19results about How to "Realize failure prediction" patented technology

The invention provides an LCM module aging test method, device and equipment and a storage medium, and the method comprises the steps: obtaining the initial state data and initial environment parameter combination of an LCM module through intelligent environment simulation and initialization processing, and carrying out the multi-mode alternate aging test and real-time monitoring processing of the module through an intelligent environment simulation system, and obtaining performance data in a dynamic environment, and carrying out surface periodic scanning and working sound recording to obtain microstructure data and acoustic data. Through intelligent fault detection and deep analysis processing, fault features and reasons of the module are identified, predictive analysis is performed on the fault in combination with a machine learning algorithm, and a predictive fault trend and an optimized environmental parameter combination are generated. And performing comprehensive performance evaluation on the module according to the fault features, the reason analysis, the prediction trend and the optimization parameters. According to the invention, through combination of intelligent environment simulation, real-time monitoring and deep analysis, accurate performance evaluation and fault prediction of the LCM are realized.

The invention provides a medical equipment maintenance data monitoring method based on big data, and the method comprises the steps: collecting the operation data of medical equipment, carrying out the feature extraction, and merging the extracted features into a comprehensive data matrix; constructing an equipment relation graph and carrying out feature extraction; extracting high-order features through neighborhood feature aggregation according to the constructed equipment relation graph and the extracted features; dimensionality reduction and reconstruction are carried out on the high-order feature matrix by using a variational auto-encoder, and potential feature representation is extracted; optimizing a maintenance plan and resource scheduling of the medical equipment according to a prediction result; and constructing a causal relationship model according to a prediction result and an optimization result, carrying out fault tracing analysis based on a causal inference result, optimizing a maintenance strategy by using an optimization algorithm, implementing a maintenance plan according to the optimized maintenance strategy, and monitoring a maintenance effect in real time. According to the invention, the reliability and the maintenance efficiency of equipment operation are improved, and the innovativeness and the practicability are remarkable.

The invention discloses a photovoltaic power generation control method and system, and the system comprises a distributed sensor network which is used for collecting various environmental parameters of a photovoltaic panel in real time, and the environmental parameters comprise light intensity, temperature, humidity, wind speed and wind direction; the central processing unit is used for receiving and processing the environmental parameters and the meteorological prediction information and generating an angle and load adjustment instruction of the photovoltaic panel through an advanced algorithm; the intelligent actuator system comprises at least two actuators and a driving unit and is used for adjusting the position and the load of the photovoltaic panel according to the instruction; the invention discloses a self-adaptive energy storage system. Through cooperative work of the distributed sensor network and the artificial intelligence module, real-time monitoring, intelligent optimization and fault prediction of the photovoltaic system are achieved, the overall efficiency, reliability and safety of the system are remarkably improved, meanwhile, the cloud data processing platform provides remote monitoring and optimization suggestions, and the system is convenient to use. A user can master and manage the system state anytime and anywhere, and efficient operation and long-term stability of the system are ensured.

The invention discloses a monitoring and maintaining method and system for forging and pressing equipment, and relates to the technical field related to the forging and pressing equipment, and the method comprises the steps: obtaining a plurality of pieces of data sensing information, analyzing the plurality of pieces of data sensing information, and generating a plurality of data monitoring signals. And traversing the plurality of data monitoring signals to carry out frequency spectrum transformation, drawing a frequency spectrum change trend chart, and carrying out operation analysis according to the frequency spectrum change trend chart to obtain equipment health state data. And performing aging analysis based on the equipment health state data to obtain an equipment recession coefficient, performing fault prediction according to the equipment recession coefficient, and determining an equipment fault mode. And formulating a maintenance report to perform resource scheduling optimization on the forging and pressing equipment based on the equipment fault mode in combination with the equipment health state data. The technical problem that the operation state and potential fault mode recognition accuracy of the forging and pressing equipment is low due to the fact that a monitoring and maintaining method of the forging and pressing equipment in the prior art is difficult to efficiently process and analyze multi-source data from a wireless sensor network is solved.

The invention provides a remote control method of a fish passing facility, and relates to the technical field of Internet of Things. The method comprises the following steps: acquiring real-time monitoring data of a plurality of water body environments through a plurality of data acquisition subsystems in an Internet of Things system, then storing the real-time monitoring data to a preset database through a plurality of edge computing nodes in the Internet of Things system, and processing the real-time monitoring data through a cloud server in the Internet of Things system, according to the method, the target device with the fault and the target fault type of the target device are determined, and then the target device is remotely controlled through the target edge computing node corresponding to the target device, so that the target device can execute the fault repair operation, and fault prediction and remote control of each device are realized through the method provided by the invention.

The invention relates to the field of artificial intelligence computing technology, and provides a nationwide architecture sonar analysis and fault early warning method, system and device and a medium, and the method comprises the steps: obtaining real-time data, and carrying out the reasoning of the real-time data, and obtaining an observation result; inputting the real-time data and the observation result into a preset fault prediction model to obtain a first prediction result; comparing the first prediction result with the real-time data to obtain fault features, and performing clustering analysis on the fault features to obtain a second prediction result; and performing fault alarm based on the second prediction result. On one hand, an underwater target can be monitored in real time, on the other hand, fault prediction can be carried out when the system is about to be abnormal, early warning is carried out in advance once the system is found, an alarm is automatically given in real time, monitoring personnel are reminded to carry out maintenance in time, real-time monitoring, target object recognition and fault prediction on the sonar system are achieved, and the system is high in practicability. And the performance and the safety of the sonar system can be obviously improved.

The application discloses an industrial robot predictive maintenance system based on machine learning, and relates to the technical field of industrial robot maintenance.The application comprises a data acquisition module, a preprocessing module, a feature engineering module, a hybrid prediction model unit, a meta-learning and field adaptation module, a federal learning coordination module, a digital twin sample generation module and a dynamic decision engine unit.The application has the following advantages: through the collaborative mechanism of the meta-learning and field adaptation module, a model-agnostic meta-learning algorithm is used to train a cross-brand general feature extractor;different brand data distributions are confused by combining an adversarial field adaptation network;the "data gap" caused by the definition of sensor parameters and the difference in sampling frequency in traditional modeling is broken through;the model is collaboratively trained under the premise that the data of each brand is not out of the local;the global model containing the commonness of cross-brand faults is generated;and the "data island" problem caused by commercial security requirements in the industrial scene is solved.

The application discloses an ODD boundary detection system and an identification method thereof based on real accident data driving, which comprises a data input and evaluation object module, an ODD feature extraction and scene library construction, an automatic driving large model capability evaluation system, online identification algorithm research, cloud control test and verification reproduction, project achievement application module, real traffic accident deep investigation data, automatic driving special large model, standardized scene library, model capability evaluation result, real-time running perception data, multi-source perception information fusion, online boundary detection and failure prediction, millisecond-level early warning model construction, authoritative closed test field verification, multi-target cloud control scene reproduction system, real vehicle performance test and algorithm optimization, millisecond-level online identification system and safety fence. The scheme drives with accident data, evaluates with a large model, identifies in milliseconds and iterates in a closed loop, constructs a verifiable safety fence and guarantees L3 / L4 automatic driving safety landing.

The invention belongs to the technical field of radars, and particularly relates to a radar servo control system fault prediction and diagnosis method. By analyzing composition characteristics, working principles and working states of an electromechanical hybrid device or a complex electronic system in a servo control system, considering factors such as maintenance strategies, use modes, maintenance levels and replacement methods of the products, and combining historical operation conditions, fault data statistical analysis and the like, the method and the system can be used for solving the problems in the prior art. And reasonable use and maintenance suggestions are given for a product guarantee decision.

The application relates to a power conversion equipment fault prediction method and device and a power conversion system. The power conversion equipment fault prediction method comprises the following steps: obtaining the output voltage of a detection coil multiple times in a preset time period, extracting each output frequency corresponding to each output voltage of the detection coil, and predicting the fault occurrence time of the power conversion equipment according to the change trend of each output frequency. The power conversion equipment fault prediction device comprises a detection coil and a data processing device, the detection coil is connected with the data processing device, and the detection coil is a closed coil; the data processing device is used for obtaining the output voltage of the detection coil, extracting the corresponding output frequency, and predicting the fault occurrence time according to the change trend of each output frequency. The power conversion equipment fault prediction method, device and power conversion system realize fault prediction of the power conversion equipment, and further improve the reliability of the power conversion equipment operation.

The application discloses a transformer fault prediction method and system, and relates to the technical field of power equipment.The method comprises the following steps: collecting the start-stop action times of each time window, and determining the temperature control response lag coefficient of each time window by analyzing the temperature control lag level of the cooling control system in the power transformer when the cooling control system faces power mutation; analyzing the non-steady-state operation degree of the cooling control system in the corresponding time window to determine whether the temperature control state of the cooling control system affects the normal operation of the power transformer, and issuing a transformer fault prediction instruction; combining the power consumption drift and voltage frequency spectrum disturbance of the power transformer in each time window, analyzing the non-normal operation degree of the power transformer in the corresponding time window, performing digital model analysis on the non-normal operation index of the power transformer in each time window, generating a corresponding grade fault prediction signal, and performing corresponding voice broadcast reminding.

The present application provides a fault simulation method and device based on digital twins. The method includes: constructing a digital twin model of industrial equipment and a fault simulator, performing fault simulation according to the digital twin model, processing according to the fault simulation result data, obtaining a fault performance evaluation index, obtaining a fault evaluation influence factor according to the historical fault record data processing, and then obtaining a fault performance evaluation correction index, determining the fault type of focus according to the fault performance evaluation correction index, and then processing to obtain a fault prediction model corresponding to the fault type of focus, processing according to the fault prediction model to obtain the fault prediction result data and push it to the user, and processing according to the fault performance evaluation index to obtain a comprehensive fault performance evaluation index, and performing reliability evaluation on the equipment according to the comprehensive fault performance evaluation index. Thereby achieving the purpose of fault prediction and reliability evaluation of the equipment through fault simulation technology based on digital twins.

The invention discloses an expert system for diagnosing faults of textile slurry production equipment, and the system comprises a data collection module which collects the operation data of the textile slurry production equipment through a sensor network; the signal input end of the data transmission module is connected with the signal output end of the data acquisition module, and the data transmission module can convert the electric signals acquired by the data acquisition module into digital signals which can be processed by a computer; the signal input end of the expert system module is connected with the signal output end of the data transmission module, and the expert system module can compare the digital signals transmitted by the data transmission module to complete fault diagnosis; the signal input end of the user interface module is connected with the signal output end of the expert system module; the whole system can be directly designed for industry application requirements at the same time, and can be widely applied to fault diagnosis of textile slurry production equipment.

This utility model discloses an energy meter with a fault self-diagnosis function circuit, comprising: a main control module, a metering module, a communication module group, a multi-level interlocking protection circuit, a diagnostic bus matrix, a fault tracing memory, and a power supply module. The main control module is connected to the metering module, the communication module group, the multi-level interlocking protection circuit, the diagnostic bus matrix, and the fault tracing memory. The diagnostic bus matrix is ​​connected to the metering module and the communication module group. The fault tracing memory is connected to the multi-level interlocking protection circuit. The power supply module is connected to the main control module, the metering module, the communication module group, the multi-level interlocking protection circuit, the diagnostic bus matrix, and the fault tracing memory. This technical solution enables comprehensive fault self-diagnosis of the energy meter, increasing the detection coverage to 12 key nodes, improving response speed, supporting fault prediction and reliable data storage, ensuring operational safety, and improving the level of intelligent power grid management.

The invention relates to the technical field of disaster recovery intelligent operation and maintenance, and discloses a heterogeneous system intelligent operation and maintenance method, system and device based on LSTM. The method comprises the following steps: collecting heterogeneous system data of a plurality of data sources; classifying the plurality of heterogeneous system data into first data and second data; performing anomaly prediction on the first data at the center node by using a first anomaly detection model to generate a first prediction result; performing anomaly prediction on the second data at the edge node by using a second anomaly detection model to generate a second prediction result; determining abnormal data in combination with the first prediction result and the second prediction result; performing synchronous processing on the abnormal data based on a preset network requirement; and performing backup processing on the abnormal data based on a preset network demand and the importance of the abnormal data. According to the invention, fault prediction and intelligent disaster recovery are realized, and the accuracy and real-time performance of data processing and prediction can be improved.

The invention relates to the technical field of data processing and signal analysis, and discloses a steam turbine generator unit vibration-power cross-domain feature fusion analysis method and system, and the method comprises the steps: obtaining vibration signal time sequence data and power signal time sequence data of multiple operation cycles of a steam turbine generator unit, carrying out the preprocessing of the two types of data, and obtaining a power signal time sequence data; obtaining standardized time sequence data which can be used for feature extraction; vibration signal features and power signal features are extracted from the standardized time sequence data, and cross-domain feature vectors of all operation cycles are formed through fusion; inputting the cross-domain feature vector of each operation cycle into a fusion analysis model for processing, and outputting a comprehensive evaluation index of each operation cycle; and on the basis of the multiple operation cycle comprehensive evaluation indexes, operation abnormity identification and early warning judgment of the steam turbine generator unit are executed, and accurate monitoring of the unit operation state is achieved. According to the invention, the technical problem of insufficient evaluation precision caused by a single signal analysis method in the prior art is solved.

This application provides a method and system for predicting power equipment faults based on 5G communication, relating to the field of fault prediction technology. The method includes: acquiring K transmission lines; obtaining first and second equipment monitoring data sets through asynchronous time-series extraction; traversing these data sets, performing fluctuation integration analysis, and determining the equipment fluctuation factor set; dynamically dividing power equipment into first and second-level dynamic monitoring equipment sets; generating first and second-level monitoring data sets through long and short time-series monitoring; and using a fault prediction network layer to perform fault prediction, obtaining K fault prediction results. This application addresses the shortcomings of existing technologies, which suffer from low efficiency and difficulty adapting to dynamic changes when processing large-scale power system data, making it difficult to reflect the operating status of equipment and predict potential faults in real time and accurately. It enables fault prediction of power system equipment, early identification of potential fault risks, reduction of fault incidence, and improvement of power system reliability and security.

The present application relates to the technical field of pole-mounted circuit breaker testing, and discloses a pole-mounted circuit breaker testing device and testing method. The method comprises: constructing a coupled three-dimensional simulation model of the pole-mounted circuit breaker and performing finite element simulation analysis to obtain power loss simulation data and insulation resistance simulation data; performing change calculation to obtain relationship coefficients; performing feature fusion and feature screening on the power loss change data and the insulation resistance change data based on the relationship coefficients to obtain fused change feature data and using the fused change feature data as the feature nodes of the Markov network to obtain an initial Markov network model; performing multiple iterations and model optimization through a genetic algorithm to obtain a target Markov network model; real-time monitoring of the operation status data of the pole-mounted circuit breaker and performing operation fault prediction through the target Markov network model to obtain real-time fault prediction results. The present application improves the fault detection accuracy of the pole-mounted circuit breaker.

The application discloses a short-circuit cumulative distortion evaluation method and system of a power transformer spiral winding and a medium, relates to the technical field of electrical equipment reliability evaluation, and is based on structure parameters and historical fault parameters to fit out peak current plastic deformation and peak current plastic deformation generated by the first peak current in short-circuit impact; and according to the peak current plastic deformation, single-impact deformation reduction and reclosing-impact deformation reduction are calculated; finally, multiple-impact deformation accumulation is calculated, and distortion evaluation is performed on the last impact deformation accumulation result; the application provides a short-circuit cumulative distortion calculation method based on the structure and historical fault parameters of a target power transformer, can effectively evaluate the spiral winding distortion deformation condition, enhances the reliability of the transformer and the stability of the power grid operation, ensures the continuous and stable power transmission, and realizes fault prediction and health management of the transformer spiral winding.