79 results about "Maintenance actions" patented technology

A structural-health-monitoring system is disclosed for real-time detection and autonomous maintenance of physical structures. The system includes a sensor network comprising at least one strain gauge and one tri-axial accelerometer mounted on the structure to generate real-time sensor signals. A perception module filters and normalizes the signals and extracts numerical features such as peak amplitude and dominant frequency. A digital-twin module maintains a finite-element model updated in response to the extracted features. A data-driven surrogate model predicts sensor behavior and refines itself using machine-learning techniques. An anomaly-detection module computes an anomaly score from model residuals or classifier outputs. Upon exceeding a threshold, a maintenance module initiates a maintenance action, including generating an inspection schedule or issuing a control signal to an autonomous inspection or repair device. A learning module continuously improves system performance using reinforcement learning based on historical outcomes. The system supports predictive diagnostics, robotic repair, and automated optimization for long-term structural integrity.

The invention provides a bridge group maintenance priority dynamic decision-making method and device based on reinforcement learning, and relates to the technical field of bridge intelligent maintenance. The method comprises the following steps: constructing a topological structure of a bridge network and a road; defining a state space, a maintenance action space and a state transition matrix of the bridge; defining a reliability index corresponding to the state of the bridge, and designing a comprehensive reward function based on maintenance cost, asset risk and traffic network capacity loss risk based on the topological structure; constructing a bridge maintenance decision problem; the method comprises the following steps of: describing a bridge maintenance decision problem as a Markov decision process, establishing a pointer network strategy model by adopting a pointer network, and training the pointer network strategy model by adopting an Actor-Critic algorithm to obtain a maintenance decision model based on reinforcement learning; and training the maintenance decision model based on reinforcement learning until convergence, and outputting a bridge maintenance action sequence under limited constraints. By adopting the method, the limitation problem of traditional single bridge assessment can be solved.

A network operation and maintenance metrics question and answer method and system based on a knowledge graph and a large model, relating to the technical field of computers. According to the method, a large network model may be triggered to extract at least one type of target operation and maintenance data from entity objects, entity relationships, entity attributes, and operation and maintenance events in network operation and maintenance data, so as to construct a knowledge graph on the basis of the target operation and maintenance data; the knowledge graph can assist the large network model in responding to knowledge question and answer, and the knowledge question and answer result can further assist in enhancing a modeling process of the knowledge graph, thereby improving the response precision of the large network model to knowledge question and answer in the field of operation and maintenance; and the knowledge graph can model and represent operation and maintenance actions, thereby achieving the standardization and automation of the operation and maintenance actions. The large network model can further optimize these operation procedures by learning a large amount of operation and maintenance action data, thereby improving the efficiency of operation and maintenance.

The invention provides a GPU (Graphics Processing Unit) hardware health prediction and active maintenance method and system, and belongs to the technical field of computing hardware maintenance and fault prediction. Based on the GPU health state data, a health degree comprehensive score of the GPU is calculated by using a preset health degree evaluation model, and a key health index in a future set time period is predicted by using a time sequence model. Calculating the fault probability of a preset type of fault risk by using a preset fault risk model based on the health degree comprehensive score of the GPU and / or the predicted key health index; and comparing the calculated fault risk probability with a preset threshold value, and executing a main preset maintenance action when the fault risk probability exceeds the preset threshold value. Through multi-source data acquisition and time sequence prediction, the potential fault risk of the GPU is found in advance, the maintenance action is actively executed, task interruption and data loss are reduced, and the reliability and availability of a GPU cluster are improved.

The invention relates to the technical field of artificial intelligence and vehicle crossing, and provides a commercial vehicle maintenance strategy recommendation method and system.The method comprises the steps that multi-source loss assessment data are obtained, and the multi-source loss assessment data at least comprise damage information and vehicle attributes; generating a maintenance item list based on the damage information and the vehicle attributes, and inputting the multi-source loss assessment data and the maintenance item list into a reinforcement learning model, so that the reinforcement learning model constructs a state space, defines an action space, calculates a multi-target reward function, and generates a plurality of maintenance strategies; each maintenance strategy comprises maintenance action details and corresponding multi-dimensional quantitative indexes. According to the method, multi-source loss assessment data and a maintenance item list are processed through a reinforcement learning model, and a plurality of maintenance strategies including maintenance action details and multi-dimensional quantitative indexes are generated, so that the problems that an output scheme is single, the intelligent effect is poor, and a scheme conforming to an actual maintenance scene is difficult to generate are solved.

The invention provides a training method of an aircraft maintenance simulation model and an aircraft maintenance simulation method, relates to the technical field of aircraft maintenance simulation, and aims to predict future evolution of aircraft maintenance so as to improve authenticity of aircraft maintenance simulation. The method comprises the following steps: acquiring training data related to maintenance simulation; training a maintenance simulation model based on the training data; the aircraft maintenance simulation model comprises a video word segmentation device, a multi-modal input encoder, a multi-modal token sequence and a multi-modal output encoder, wherein the video word segmentation device is used for encoding videos related to aircraft maintenance simulation into a video token sequence; the multi-modal input encoder is used for encoding multi-modal input data related to aircraft maintenance into a multi-modal token sequence; the potential action model is used for determining a potential action representation of a maintenance action based on the video token sequence and the multi-modal token sequence, and the dynamic prediction model is used for predicting a prediction token at the next moment based on the video token sequence, the multi-modal token sequence and the potential action representation so as to simulate a maintenance scene at the next moment.

The invention discloses a fire-fighting facility maintenance method and system based on a knowledge graph, and relates to the technical field of fire fighting, and the method comprises the following steps: S1, constructing a fire-fighting facility maintenance knowledge graph, S2, calling an atomization maintenance step set corresponding to a facility, and S3, dynamically superposing maintenance guidance to an equipment entity based on an augmented reality technology, s4, collecting real-time maintenance action data and comparing the real-time maintenance action data with standard actions in the knowledge graph, S5, performing verification in compulsory execution and completing verification in steps, and S6, responding to an equipment abnormal state, and automatically triggering and pushing associated emergency plan operation guidance. According to the method, operation deviation is reduced through AR dynamic guidance, compliance is ensured through real-time action monitoring and double verification, an emergency plan is simplified in the mode that abnormal second-level triggering is smaller than or equal to 20 seconds, closed-loop management is achieved through bidirectional cooperation of the five modules, AR interaction efficiency is improved by 40%, leapfrogging operation is eradicated through a leak detection prevention controller, data driving execution-optimization intelligent closed loop is achieved, emergency response cross-terminal synchronization is achieved, and operation time is compressed.

The invention relates to the technical field of sensing, and discloses an equipment operation maintenance state intelligent monitoring system and method.The system comprises a multi-mode sensing acquisition module, an edge calculation analysis module, a digital twinborn decision module and a maintenance execution control module; when the operation state of the equipment is monitored, static parameters and dynamic operation data of the equipment are fused, multi-dimensional feature extraction and abnormal coupling analysis of the health state of the equipment are realized, early potential faults of the equipment can be accurately identified, the problems of false alarm and missing alarm caused by monitoring of a traditional single sensor are avoided, the accuracy and reliability of state evaluation are improved, and the reliability of state evaluation is improved. The method is advantaged in that continuous and safe operation of equipment is guaranteed, long-term benefits of different maintenance actions are simulated in a virtual environment based on equipment degradation state quantitative indexes during equipment maintenance strategy optimization, and a problem of non-planned shutdown caused by dependence on artificial experience and maintenance lag of a traditional threshold alarm mechanism is solved.

The invention discloses a network operation and maintenance automatic management method based on deep learning, and the method comprises the following steps: collecting operation and maintenance data, and carrying out the preprocessing of the operation and maintenance data, and obtaining a standardized data set; adopting a Mama selective state space network to generate an operation and maintenance state vector; inputting the operation and maintenance state vector into the improved CORAL model to generate an anomaly detection result; generating a root cause analysis result by adopting a causal inference method; generating candidate operation and maintenance actions by adopting a constraint modeling method in combination with a service level agreement rule; obtaining an optimal operation and maintenance action by adopting an action evaluation method and a risk analysis method, issuing and executing the optimal operation and maintenance action, and collecting execution feedback data; and generating an operation and maintenance audit report based on the anomaly detection result, the root cause analysis result and the execution feedback data. Intelligent, automatic and auditing management of the whole operation and maintenance process is realized, and the method can be widely applied to intelligent operation and maintenance scenes of a large-scale complex network.

The invention discloses a civil aviation fleet maintenance decision-making method based on multi-body distributed hierarchical reinforcement learning, and the method comprises the steps: constructing a civil aviation fleet maintenance decision-making environment through fleet parametric modeling, and simulating a multi-aircraft multi-task scheduling and maintenance process in real operation; and key factors such as equipment degradation, maintenance resource constraint and task execution priority are fully considered. In the environment, a distributed hierarchical reinforcement learning algorithm is adopted: an upper-layer strategy is used for global maintenance resource allocation and task coordination, and a lower-layer strategy is used for local maintenance actions of a specific body. According to the method, a shared communication mechanism and a reward structure are introduced among multiple agents, so that the cooperation efficiency is improved, and the training convergence is accelerated. Experimental results show that the method is remarkably superior to a traditional heuristic method and a standard reinforcement learning algorithm in the aspects of task completion rate, maintenance cost control and system robustness, and high efficiency and reliability of civil aviation team maintenance are achieved.

The invention relates to the technical field of shield tunneling machine cutter maintenance, and discloses a shield tunneling machine cutter maintenance decision-making method and device, a medium and a computer program product, and the method comprises the steps: initializing a state; defining a sequence decision process in a simulation environment: according to a maintenance action and an updated state calculation moment award, storing an experience tuple into an experience playback buffer area; randomly sampling a batch of empirical tuples from an empirical playback buffer area, minimizing a loss function by using a gradient descent method, and updating policy network parameters of an inspection agent and a maintenance agent; and repeating the above process until a preset termination condition is reached. According to the method, the problem of passive agents in multi-agent reinforcement learning is solved by constructing a sequential simulation environment and adopting a value decomposition network architecture, and the inspection interval can be dynamically adjusted according to different degradation conditions of the shield tunneling machine cutter, so that the maintenance strategy is optimized, and the maintenance cost is reduced.

The invention relates to an escalator maintenance quality detection method, device and system, and the method comprises the steps: obtaining at least one sensor data and maintenance video data, and determining the sensor data meeting a preset standard condition; a preset action recognition model is used for recognizing the maintenance action of the maintenance video data, and the maintenance quality detection result of the escalator is obtained according to the similarity between the maintenance action of the maintenance video data and a preset maintenance action template and according to the sensor data meeting the preset standard conditions and the similarity between the maintenance action and the preset maintenance action template. And the accuracy of the maintenance quality detection of the escalator is improved.

According to various embodiment, a method for performing maintenance of a communication network is described comprising receiving a specification of one or more maintenance goals for one or more network entities of the communication network, determining a set of maintenance actions to achieve the one or more maintenance goals, determining at least one impact of the set of maintenance actions on one or more further network entities if they are applied to the one or more network entities, determining one or more further maintenance actions which prevent negative impact of the set of maintenance actions on the one or more further network entities, determining a maintenance action schedule for at least a subset of the maintenance actions and the determined one or more further maintenance actions and carrying out the maintenance actions of the subset of the maintenance actions and the determined one or more further maintenance actions according to the maintenance action schedule.

The present disclosure relates to a method of providing for maintenance of a separator (1), and a separator (1) performing the method. The method comprises determining (S101) operational modes in which the separator (1) is controlled to operate upon performing separation processes, storing (S102) information as to which operational modes are performed by the separator, evaluating (S103) the stored information for scheduling a maintenance action to be performed on the separator (1) based on the performed operational modes, and alerting (S104) an operator (41) of the separator (1) of the scheduled maintenance action to be performed on the separator (1).

A method for maintaining a test table (2) using a maintenance unit (4) is described, wherein the test table (2) has a surface (6) with at least one test module (8) for connecting and testing a cable set, wherein the maintenance unit (4) has a sensor unit (10) positioned above the surface (6), wherein the maintenance unit (4) uses the sensor unit (10) to detect the test module (8) and determine its current state, wherein the maintenance unit (10) determines an ID of the test module (8), wherein the maintenance unit (4) uses the ID to retrieve a target state for the test module (8) from a database (14), wherein the maintenance unit (4) compares the current state with the target state and automatically performs a maintenance action for the test module (8) based on the comparison. A corresponding maintenance unit (4) is further described.

The invention discloses an equipment maintenance action digital processing method and device, equipment and a storage medium, and relates to the technical field of industrial production and equipment management, and the method comprises the steps: obtaining the maintenance video data of target equipment in a maintenance scene; dividing the maintenance video data into a plurality of independent action segments, and synchronously identifying an action category and operation tool information corresponding to each action segment; on the basis of the action category and the operation tool information of each action section, generating a special semantic descriptor for maintenance of the target equipment in the maintenance scene; and generating a standardized maintenance log based on the maintenance special semantic descriptor of the target equipment. Through the above mode, maintenance operation and operation tools are directly and accurately extracted from the video data, the accuracy and adaptability of extraction are ensured, and the generated standardized maintenance log can be used as a digital carrier of experience and skill of workers for a maintenance scene, thereby providing reliable data support for intelligent maintenance decision and skill training.

The application provides a power grid outage maintenance scheduling optimization method based on Q learning, which comprises the following steps: generating a Gantt chart by acquiring an original power grid topology file, and establishing a state judgment rule and a target function of reinforcement learning; integrating maintenance plans of subordinate units to the Gantt chart to form an initial maintenance plan; calculating an initial power flow collection by using a built-in power flow solver of Matlab, and evaluating a power grid operation state; in the agent training process, an epsilon-greedy method is used to select a maintenance action, the Gantt chart and the topology file are updated, and the Q value is updated through a Bellman equation, so that the maintenance plan is optimized; and the Gantt chart of a final outage maintenance plan is output after the training is completed. The power grid scheduling problem is abstracted as a Q learning problem, the outage scheduling is optimized by using a Q learning algorithm through reasonable constraints and a target function, the work intensity of dispatchers is reduced, the talent training cost is reduced, the scheduling efficiency and reliability are improved, and the key technical problems of power grid scheduling are solved.

The application discloses a kind of ship log operation and maintenance method, equipment, medium and product, involve log maintenance and ship operation and maintenance technical field, the method includes: periodically combining standardization log data with on-cycle verification conclusion or separately sent into shipborne large language model, with model semantic analysis identifies exception and calls maritime knowledge base matching knowledge paragraph supplementary analysis context, disassemble to form with execution object, operation, expected effect Standardized operation and maintenance instruction is issued to controller and landed execution and returns result, compares output verification conclusion, relies on historical disposal conclusion iteration optimization precision of each round of abnormal analysis, rely on maritime professional knowledge to eliminate the defect that pure log semantic analysis lacks industry basis, through structured task chain and standardization instruction Realize that operation and maintenance action can be landed, can be checked, with the comparison of execution result and expected effect Form complete cycle feedback logic, improve ship equipment abnormal positioning accuracy and operation and maintenance disposal normativity.

An inspection system and method of operation may include receiving sensor data for a component of a powered system, and determining an expected failure time of the component at which the component is expected to fail based at least in part on the sensor data. The expected failure time occurring on a timeline. A window start time may be determined on the timeline that is after a current time but is prior to the expected failure time. The window start time and the expected failure time may define a window time range that extends between the window start time and the expected failure time on the timeline. One or both of a repair action or a maintenance action of the powered system may be scheduled at a scheduled time occurring during the window time range and at a time prior to the expected failure time on the timeline.

The invention discloses an overseas fusion CDN fault prediction method based on deep learning. The overseas fusion CDN fault prediction method comprises the following steps: outputting a sliding window time sequence tensor; traversing the sliding window time sequence tensor in the forward direction and the backward direction through bidirectional gating circulation units with different expansion coefficients, and outputting a global context embedding sequence; generating an aligned context embedding representation, performing normalization processing, and outputting a normalized aligned context embedding representation; obtaining an optimized multi-task migration prediction model; and comparing the fault probability prediction result with a dynamic fault threshold value to generate a fault early warning signal, and automatically triggering an overseas fusion CDN intelligent operation and maintenance action according to the fault early warning signal. According to the method, the operation and maintenance response efficiency and the network service stability are improved, and the high-availability and high-quality access requirements of global users are met.

The invention discloses a mechanical equipment maintenance and spare part decision-making method and system based on reinforcement learning, a medium and equipment, and the method comprises the steps: carrying out the noise reduction of continuous monitoring data of mechanical equipment through employing a principal component analysis method, fitting a degradation curve based on a Wiener process, and determining a failure threshold value; constructing a state space based on discrete states of equipment degradation and inventory, and constructing an action space based on maintenance actions and ordering opportunities; establishing a cost function based on the maintenance cost and the spare part management cost, and calculating an expected reward value; and by adopting a multi-agent DDQN reinforcement learning algorithm and taking the maximum expected reward value as an optimization target, obtaining optimal maintenance and spare part management behaviors in a discrete state of mechanical equipment degradation.

The present application relates to the technical field of bridge resilience operation and maintenance management, and discloses a near-shore bridge operation and maintenance action optimization and scheduling management system based on resilience management, which comprises: a state and data modeling module, which defines the deterioration state and exposure state of the near-shore bridge components and obtains passive agent observation data; a likelihood and tail distribution module, which constructs an observation likelihood model and establishes a heavy-tailed joint distribution; a shock identification and updating module, which identifies shock events and updates the posterior distribution of the deterioration state and exposure state; a safety index calculation module, which calculates the resistance distribution and demand distribution, evaluates the failure probability and reliability index; an operation optimization and scheduling module, which optimizes the operation action scheme, resource allocation and scheduling; a resilience target configuration module, which calculates the resilience gap score and generates a set of resilience strategy parameters; and a monitoring and auditing module, which splits the task list and calculates the cost deviation, progress deviation and resilience back-off amount. The present application realizes the operation action optimization and efficient resource allocation of the near-shore bridge.

The application discloses a kind of mechanical and electrical equipment management method and system based on Internet of Things, belong to mechanical and electrical equipment management technical field, including the first state vector obtained by preprocessing original data, input first state vector and working condition label, output risk score and feature vector, based on risk score and feature vector, generate first maintenance action, and construct strategy function, execute first maintenance action, after execution is completed, the current state vector of equipment is collected as second state vector, feedback score function is constructed and second state vector is input to obtain feedback score, feedback score, first maintenance action and second state vector are composed training sample, feedback score and training sample are packaged as block chain data unit, and shared access is realized by key strategy.The application realizes real-time monitoring, fault prediction, intelligent maintenance decision in equipment management by combining edge computing and intelligent decision algorithm.

The invention discloses an operation and maintenance analysis method, device and equipment for a virtual power plant and a medium, and the method comprises the steps: obtaining structured time series data, text data and image data generated in the operation and maintenance process of the virtual power plant, and carrying out the feature extraction of the multi-modal data, and obtaining a multi-modal fusion feature; and then, inputting the multi-modal fusion features into the constructed causal enhanced multi-agent fault diagnosis framework for reasoning so as to determine the fault root cause and the propagation path thereof of the virtual power plant. And meanwhile, an equipment health state evaluation model based on meta reinforcement learning is constructed, the model is combined with the multi-modal fusion features and the dynamic knowledge graph, the health state of the equipment in the virtual power plant is evaluated, and corresponding maintenance actions are output. The accuracy and practicability of operation and maintenance analysis of the virtual power plant can be improved, and the operation reliability, economy and flexibility of the virtual power plant in a complex power grid environment can be enhanced. The method can be widely applied to the technical field of electric power.

A structural-health-monitoring system is disclosed for real-time detection and autonomous maintenance of physical structures. The system includes a sensor network comprising at least one strain gauge and one tri-axial accelerometer mounted on the structure to generate real-time sensor signals. A perception module filters and normalizes the signals and extracts numerical features such as peak amplitude and dominant frequency. A digital-twin module maintains a finite-element model updated in response to the extracted features. A data-driven surrogate model predicts sensor behavior and refines itself using machine-learning techniques. An anomaly-detection module computes an anomaly score from model residuals or classifier outputs. Upon exceeding a threshold, a maintenance module initiates a maintenance action, including generating an inspection schedule or issuing a control signal to an autonomous inspection or repair device. A learning module continuously improves system performance using reinforcement learning based on historical outcomes. The system supports predictive diagnostics, robotic repair, and automated optimization for long-term structural integrity.

The invention relates to the technical field of equipment management, in particular to a food processing equipment management system based on cloud edge collaboration, which comprises a production disturbance quantification module, a micro-shutdown time window identification module, a maintenance task dynamic matching module and a maintenance state closed-loop feedback module. According to the method, disturbance of maintenance on production takt is quantified by constructing a discrete event simulation model, complex maintenance is decomposed into an atomization action sequence, non-fault shutdown time windows such as production switching are actively recognized, the duration time is accurately predicted through a K-nearest neighbor algorithm, atomization maintenance actions are dynamically matched and combined, and the production takt time is accurately predicted. The method comprises the steps of generating a micro task package which can just fill the downtime and pushing and executing the micro task package, then forming closed-loop feedback according to a completion signal, updating the global task progress in real time, changing passive planned maintenance into active opportunity maintenance, and completing maintenance without interrupting the production process in a seaming manner, so that the comprehensive efficiency and the production continuity of equipment are remarkably improved.

The invention discloses a refrigerator which comprises a storage chamber and a refrigerator body. A cooling unit; an air door; the processing unit comprises a scene diagnosis part, a fault diagnosis part and an execution part; the scene diagnosis part is configured to receive a time sequence of the operation data from the detection unit, diagnose an abnormal scene by using a scene diagnosis model, and collect a scene diagnosis result of temperature abnormity of the storage chamber; the fault diagnosis part is configured to receive a time sequence of the operation data from the detection unit, diagnose fault classification causing temperature abnormity of the storage chamber by using a fault diagnosis model, and collect a fault diagnosis result of an air door fault when a collected scene diagnosis result meets a preset scene evaluation condition; and the execution part is configured to respond to an evaluation result to execute one or more maintenance actions when the collected fault diagnosis result of the air door fault meets a preset fault evaluation condition. The refrigerator provided by the invention can accurately detect the fault of the air door.

The application relates to a device deployment and long-term self-maintenance method, device, computer equipment, computer readable storage medium and computer program product. The method comprises the following steps: obtaining a device running state, an installation relationship state, a calibration reference state and a reference archive state of a measuring device; determining an installation relationship parameter of the measuring device according to the installation relationship state, comparing the installation relationship parameter with a standard installation state of the measuring device, and obtaining a deployment health state of the measuring device; establishing a calibration reference archive of the measuring device according to the calibration reference state and the reference archive state; analyzing the device running state to obtain a component health state of the measuring device; performing device health self-maintenance or calibration maintenance on the measuring device according to the component health state, the deployment health state and the calibration reference archive, and outputting a maintenance action result. The application can improve the efficiency and accuracy of device maintenance.

This invention discloses a machine learning-based method for user operation and maintenance decision-making in an embedded tag e-commerce platform, comprising: collecting multi-source behavioral and operation and maintenance interaction data to construct a current session state set; constructing an intent impulse sequence and generating a tag reachability tensor, constructing and updating a tag debt state set; constructing a multi-layer hypergraph of tag position and action, and constructing a corresponding multi-scale input feature set; inputting the multi-scale features into an improved deep factorization machine model to generate a counter-evidence net effect value; selecting target operation and maintenance solutions based on the net effect value, and constructing a tag commitment execution chain across page positions; controlling the embedding position and timing of embedded tags and the execution of operation and maintenance actions, and updating the model and the tag commitment execution chain. This invention achieves accurate reach and continuous operation and maintenance decision-making for embedded tags in multi-page, multi-stage sessions by constructing a tag debt memory mechanism and an improved deep factorization machine dual-mirror recognition model.

This invention discloses a deep learning-based method for predicting storage device failures, comprising: collecting operational monitoring data of the storage device; preprocessing to construct a time-series health representation sequence; performing adaptive window construction to extract the modeling sequence; establishing a topology graph and aggregating the node-level health representation sequences; constructing an improved SCINet model to obtain a prediction sequence; calculating the prediction residual sequence and generating a standardized residual sequence; outputting a failure risk judgment result based on the sequential probability ratio test; generating alarm information and triggering coordinated operation and maintenance actions. This invention, by combining the improved SCINet model and the sequential probability ratio test, achieves online prediction and early warning-based coordinated handling of storage device failure risks.