Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

34 results about "Actuator fault detection" patented technology

Aircraft actuator fault detection and diagnosis method based on depth random forest algorithm

ActiveCN108594788AAccurately describe input and output characteristicsQuick checkElectric testing/monitoringData setFeature extraction
The invention discloses an aircraft actuator fault detection and diagnosis method based on a depth random forest algorithm. The method includes: firstly, summarizing the fault mode of an aircraft actuator; establishing an RBF neural network, and collecting the input and output data of the aircraft actuator under the normal working condition to serve as training data, and training the parameters inthe neural network model to obtain analysis redundancy of the monitored actuator; analyzing the residual data of the output signals by collecting the output of the actual actuator and the neural network model, and after the feature extraction, inputting the feature data set into a trained depth random forest multi-classifier for fault mode recognition. According to the invention, the complex nonlinear input and output relation of the aircraft actuator can be accurately simulated by the neural network, the fault mode is accurately recognized by a depth random forest strong classifier, and moreover, the method has the advantages of parallel calculation and high running speed, can be integrated into a flight management computer of an aircraft, realizes the online real-time monitoring, and the accuracy and the efficiency of fault diagnosis of the aircraft actuator are improved.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Dynamic-actuator aircraft attitude distributed type fault-tolerant control system

The invention discloses a dynamic-actuator aircraft attitude distributed type fault-tolerant control system. The system comprises an actuator fault detection and identification unit, an auxiliary system based on an observer and an inversion fault-tolerant control algorithm based on order filtering. According to the distributed type fault-tolerant control system, the actuator fault detection and identification unit is used for obtaining fault information of actuators in real time, the self-adaptive sliding-mode observer is obtained according to an attitude angular speed ring, the observer has strong robustness, an undetermined or interference upper bound does not need to be known, and control surface damage fault information an interference information are both hidden in the observer; a fault-tolerant controller is obtained based on an observer model. Robustness fault-tolerant control over various faults of different types under the multi-fault condition is achieved, the fault-tolerant control system is applied to near-space vehicle attitude stable control and tracking control under the condition of faults of the actuators and the control surface, flying attitude robustness fault-tolerant control is achieved, and good control performance and effect are achieved.
Owner:SHANDONG JIELIER FERTILIZER CO LTD

Multi-model-based high speed train suspension system multi-actuator fault detection and isolation method

The invention provides a multi-model-based high speed train suspension system multi-actuator fault detection and isolation method. The method involves a first bullet train, a trailer and a second bullet train and comprises the following steps that (1) a suspension system, of a two-bullet-train and one-trailer structure, of a train is modeled to obtain a suspension system model; (2) a fault model is built for each actuator of the suspension system of the two-bullet-train and one-trailer structure; (3) a sliding-mode observer matched with each fault model is arranged based on the corresponding fault model, and the corresponding residual quantity is generated; (4) a fault warning threshold value is generated according to the train operating environment and suspension system working conditions, and a logic controller is used for decision making for all residual quantities to judge whether an alarm needs to be given out or not and point out the fault occurrence position. The application of the fault detection and isolation technology is the effective way for improving the system reliability, and an alarm is given in time when a fault occurs, particularly, the fault occurrence position is pointed out when the multiple actuators break down, and fault screening and system maintenance are facilitated.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Delta operator-based fault detection method for actuator of boost converter

ActiveCN112733320AContinuous performanceAvoid Numerical InstabilityDesign optimisation/simulationComplex mathematical operationsControl engineeringPerformance index
The invention relates to the technical field of fault diagnosis, and discloses a delta operator-based fault detection method for an actuator of a boost converter, which comprises the steps of establishing a boost converter circuit model, and constructing an augmentation vector; giving a general system model containing external interference and actuator faults; designing an unknown input observer, constructing an augmentation vector, and obtaining a corresponding dynamic estimation error system; for a dynamic estimation error system, giving a sufficient condition meeting an H-infinity performance index, and designing a fault observer parameter; and setting a threshold Jth according to a designed observer, constructing a residual evaluation function, and judging whether the system has a fault or not through decision logic. According to the fault detection method designed in the invention, the error dynamic system satisfies the following conditions: (1) the system is asymptotically stable in the absence of faults and interference; and (2) when the system has faults and interference, a certain H-infinity performance index is satisfied under a zero initial condition, and actuator fault detection of the boost converter circuit system can be completed.
Owner:HUAIYIN INSTITUTE OF TECHNOLOGY

A Fault Detection, Diagnosis and Performance Evaluation Method for Redundancy Aileron Actuator

The invention discloses a fault detection, diagnosis and performance evaluation method for a redundant aileron actuator. According to the method, fault detection, diagnosis, evaluation and real-time detection of the actuator are performed by means of an input order signal, an output displacement signal, a force motor current signal and aerodynamic loading data of the actuator; the fault detection is realized by a two-stage neural network, a first neural network is used as a system observer and is matched with actual output to acquire a residual error, and a second neural network outputs a self-adaptive threshold value synchronously; the fault detection is realized by the system observer and a force motor current observer; a time domain feature is extracted from a residual error signal and output to a self-organizing mapping neural network, and a minimum quantization error is acquired and normalized to a health degree, so that the actuator performance is evaluated; and on the basis of fault detection, the aerodynamic loading data is introduced, by means of a specific input order spectrum, the system observer and the neural network with the self-adaptive threshold value are trained, and the real-time fault detection is realized.
Owner:北京恒兴易康科技有限公司

A Fault Detection and Diagnosis Method for Aircraft Actuators Based on Deep Random Forest Algorithm

The invention discloses an aircraft actuator fault detection and diagnosis method based on a depth random forest algorithm. The method includes: firstly, summarizing the fault mode of an aircraft actuator; establishing an RBF neural network, and collecting the input and output data of the aircraft actuator under the normal working condition to serve as training data, and training the parameters inthe neural network model to obtain analysis redundancy of the monitored actuator; analyzing the residual data of the output signals by collecting the output of the actual actuator and the neural network model, and after the feature extraction, inputting the feature data set into a trained depth random forest multi-classifier for fault mode recognition. According to the invention, the complex nonlinear input and output relation of the aircraft actuator can be accurately simulated by the neural network, the fault mode is accurately recognized by a depth random forest strong classifier, and moreover, the method has the advantages of parallel calculation and high running speed, can be integrated into a flight management computer of an aircraft, realizes the online real-time monitoring, and the accuracy and the efficiency of fault diagnosis of the aircraft actuator are improved.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Secondary chemical reactor actuator fault detection method based on function observer

ActiveCN113189973AReduce online computing timeMeet online fault detectionProgramme controlElectric testing/monitoringChemical reactionChemical reactor
The invention discloses a secondary chemical reactor executing mechanism fault detection method based on a function observer. The method comprises the following steps of: firstly, constructing a mathematical model of a system according to the principle of a secondary chemical reactor, and converting the mathematical model into a state equation in a standard form; according to a state equation of the secondary chemical reactor, giving a general form when the secondary chemical reactor has external disturbance and an execution mechanism has a fault; designing a function observer, and giving an error dynamic variance, and a decision logic for judging whether the system breaks down or not; giving a sufficient condition for asymptotic stability of an error dynamic system, and obtaining a fault detection observer parameter according to the sufficient condition; and performing secondary chemical reactor actuator fault detection by using a fault detection observer according to the decision logic. The fault detection method designed in the invention has robustness to unknown input and relatively high sensitivity to faults, does not need to calculate a threshold value, reduces online calculation time, and can complete fault detection of the execution mechanism of the secondary chemical reactor system.
Owner:HUAIYIN INSTITUTE OF TECHNOLOGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products