in a processor core micro-architecture, and enabling the multi-stage branch predictor to comprise three stages of predictors which are sequentially accessed in an assembly line, the hardware resource consumption and the prediction accuracy of each predictor are gradually increased from front to back; monitoring the prediction condition of each predictor in real time through low-power-consumption control logic, and closing all predictors behind the first predictor meeting the prediction requirement within a first preset time according to a front-to-back sequence; branch jump addresses are divided into high-order address fields and low-order address fields by BTBs in the multiple levels of predictors except the first-level predictor to be stored in different storage blocks, and label registers used for taking the high-order addresses as label indexes are arranged. The power consumption unit of each predictor can be finely controlled, the energy consumption is greatly reduced, system-level cooperation is not needed, and the universality is high.

The application relates to a service scheduling and deployment method for Internet of Things edge computing node resources, which is realized based on an Internet of Things edge computing system. The system comprises a cloud data center, a convergence layer core network and a plurality of access layer switch networks connected in sequence. Each access layer switch network is in communication connection with a plurality of edge computing nodes, and each edge computing node is in communication connection with a plurality of data acquisition terminals. The application comprehensively considers the current running state of the edge computing system, network delay problems and running results after deployment, and performs service scheduling and deployment of Internet of Things edge computing node resources on each real-time data stream computing application. The application is suitable for the decision environment of the real-time computing task load and bandwidth dynamic change of the Internet of Things edge computing node, realizes global optimization from the system level, takes into account the single node load capacity, and realizes the optimal scheme and application planning and deployment decision suggestion of the long-period stable operation and real-time task flexible scheduling strategy.

Disclosed embodiments provide methods, systems, and computer program products for implementing enhanced phase power load balancing of a set of systems (e.g., the set of systems of a data center) using a subset of the systems. Disclosed embodiments extract phase currents of a three-phase power source of the set of systems, and determine, based on extracted phase currents for the set of systems, input phase power load balancing for the subset of the systems. Disclosed embodiments alter the current input phase power balancing of the subset, unbalancing the input phase power load for the subset of the systems to provide enhanced phase power load balancing of the set of systems. Altering the current input phase power balancing for the subset of the systems can be implemented by power shifting between power supply units (PSUs), phase rotations, or input phase switching of power distribution unit (PDU) switchable output ports.

The invention provides a dual-drive deepwater wellbore integrity failure risk evaluation method, and belongs to the technical field of deepwater drilling safety, and the dual-drive deepwater wellbore integrity failure risk evaluation method comprises the following steps: based on fault tree analysis in a bowknot model, identifying a wellbore integrity failure mode; constructing a differentiated evaluation path according to the failure mode, and quantifying a static equipment failure risk and a dynamic structure failure risk respectively; constructing a wellbore system-level failure probability model through a fault tree and Bayesian network dynamic mapping mechanism; based on event tree analysis, modeling is conducted on the safety barrier state after shaft integrity failure, accident consequences are deduced, and the occurrence probability of the accident consequences is calculated; and outputting the system-level failure probability, the key path contribution degree, the bottom event sensitivity sequence and the accident consequence probability, and solving the technical problem that the system-level failure risk is difficult to accurately predict and dynamically prevent and control because static empirical data and a dynamic mechanical mechanism are separated and cannot be coupled and updated in real time.

The invention relates to the technical field of integrated circuits, and provides a verification platform, a verification method, electronic equipment and a medium. The verification platform comprises: an application layer bus function level model comprising a customized interface for a to-be-tested design for interacting with the to-be-tested design, the to-be-tested design being a PCIe protocol docking and protocol compliance test suite, and the to-be-tested design being a PCIe protocol docking and protocol compliance test suite; the PCIe protocol docking and protocol compliance test suite supports a verification demand of a physical layer intellectual property core and a verification demand of protocol consistency of a PCIe controller and a physical layer subsystem level; and the to-be-tested design interacts with the application layer bus function level model through the customized interface. Thus, the integration and through-flow debugging cost of subsystem protocol consistency verification is reduced, the verification period of a docking test of PCIe subsystem protocol standardization is shortened, and the completeness of docking verification of a full quantization protocol of a PCIe subsystem and the platform reuse efficiency are improved.

The invention relates to the technical field of intelligent label recommendation, and discloses a standardized label framework collaborative recommendation system based on artificial intelligence. The system comprises a multi-level professional label knowledge base, a large language model reasoning unit, a semantic consistency verification module, a path verification module, a collaborative decision module and a label recommendation engine. The multi-level professional label knowledge base stores a standardized label system containing a multi-level structure; after receiving the input content, the large language model reasoning unit generates an initial label set according to label system level constraint reasoning; a semantic consistency verification module compares the label and content semantic matching degree and outputs a result, and a path verification module verifies whether a label generation path accords with a hierarchical structure and gives a compliance indication; the collaborative decision-making module corrects the initial label set according to a preset rule when the semantic verification result conflicts or the confidence coefficient is insufficient; and integrating the corrected label set by the label recommendation engine, and outputting a final standardized label recommendation result to adapt to multi-field labeling requirements.

The invention relates to the field of voice questions and answers, and particularly discloses a large model customer service system based on multi-modal double-layer shunt reasoning, which introduces semantic complexity evaluation on a text input by a user, and forms a three-dimensional decision matrix in combination with confidence of front-end voice recognition. By dynamically weighting the intention confidence, the semantic complexity score and the speech recognition confidence, the system can accurately recognize queries which seem to be simple and actually complex. In this way, the traditional confidence trap is solved, even if a complex query generates virtually high intention confidence due to the fact that the complex query contains keywords, the high complexity score of the complex query can correct the shunting decision, and the query is guided to a heavy weight model capable of conducting deep semantic understanding. Finally, it is ensured that all kinds of user requests can be properly processed by the system level, and the accuracy and the problem solving rate of a customer service system are remarkably improved.

Various embodiments include techniques for managing cache memory in a computing system. The disclosed techniques include a cache policy manager that monitors activity of various components that access a common cache memory. The cache policy manager establishes cache rules that determine what data remains stored in cache memory and what data is removed from cache memory in order to make room for new data. As the activities of these components change over time, cache rules that work well for a previous activity profile may no longer work well for the current activity profile. Therefore, the cache policy manager dynamically modifies the cache rules as the activity profile changes in order to select cache rules at any given time that work well with the current activity profile. These techniques are advantageous over conventional approaches that employ static cache rules that work well only for specific activity profiles.

Generally disclosed herein is a mechanism to mitigate power fluctuations of a data center by dynamically charging and discharging a battery energy storage system (BESS). According to some examples, a BESS control system can be configured to monitor power demand fluctuations and initiate charging of the BESS during periods of low power demand. One example of a period of low power demand includes active idle, wherein the workloads of the server machines frequently decrease by a small magnitude. Another example of a period of low power demand includes deep idle, wherein the workloads of the server machines decrease by a larger magnitude than the active idle for a longer duration. The system may discharge the power from the BESS during the peak power demand. The BESS control system may stabilize the data center power system through fast-acting voltage and frequency control at a system level.

The invention discloses a time sequence root cause analysis method and system based on dynamic causal inference, and belongs to the technical field of industrial system fault diagnosis and intelligent operation and maintenance. The method comprises the following steps: collecting and preprocessing multivariable time series data in an industrial system; performing dynamic causal topology discovery by using an improved DAG-GNN algorithm, and generating a dynamic causal topology reflecting system state transition; performing spatio-temporal feature aggregation of causal guidance through GCN and LSTM, and extracting joint representation fusing node local abnormal information and a system-level global fault trend; node-level and system-level collaborative analysis is carried out through a multi-granularity root cause inference module, and a root cause candidate set with confidence ranking is generated; according to the method, the defects in the aspects of dynamic causal modeling, feature coupling and multi-granularity reasoning in the prior art are overcome, accurate tracing of a cross-level fault chain can be achieved, and reliable and explainable decision support is provided for intelligent operation and maintenance of an industrial system.

The invention provides an indoor distribution system fault diagnosis method and device, a repair method and device, electronic equipment and a computer readable storage medium, and relates to the technical field of communication. The diagnosis method comprises the steps that multi-source data of an indoor distribution system are acquired, and the multi-source data comprise user terminal signal quality data, indoor distribution equipment state data, indoor distribution equipment configuration information, environment data and network management data; positioning multi-source data of the fault room subsystem according to a preset fault feature library; the multi-source data of the fault room subsystem are analyzed from the terminal level, the equipment level, the area level and the system level, and the fault type of the fault room subsystem is diagnosed. The problem that faults are difficult to comprehensively and accurately locate due to the fact that a single data source or a simple monitoring means is mostly depended in the prior art is at least solved. The method is suitable for fault diagnosis and repair scenes.

The invention relates to the technical field of industrial safety management and control, and discloses an integrated digital twinning boiler limited space safety operation management and control system and method, and the system comprises a twinning environment building and sensing module which is used for building a three-dimensional digital twinning model, and collecting environment, personnel position and physiological signals in real time; the core calculation and analysis module is used for calculating an individual risk correction coefficient based on the physiological signal and calculating a dynamic risk potential field in a twinborn model based on the environmental data; the risk assessment and decision module is used for coupling the risk potential energy value at the personnel position and the individual risk correction coefficient to generate a comprehensive risk index; and the collaborative intervention and presentation module is used for generating and executing an active intervention instruction based on the comprehensive risk index. According to the invention, by constructing a human-loop coupled dynamic risk potential field, quantitative evaluation and active intervention of individual and system level risks are realized, and operation safety management and control from passive alarm to active prevention and from static management to dynamic closed loop are realized.

The invention discloses a wireless energy supply mobile edge computing system-level energy efficiency optimization method based on distributed optimization. The method comprises the following steps: 1, system modeling and problem construction; 2, performing problem reconstruction and convex processing; 3, an ADMM (Alternating Direction Media Of Multipliers) distributed framework design is carried out, and the distributed framework design is carried out according to the ADMM (Alternating Direction Method of Multipliers); 4, coupling variable updating assisted by the dichotomy; and 5, iterative optimization and convergence guarantee. According to the method, a green WPMEC (Wireless Power Mobile Edge Computing) system which can still run efficiently under the constraint of nonlinear energy collection, multi-user task unloading and strict delay and is high in expandability and optimal in energy is realized through a closed-loop process of modeling, reconstruction, decomposition, solution and iteration. The method is suitable for a large-scale Internet of Things equipment access scene.

The invention relates to the technical field of integrated circuits and provides a physical IP verification device and method, computer equipment and a medium. The physical IP verification device comprises a first reusable multimode test sequence generator, a verification component physical interface, a second reusable multimode test sequence generator and a verification component serial interface. Therefore, different simulation requirements and scenes such as accelerated simulation efficiency and integrated verification can be considered, protocol consistency verification, functional verification completeness of a physical layer subsystem level and standardized protocol verification are supported, and abundant test vector sets are provided; according to the method, the requirements of butt joint test scenes and completeness verification of different levels such as a transaction layer, a data link layer and a physical layer can be met, debugging interaction interfaces and debugging means with rich levels are supported, different physical interface versions and interface data bus bit widths are supported, and hierarchical and fine-granularity low-power-consumption management is also supported.

Various embodiments include techniques for managing cache memory in a computing system. The disclosed techniques include a cache policy manager that monitors activity of various components that access a common cache memory. The cache policy manager establishes cache rules that determine what data remains stored in cache memory and what data is removed from cache memory in order to make room for new data. As the activities of these components change over time, cache rules that work well for a previous activity profile may no longer work well for the current activity profile. Therefore, the cache policy manager dynamically modifies the cache rules as the activity profile changes in order to select cache rules at any given time that work well with the current activity profile. These techniques are advantageous over conventional approaches that employ static cache rules that work well only for specific activity profiles.

The invention provides a flexible load hierarchical polymerization optimization regulation and control method. Flexible load operation data is acquired and divided into adjustable and non-adjustable loads, and a classification foundation is laid for subsequent hierarchical aggregation; three-level aggregation of an equipment layer, a region layer and a system layer is executed on two types of loads, and scattered resources are integrated into a hierarchical structure, so that the complexity of directly regulating and controlling massive scattered loads is remarkably reduced; a regulation and control model is established based on a hierarchical aggregation result, and an optimization algorithm is adopted to solve a strategy, so that collaborative optimization from local equipment to a global system is realized. According to the method, the contradiction between resource dispersity and regulation and control real-time performance is solved through a layering mechanism, the transmission efficiency and execution precision of regulation and control instructions are improved, meanwhile, the communication burden and the calculation cost are reduced through an aggregation model, and an efficient framework is provided for flexible dispatching of power grid flexible loads.

The invention discloses a medical precision instrument full life cycle tracing system based on digital twinning, and relates to the technical field of medical instrument management. The full-life-cycle tracing system comprises an identification recording module which is used for endowing different and unique identity identification codes for components of the medical precision instrument; the data recording module is used for recording physical working condition data, operation and maintenance event data and parameter data of the components of the medical precision instrument in the whole life cycle by taking the identity identification code as a base point; and a digital twin module. According to the method, each component is endowed with a unique identity identification code, the management degree is adjusted to the level of key parts, the deviation between a parameter prediction value output by a digital twin model and an actual measurement value is combined, and path enumeration and intersection analysis are carried out on a complex influence relationship by using a knowledge graph; according to the invention, single or multiple fault source components causing system-level performance abnormity can be automatically and quickly locked.

The invention provides a system-level design generation method and system based on AI-Agent. The method provided by the invention comprises the following steps: receiving design demand information input by a user; carrying out system-level architecture design and system segmentation on the design demand information based on the AI-Agent, generating a system architecture scheme, design prompt information and a constraint file, and carrying out feasibility verification on the system architecture scheme by generating a rule checking mechanism to obtain the system architecture scheme, the design prompt information and the constraint file which pass verification; matching a corresponding path generation method based on the design prompt information passing verification or a Python algorithm code input by a user, and generating a hardware description language code based on the path generation method; and performing function verification on the hardware description language code, connecting the hardware description language code passing the function verification and the constraint file passing the verification with a back-end tool, performing layout wiring, and outputting a GDS-II layout file.

The invention discloses a real-time reliability evaluation method for a marine autonomous surface ship power system based on diagnosis input, and the method comprises the steps: obtaining the operation state data of one or more parts, and obtaining a processed data sequence; obtaining a pre-trained fault diagnosis model, and inputting the processed data sequence into the pre-trained fault diagnosis model to obtain a fault diagnosis result; and constructing a dynamic Bayesian network, performing posterior reasoning through the dynamic Bayesian network in combination with the fault diagnosis result, and outputting a reliability evaluation result of the marine autonomous surface ship power system. According to the method, causal reasoning is carried out by using a component-level fault diagnosis result and combining a dynamic Bayesian network, so that local fault information can dynamically influence system-level prediction, the gap between component-level diagnosis and global reliability estimation is bridged, the problem that system-level quantitative analysis cannot be carried out due to system-level fault data missing is solved, and the reliability of the system is improved. And system-level real-time reliability evaluation can be achieved, and safe operation of the autonomous ship is guaranteed.