50results about How to "Accurate Failure Prediction" patented technology

The invention discloses an engine fault prediction method. The method comprises the following steps that effective measurement data of a plurality of sensors of an engine are obtained; the effective measurement data are subjected to normalization processing; the effective measurement data obtained after normalization processing are sliced, and a plurality of slice samples are formed; the multiple slice samples are sent into a deep nerve network to be subjected to feature extraction, and after feature extraction, the slice samples are connected to a fully-connected network; and according to output of the fully-connected network, classification is conducted through a softmax classifier, and the left service life of the engine is determined. According to the provided engine fault prediction method, the process is small, operation is easy, and the engine fault prediction method can be widely applied to various engines of aircraft.

The invention relates to an on-line monitoring system of navigation equipment and a method thereof. The monitoring system comprises a test antenna, a GPS antenna, an antenna control module, a radio frequency acquisition and processing module, a signal analysis module and a central controller module. The test antenna is used for obtaining instrument landing system ILS / VHF Omnidirectional Range VOR spatial signals. The GPS antenna is used for receiving satellite signals. The antenna control module transmits signals received by the test antenna and the GPS antenna to the radio frequency acquisition and processing module. The radio frequency acquisition and processing module carries out filtering, demodulation and calculation on the received signals to obtain relevant parameter data and transmits the relevant parameter data to the signal analysis module. The signal analysis module analyzes the received data and transmits analysis results to the central controller module. According to the invention, accurate position measuring points of navigation channels can be determined, and measuring precision and accuracy of the on-line monitoring system of the navigation equipment are enhanced.

The invention discloses a power transmission and transformation equipment fault early warning system based on online monitoring, and the system comprises the following modules: a multi-parameter sensor module which is used for collecting data in real time; the wireless sensor network module is used for transmitting the data to the data processing center for processing; the data fusion module is used for generating a comprehensive health score of the equipment by adopting a multi-modal data fusion algorithm based on a self-evolution nested network; the trend prediction module introduces an adaptive residual module to carry out trend prediction based on a nonlinear time sequence analysis technology of a generative adversarial adaptive residual network; the early warning threshold value adjusting module is used for dynamically adjusting an early warning threshold value by adopting a self-adaptive evolutionary algorithm of meta reinforcement learning; the maintenance suggestion generation module is used for generating maintenance suggestions; and the power grid dispatching linkage module is used for automatically linking a power grid dispatching system and detecting and adjusting an equipment load. According to the invention, a multi-parameter fusion and generative adversarial network method is adopted, and an adaptive residual module is introduced, so that accurate early warning of faults of power transmission and transformation equipment is realized.

The invention relates to a high-voltage single conductor cable service life evaluating method and system. A high-voltage single conductor cable service life evaluating method comprises the following steps of acquiring high-voltage single conductor cable original operation zero-failure data, conducting estimation for shape and size parameters of a double-parameter Weibull distribution model built for evaluating high-voltage single conductor cable service life via a corrected maximum likelihood function to acquire shape parameter estimation values and size parameter estimation values, and acquiring a high-voltage single conductor cable service life distribution probability curve via the double-parameter Weibull distribution model according to the shape parameter estimation values and size parameter estimation values. Accurate fault analysis and fault prediction can be provided with fewer samples by the use of the Weibull distribution model; parameter estimation can be achieved even when zero-failure samples do not exist by the corrected maximum likelihood function; and accuracy for insulation cable service life estimation can be improved.

The invention relates to an elevator fault prediction method based on big data learning, and provides a method for predicting and diagnosing faults of an elevator based on big data acquired through asensor during actual operation of the elevator. The elevator fault prediction method comprises the three aspects of association of elevator operation characteristic big data and operation reasons, acquisition of complex equipment operation fault characteristics based on big data analysis, and elevator operation fault prediction based on data learning. According to the elevator fault prediction method, big data is subjected to noise reduction treatment, more effective data is acquired, elevator operation parameters are analyzed, characteristic parameters are acquired, a depth neural network prediction model is established, and fault prediction is more accurate.

The invention discloses an equipment operation evaluation method based on multi-source data fusion, and relates to the technical field of equipment operation evaluation, and the method comprises the following steps: S1, data collection: collecting multi-source data of equipment in a real-time operation state, the multi-source data comprising sensor data, operation logs, environment data and maintenance history of the equipment; according to the equipment operation evaluation method based on multi-source data fusion, accurate equipment state monitoring and fault prediction can be provided, and the performance and accuracy of the equipment can be continuously optimized according to actual equipment operation data and environmental conditions of the equipment, so that efficient and intelligent equipment management and maintenance strategies are realized; according to the method, specific steps and features of the equipment operation evaluation method based on multi-source data fusion are clearly defined, comprehensiveness and high efficiency of the method are ensured, and the method is suitable for various complex industrial environments so as to improve reliability and maintenance efficiency of equipment.

The invention discloses a multi-source information fusion bearing fault prediction system and method, and the technical scheme is that the system comprises a multi-source information collection systemand a fault prediction system, and the multi-source information collection system is used for obtaining the multi-source information of a full-life-cycle operation state of a bearing, and comprises aplurality of sensors installed on the bearing; the fault prediction system comprises a database, a data processing module, a state monitoring module and a fault prediction module, the database is used for storing data acquired by different sensors, and the data processing module is used for processing original signals acquired by different sensors; the state monitoring module is used for displaying data in real time, and the fault prediction module can train the processed data to obtain a fault prediction result. According to the invention, the bearing operation full-life-cycle state can be obtained, multiple state signals of the bearing are collected and analyzed at the same time, the fault feature recognition rate is improved, and the model prediction accuracy is improved.

The invention discloses an electrical switch cabinet detection method based on the Internet of Things, and particularly relates to the technical field of electrical switch cabinets. A sensor is installed inside or outside a switch cabinet, temperature, humidity, current, voltage and gas concentration are collected, data are transmitted to an edge computing node for preprocessing by using a wireless communication technology, the preprocessed data are uploaded to a cloud platform, storage and trend analysis are performed at a cloud end, and the data are analyzed based on big data analysis and an artificial intelligence algorithm. According to the invention, the system can predict potential faults, a user can check the operation state and the prediction result of the equipment in real time through the cloud platform, and carries out the emergency shutdown or equipment scheduling operation remotely according to the early warning information, thereby effectively solving a reliability problem caused by communication interruption or data delay in an existing Internet of Things system, and improving the safety and intelligent level of the monitoring of the switch cabinet.

A method and device for predicting the fault of a fan are provided. The method includes the steps of initializing a fan model of a fan; periodically updating fan model parameters of the fan model according to current environmental conditions and current actual fan state parameters of the fan; establishing a fan model parameter variation model according to historical fan model parameters and corresponding historical environmental conditions; predicting fan model parameters at a future moment using the fan model parameter variation model on the basis of future environmental conditions at the future moment; establishing a fan fault model according to the historical fan model parameters and corresponding historical fan faults; and predicting a fan fault at a future moment according to the predicted fan model parameters and the fan fault model. According to the invention, the fault of the fan can be accurately predicted.

The invention relates to the technical field of electric power measurement and control instruments, in particular to an operation method and system based on an electric power measurement and control instrument, and the method comprises the following steps: based on the electric power measurement and control instrument, remotely collecting real-time operation data of a power grid, screening and removing abnormal data, integrating historical operation data, analyzing data collected from a sensor, and obtaining an equipment fault probability index. According to the invention, real-time data remotely collected by the electric power measurement and control instrument is combined with historical data for analysis, so that fault prediction is more accurate, the probability of power grid interruption is reduced, the accuracy of real-time determination of key monitoring points and fault prediction is improved, resource allocation is optimized, the fault processing speed is accelerated, and intelligent comparison with maintenance period data is realized. The method optimizes the maintenance schedule, guarantees the efficient operation of the power equipment, effectively predicts the future load change through analyzing the difference between the current load and the predicted load, guarantees that the power grid can adapt to different operation conditions, and improves the reliability and efficiency of the whole power grid.

The invention discloses an in-transit intelligent train air conditioning unit fault diagnosis method, device and equipment and a medium, and the method comprises the steps: constructing a standard event template library according to a standard electric power time sequence, and enabling the standard event template library to comprise transient and steady state standard event templates; obtaining corresponding transient and steady-state time sub-sequences according to the historical electric power time sequence; finding matched transient and steady-state standard event templates in a standard event template library to obtain corresponding historical electric power steady-state residual sub-sequences, and training an extreme learning machine by taking the historical electric power steady-state residual sub-sequences as historical samples to obtain a train air conditioning unit fault prediction model; and obtaining a real-time electric power time sequence of the air conditioning unit of the train on the way, obtaining a corresponding real-time electric power residual error sequence according to the same method, and inputting the real-time electric power residual error sequence into thetrain air conditioning unit fault prediction model, thereby predicting the fault type of the air conditioning unit of the train on the way. The number of sensors needing to be additionally arranged is small, the cost is low, and the fault prediction accuracy is high.

The invention discloses a new energy automobile lithium battery thermal runaway monitoring system and method. The system comprises a vehicle-mounted lithium battery, a multi-source data acquisition module, a multi-source data fusion module, a hidden Markov model monitoring module, a state identification module, a data analysis processing module, an early warning module, an emergency processing module, a wireless communication module, a cloud platform and a battery management system. The multi-source data acquisition module is responsible for acquiring multi-dimensional data such as voltage, temperature and internal resistance of a lithium battery, and the data fusion module processes the data and then transmits the data to the hidden Markov model monitoring module for state monitoring and prediction. According to the system, a high-order hidden Markov model and a hidden semi-Markov model are adopted, state retention time modeling and a self-adaptive online learning mechanism are combined, and conversion of a battery from a normal state to an abnormal state and a thermal runaway state can be accurately recognized. The system remarkably improves the safety and stability of the lithium battery of the new energy automobile, and is suitable for power battery management of the new energy automobile.

The invention provides an airplane hydraulic system fault identification method and device, and a readable storage medium, and the method comprises the steps: obtaining N types of flight parameter data, sensitive to a hydraulic system fault, of a plurality of sorts of an airplane, and constructing a time sequence data set; carrying out data preprocessing on a time series data set constructed by the N hydraulic system parameters; dividing a time series data set constructed by the N hydraulic system parameters into a time series data set with a marked fault state and a time series data set without a marked fault state; constructing an aircraft hydraulic system fault identification model based on semi-supervised learning by utilizing the N hydraulic system parameters; and determining the actual fault state of the aircraft hydraulic system according to the aircraft hydraulic system fault identification model based on semi-supervised learning and the real data set. The aircraft hydraulic system fault identification model based on semi-supervised learning is adopted to identify the fault of the aircraft hydraulic system, and the fault condition of the aircraft hydraulic system can be effectively identified.

The invention provides a fault detection method and a fault detection device. The fault detection device comprises an energy storage power supply, wherein the energy storage power supply is composed of energy storage power supply modules, and each energy storage power supply module is composed of single super capacitors. The fault detection method comprises the steps of: acquiring a module voltageof each energy storage power supply module during operation of the energy storage power supply; for each energy storage power supply module, calculating to obtain a module voltage equilibrium value and a module voltage fluctuation value based on the module voltage, judging whether the module voltage equilibrium value is greater than a first preset threshold value or not in an acquisition period,and judging whether the module voltage fluctuation value is greater than a second preset threshold value or not in the acquisition period; and if the module voltage equilibrium value is greater than the first preset threshold value in the acquisition period, and / or the module voltage fluctuation value is greater than the second preset threshold value, determining that the energy storage power supply modules have a fault until the determination of all the energy storage power supply modules in the energy storage power supply is completed. The fault detection method and the fault detection device realize the detection of whether the energy storage power supply modules have a fault, and further realizes the purpose of predicting the occurrence of electrolyte leakage or burnout of the energy storage power supply.

The invention discloses a well station instrument fault intelligent diagnosis system and diagnosis method based on big data and artificial intelligence, and the system comprises a well station instrument data management and acquisition module which collects and stores well station instrument data in real time, and provides a visual data display interface at the same time, so that an operator can know the operation state of a well station in time; the well station instrument data analyzing and processing module is used for analyzing the collected well station instrument data and extracting key index data; according to the well station instrument fault early warning model system, a multi-level early warning model is created, and potential faults of well station instruments can be effectively recognized and predicted; and the well station instrument fault diagnosis and analysis module is used for quickly identifying abnormal conditions in the well station instrument data, making fault early warning and analysis reports and providing the fault early warning and analysis reports to management personnel. According to the intelligent diagnosis system and the diagnosis method, problems possibly occurring in production are analyzed and predicted through an intelligent algorithm and a model, and corresponding measures are taken in advance so as to ensure safety and stability of oil well production.

The invention belongs to the technical field of digital twinning, particularly relates to an intelligent monitoring and adjusting method, system and equipment based on the digital twinning technology, and aims to solve the problems that in the prior art, efficient and accurate fault prediction cannot be carried out on production equipment, the fault position is difficult to locate accurately, and the maintenance efficiency is affected. The method comprises the following steps: acquiring operation state data, working condition data and environmental condition data of to-be-monitored production equipment as input data; preprocessing the input data, and constructing a digital twin model; real-time monitoring is carried out through the digital twin model, and monitoring data are obtained; based on the monitoring data, fault prediction is carried out through an adaptive threshold fault prediction method, and a fault prediction result is obtained; and the digital twinborn model performs live-action simulation according to a fault prediction result, locates a fault position and gives an alarm to monitoring personnel. According to the invention, efficient and accurate fault prediction of the production equipment is realized, the accuracy of fault location positioning is improved, and the maintenance efficiency is improved.

The invention discloses a failure predicting method and a failure predicting device aiming at an electronic single chip under a hot standby environment. The method comprises the following steps: predicting the failure of an electronic device by using a combinational algorithm of an expert system and a gray prediction model, designing a corresponding knowledge table and realizing a reasoning process by using a quick matching method of rules. The device comprises a controller module, a power supply module, a touch display screen, an LED (Light Emitting Diode) alarm module, a test bench chassis, a data collecting and caching module, a gray prediction module and an expert system module. Through the method and the device, latent failures of the electronic single chip can be efficiently and accurately predicted in real time, so that the guarantee for reliable operation of the electronic single chip of the device can be provided.

The invention relates to an electro-hydraulic proportional valve as well as a high-precision position control system and method and a fault prediction method thereof. The electro-hydraulic proportional valve comprises a valve element, a proportion electro-magnet, a displacement sensor, a current controller, a position controller and other main components, wherein the high-precision position control system mainly comprises a position control loop, a position feedforward link, a current control loop, a pulse width modulation link and the like, and a CNN+BiLSTM network structure is adopted to conduct fault prediction on the electro-hydraulic proportional valve. Compared with the prior art, high-precision position control of the electro-hydraulic proportional valve can be achieved, and accurate fault prediction can be conducted on the electro-hydraulic proportional valve when position control is abnormal through a trained network model.

The invention discloses a penicillin fermentation process fault prediction method based on Attention-LSTM (Long Short Term Memory) of a multivariate time series, which comprises the following steps: firstly, selecting a plurality of related process variables in a penicillin fermentation process through Pearson correlation analysis, then endowing implicit vectors at different moments of an input sequence of the LSTM with different weights through an Attention mechanism, the neural network prediction model is enabled to be more effective in processing long-time sequence input, and fault prediction modeling of the penicillin fermentation process is realized. According to the method, the fault prediction model combining the attention mechanism and the LSTM is adopted to perform fault prediction on the penicillin fermentation process, so that the problem that important time sequence information is easily ignored when the existing LSTM processes long sequence input is solved, and the fault prediction based on the LSTM is more accurate.

The invention discloses a complex equipment IETM system based on digital twinning. The complex equipment IETM system comprises the following steps that S1, multi-source heterogeneous data are collected and preprocessed; s2, constructing a multi-scale space-time coupled digital twin model to realize real-time modeling of equipment; s3, utilizing non-Euclidean space mapping to establish a dynamic evolution track of the equipment; s4, the information entropy is calculated and the model parameters are dynamically adjusted by monitoring the equipment state in real time; s5, generating a fault prediction and maintenance scheme, and optimizing the operation state of the equipment; s6, displaying an equipment state and a maintenance suggestion through an IETM system, and providing equipment management support; and S7, continuously optimizing the twin model by the system. According to the invention, the equipment maintenance precision is improved, and the use efficiency, the maintenance convenience and the information acquisition accuracy of the equipment are improved in real time.

The invention relates to a switch cabinet with a built-in intelligent management and control system, through integration of a sensor network module, a data acquisition module, an intelligent processing module, a remote monitoring module and an active safety protection module, conversion from passive maintenance to active management and control is realized, and the switch cabinet is equipped with various sensors, so that the operation state of equipment can be monitored in real time; historical data are generated through timestamp records, and the intelligent processing module predicts the service life and the fault risk of the equipment in real time by applying a health management algorithm and a deep learning algorithm, identifies different fault modes and sends out an alarm signal; the active safety protection module comprises an electric power cut-off device, a temperature overrun protection unit and an emergency power supply unit, and can quickly cut off a power supply or start a cooling measure when abnormal parameters are detected, so that the equipment safety is ensured; and the intelligent level and the reliability of the switch cabinet are improved.

The invention discloses a system and a method for monitoring state of an escalator. The system comprises a signal sensing sub system, a data acquisition sub system and a monitoring and diagnosing main system, wherein the signal sensing sub system is used for obtaining state information, in an operation process, of the escalator; the data acquisition sub system is used for acquiring and obtaining corresponding original state information after pre-processing the obtained state information, and storing the original state information; and the monitoring and diagnosing main system is used for carrying out online monitoring, early-warning and alarm processing after carrying out analysis and feature extraction on the original state information to obtain a real-time state feature vector, and carrying out self-learning type intelligent diagnosing and fault predicating on the state feature vector by combining with historical fault data and / or expert knowledge base. The system can be used for realizing comprehensive online monitoring of the escalator, can be used for accurately carrying out intelligent diagnosing and fault predicating, and can be widely applied to the monitoring industry of the escalators, moving sidewalks and elevators.

The invention discloses an elevator fault prediction method based on combination of a proportional risk model and machine learning. The elevator fault prediction method is used for predicting the remaining life of an elevator. The hybrid method comprises the following steps: firstly, analyzing a relationship between life and a covariable by using a proportional risk model to obtain an accumulative risk function, and calculating to obtain a life estimated value; then modeling is carried out on the life estimation value and the fault interval time sequence based on a machine learning algorithm, the remaining life is obtained through prediction, and the method comprises the following steps that a data set is imported, and the data set comprises elevator parameter data and elevator maintenance data; extracting a covariable influencing the life of the elevator, a deletion state and the life of the elevator from the elevator parameter data and the elevator maintenance data; a risk function estimated life is calculated, a sub-model 1-COx proportional risk model (WeibullAFTFitter Weibull accelerated failure model) is used, a covariable which affects the life of the elevator and is extracted from elevator parameter data and elevator maintenance data, a deletion state and the life of the elevator are used as input, and the risk function estimated life is output; extracting a historical maintenance time sequence from the elevator maintenance data; and predicting the remaining life of the elevator, and outputting the predicted remaining life of the elevator by using the output of the sub-model 1 and the historical maintenance time sequence extracted from the elevator maintenance data as input by using a sub-model 2-machine learning model (support vector regression model).

The invention discloses a 5G slice fault prediction method and device and computing equipment, and the method comprises the steps: collecting to-be-predicted network slice data, and dividing a slice physical connection graph and a slice resource logic relation graph; converting the slice physical connection graph into a first adjacency matrix and a first feature matrix, and converting the slice resource logic relation graph into a second adjacency matrix and a second feature matrix; inputting the first adjacency matrix, the first feature matrix, the second adjacency matrix and the second feature matrix into a space-time multi-graph convolutional network model, and predicting fault information of the historical network slice data. Through the above mode, potential faults of 5G slices can be predicted by using the space-time multi-graph convolutional network model, and the space-time relationship of the slice topology network is considered, so that the faults can be found automatically and accurately.

The invention relates to the technical field of power plant inspection, and discloses a comprehensive safety inspection method for a smart power plant, which comprises the following steps: S1, arranging various sensors and pulse signal devices on each power device in the power plant, regularly collecting operation data and pulse reflection signal frequency spectrum of each power device, and establishing a normal operation state set of the devices; and S2, generating a visual three-dimensional map of the power plant according to the data of the sensor and the pulse reflection signal spectrum, marking an image model and a number of each device in the map, and mapping the accurate position of the device model in an actual scene to the map in an equal-proportion splicing mode. By introducing the equipment health index and residual life prediction model, the running state of the equipment is evaluated in real time, potential faults are predicted in combination with historical data, the service life of the equipment is prolonged, fault prediction is more accurate, predictive maintenance tasks are generated in advance, and serious faults are avoided.

The application relates to the technical field of transformer fault prediction, and particularly relates to an AI-based power engineering safety quality intelligent diagnosis system, which comprises an acquisition module, a plurality of normal data, a plurality of fault data and a plurality of expansion data output by a generative adversarial network; an analysis module for acquiring valid values and invalid values of each expansion data; a determination module for determining a reserved value of each expansion data according to the valid values and the invalid values of each expansion data; and a training module for constructing a training set based on the plurality of normal data, the plurality of fault data and the plurality of expansion data after elimination, and training a fault prediction model according to the training set, wherein the reserved value and the probability of elimination of the corresponding expansion data are in a negative correlation relationship. The application can screen out redundant data and heterogeneous data in the expansion data, so that the fault prediction ability of the trained fault prediction model is improved.

The invention discloses an offshore wind power device control method based on an FPA-BP neural network, and the method comprises the steps: (1) collecting and preprocessing the data of an offshore wind power device, and building a training sample; (2) establishing an FPA-BP neural network model of the oil temperature of a gearbox, and training a BP neural network model by taking the training sample as an input quantity of an improved flower pollination algorithm; (3) obtaining a residual feature vector between the output of the BP neural network model and the real-time oil temperature of the gearbox; (4) obtaining the state of the gearbox by using the residual feature vector and a random forest algorithm; and (5) controlling the offshore wind power device according to the state of the gearbox. The invention further discloses an offshore wind power device control system based on the FPA-BP neural network. The improved flower pollination algorithm is adopted to optimize the BP neural network, and the random forest algorithm is adopted to monitor the state of the marine gearbox; and a offshore wind turbine generator participates in system frequency modulation through virtual inertia control, so that the stability of the offshore wind power device is ensured.

The invention relates to a failure early-warning method of an engineering structure, and belongs to the technical field of failure analysis of the engineering structure. The method comprises the steps of firstly, calculating an average young modulus of the engineering structure by means of hypothetic calculation young modulus of the engineering structure, a node displacement matrix, calculated by finite element software, of the engineering structure and an actual node displacement matrix, acquired by measurement, of the engineering structure; and finally, performing corresponding failure early-warning on the engineering structure according to contrast between the average young modulus and a safety young modulus of the engineering structure. By calculating the average young modulus of the engineering structure, the integral state of the engineering structure can be accurately and comprehensively reflected, failure early-warning is performed on the engineering structure in the running process and in the failure process, and an accident is prevented; and meanwhile, failure forecast can be accurately performed on the next working condition of the engineering structure, and the working safety and stability of the engineering structure are improved.

A method and apparatus for predicting failure of a wind turbine are provided. The method includes: initializing the fan model of the fan; periodically updating the fan model parameters of the fan model according to the current environmental conditions and the current actual fan state parameters of the fan; A fan model parameter change model; based on future environmental conditions at a future moment, using the fan model parameter change model to predict the fan model parameters at the future moment; according to the historical fan model parameters and corresponding historical fan faults, a fan fault model is established; According to the predicted wind turbine model parameters and the wind turbine failure model, the failure of the wind turbine in the future is predicted. According to the present invention, it is possible to accurately predict the failure of the fan.