13 results about "Failure detection and isolation" patented technology

The invention relates to the technical field of inverter control, and provides an MBD-based reinforcement learning inverter control algorithm optimization method, which comprises the steps of S1, establishing a state space model of an inverter, designing a baseline controller of double-loop control, and constructing an MBD simulation platform containing multiple load models; s2, defining a state space of the 12-dimensional state vector, designing a continuous action space, and constructing an adaptive multi-target reward function; s3, training a control parameter optimization strategy by adopting an Actor-Critic algorithm architecture in combination with an experience playback mechanism and a hybrid exploration strategy; s4, establishing a security constraint mechanism of three-layer security protection, designing a fault detection and isolation strategy, realizing a closed-loop online learning strategy of pre-training-transfer learning-online fine tuning, and meanwhile, adopting a self-adaptive updating mechanism; and S5, verifying the optimization effect of the control algorithm through quantitative index evaluation, an experimental verification scheme and a real-time performance requirement test. And the upgrade of inverter control from model driving to data and model cooperative driving is realized.

The present invention provides an aero-engine speed acquisition circuit with fault detection, comprising: a BIT on-line detection circuit, a filtering and limiting circuit, a signal superposition and amplification circuit, a voltage biasing circuit, a comparison and buffering circuit, a processor or a logic unit; the filtering and limiting circuit is used for filtering and limiting the differential signal output by the speed acquisition sensor, the BIT on-line detection circuit is used for generating and conditioning the line detection signal, the signal superposition and amplification circuit amplifies the quasi-sine wave signal and superposes it with the detection square wave signal, the voltage biasing circuit performs a positive bias on the superposed wave signal, the comparison and buffering circuit compares and isolates the superposed wave signal, and outputs a square wave signal with the same frequency to the processor or the logic unit, and the processor or the logic unit performs operations and judgments according to the frequency of the input square wave signal to complete on-line fault detection. The present invention can perform BIT on-line detection on the acquisition circuit at the rear end of the sensor, achieving the purpose of fault detection and isolation.

The invention discloses an intelligent fault diagnosis method and device for a complex aerospace system based on correlation modeling, and relates to the technical field of aerospace system fault diagnosis, and the method comprises the steps: constructing a testability model of the aerospace system; the distinguishing capability of different faults is simplified, and test points are optimized; automatically generating a fault diagnosis strategy based on the optimized testability model; performing simulation evaluation on the fault diagnosis strategy, and counting a fault detection rate and a fault isolation rate; and performing iterative optimization by judging whether the fault detection rate and the fault isolation rate meet preset requirements or not. According to the method, the technical problems of low diagnosis efficiency and insufficient fault detection and isolation accuracy caused by dependence on artificial experience and incomplete static fault tree coverage of complex spaceflight system fault diagnosis in the prior art are solved, intelligentization and precision of complex spaceflight system fault diagnosis are realized, and the fault diagnosis efficiency is improved. And the fault detection rate and the isolation rate are improved.

The present invention discloses a grounding system for a high-voltage switchgear, which relates to the technical field of power systems and solves the problems of poor resistance stability and poor safety in the grounding system of existing high-voltage switchgears. The present invention includes a real-time detection module, an adaptive grounding resistance adjustment module, a high-frequency transient suppression module, a fault detection and isolation module, a grounding current control module, and a telemetry module. The present invention ensures the stability of the grounding resistance under different environmental conditions by connecting multiple sections of controllable resistors in series with the grounding path and automatically adjusting the resistance value in combination with the environmental compensation model. The high-frequency transient suppression module detects and quickly responds to the arc re-ignition to effectively suppress the generation of overvoltage. The fault detection and isolation module monitors the grounding current in real time to prevent the further spread of faults, improving the reliability and safety of the system. The present invention greatly improves the resistance stability and safety of the existing grounding system.

The application discloses an ultrasonic transducer group adaptive repair system and method, relates to the technical field of ultrasonic vibration and adaptive control, and comprises fault detection and isolation, adjacent transducer compensation, adaptive frequency matching, phased compensation and an intelligent optimization and learning module. Through real-time monitoring of transducer power, frequency and vibration state, once a fault transducer is detected, the fault transducer is immediately isolated, and the power and frequency of adjacent transducers are dynamically adjusted according to the fault position to realize compensation; meanwhile, frequency matching and phase modulation are carried out by using an FPGA, so that the remaining normal transducers remain vibration consistency. The system records and optimizes repair data each time through machine learning, has the advantages of rapid fault response, high compensation accuracy and strong scalability, and can be widely applied to the fields of industrial nondestructive testing, medical ultrasonic imaging and the like.

The invention discloses a fault comprehensive diagnosis logic generation method considering multiple working conditions, and belongs to the field of fault diagnosis. The method specifically comprises the following steps: for equipment S with a fault to be detected, extracting a fault mode of each key component and obtaining associated state monitoring parameters; then, dividing the operation state of the equipment S into a plurality of typical working condition sets; for each working condition, setting a fault criterion according to a fault mode and a state monitoring parameter; thirdly, further decomposing the complex fault criterion into a plurality of mutually independent test units; when the test unit triggers an alarm, it is indicated that the equipment S breaks down, and detection is carried out. And finally, constructing fault isolation logic by using the test number of the test unit and combining the mapped fault criterion, and matching the fault isolation logic with the characteristic mode of each fault mode so as to judge the specific fault and realize fault isolation. And finally generating comprehensive diagnosis logic of the fault. According to the invention, fault detection and isolation of a complex system under various operation conditions are realized.

This application discloses a method, device, and medium for fault detection and isolation of complex spacecraft equipment, relating to the field of fault identification. The method includes: inputting the current operating status data of the complex spacecraft equipment into an operating status prediction model for prediction to obtain the future operating status data distribution; the operating status prediction model is obtained by training a variational Koopman anomaly detector using a time-series training sample set of the complex spacecraft equipment; and calculating the prediction error matrix and the corresponding T based on the current operating status data and the future operating status data distribution. 2 The system calculates the values ​​and SPE statistics, and then determines the operating state of complex spacecraft equipment based on preset limits. When the operating state indicates a fault, it calculates the deviation score of each operating state variable and isolates the fault to determine the fault variables of the operating state. This application realizes effective fault detection and fault variable screening for complex spacecraft equipment.

The invention relates to the technical field of electrical variable test and analysis, in particular to a distribution box fault diagnosis and prediction method based on an AI algorithm. In order to solve the limitation of a traditional power distribution network fault diagnosis method in a complex and changeable environment, the method combines high-frequency signal processing and an artificial intelligence algorithm, and an efficient fault detection and isolation scheme is provided. The method comprises the following steps: 1, high-frequency signal injection and collection: injecting a preset high-frequency signal at a key node of a power distribution network and collecting a reflection signal; 2, data feature extraction and transformation: performing feature extraction on the signals by using short-time Fourier transformation and wavelet transformation; 3, fault classification and diagnosis: identifying fault types and predicting trends through a convolutional neural network and a long short-term memory network; 4, graph theory path simulation analysis: optimizing a fault isolation path through a graph theory model; the simulation module is used for simulating and optimizing system response and accuracy through a computer. And when the simulation of the system is insufficient, the performance is optimized by further adjusting the AI algorithm and signal processing. According to the solution, the accuracy and adaptability of fault processing are improved, and stable operation of the power distribution system is ensured.

The present invention discloses a modular electrolyte circulation air battery pack with fault isolation function, which belongs to the field of energy storage and conversion technology, and includes: several layers of battery modules, fixed modules, electrolyte circulation and purification systems, fault detection and isolation systems and battery management systems. The battery module consists of a vertical support frame and a single layer of air battery cells. The fixed module realizes mechanical fixation and electrical interconnection. The electrolyte circulation and purification system maintains the purity of the electrolyte. The fault detection and isolation system monitors and isolates the faulty unit in real time. The battery management system coordinates operation and regulates parameters. The present invention reduces the risk of flow channel blockage through a closed-loop circulation purification system, and the fault isolation mechanism avoids the spread of faults. The modular design supports plug-and-play, and the layered pump group and dynamic regulation adapt to the needs of multiple scenarios, improve energy conversion efficiency and application flexibility, and is suitable for a variety of air battery systems.

The application provides a horizontal flight direction fault-tolerant control and reconstruction method for an aircraft under rudder surface failure, designs a horizontal flight direction fault-tolerant controller, calculates an optimal control law through a nominal model of the aircraft and a rudder surface failure model, and stabilizes the aircraft under external disturbance. Then, a quadruple neural network is used to estimate the optimal control law for all possible failure degrees. When the rudder surface failure occurs, the aircraft can be stably operated. The application provides a horizontal flight direction fault-tolerant control and reconstruction system for an aircraft under rudder surface failure, which is not limited in generality, based on a fault detection and isolation module, a switching mechanism and a flight control system, introduces a horizontal flight direction fault-tolerant controller, and stabilizes the aircraft under external disturbance.

The invention discloses a modularized electrolyte circulating type air battery pack with a fault isolation function, which belongs to the technical field of energy storage and conversion and comprises a plurality of layers of battery modules, a fixing module, an electrolyte circulating and purifying system, a fault detection and isolation system and a battery management system. The battery module is composed of a vertical support frame and air battery units arranged in a single layer, the fixing module realizes mechanical fixation and electrical interconnection, the electrolyte circulation and purification system maintains the purity of electrolyte, the fault detection and isolation system monitors and isolates fault units in real time, and the battery management system operates in a coordinated manner and regulates parameters. The flow channel blockage risk is reduced through the closed-loop circulation purification system, fault diffusion is avoided through a fault isolation mechanism, plug and play is supported through modular design, the layered pump set and dynamic regulation and control adapt to multi-scene requirements, the energy conversion efficiency and the application flexibility are improved, and the system is suitable for various air battery systems.

The application discloses an airborne multi-source fusion navigation dynamic integrity monitoring and alarming method and device and a medium, relates to the field of multi-source fusion navigation dynamic integrity monitoring and alarming, and comprises the following steps: firstly, calculating the separation combination of a multi-source fusion navigation system under a plurality of fault hypotheses; secondly, performing navigation source fault detection and isolation by using a PCA multivariate statistical analysis method according to KF-LS form solutions of the separation combinations; then, verifying the fault navigation source recovery by using a w-detection method for the isolated navigation source, and dynamically regulating and controlling effective navigation source information; finally, calculating the PCA principal component contribution rate under each fault hypothesis to be monitored based on an integrity risk dynamic allocation criterion, dynamically calculating the protection level, and realizing integrity monitoring and alarming. The application can realize dynamic integrity monitoring of airborne multi-source fusion navigation, and can generate an alarm prompt by calculating the system protection level in real time.

This invention discloses a multi-timescale fault detection and isolation method for integrated navigation systems. Targeting integrated navigation systems employing a federated filtering structure, the method acquires state estimation information for each local filtering branch, constructs a residual quantity reflecting changes in consistency between branches, and normalizes this residual by combining it with corresponding uncertainty information to obtain a standardized deviation. Normal fluctuations are suppressed through soft thresholding, and non-negative effective deviations are extracted. Based on the effective deviations, fast-timescale and slow-timescale statistics are constructed respectively, and the impact of operational condition changes on the detection results is mitigated through baseline updates and platform removal processing. Finally, fault detection and isolation conclusions are output based on the joint decision results of the fast and slow-timescale statistics. This invention can balance rapid response to abrupt faults with cumulative perception of gradual faults, and is applicable to local branch fault detection and isolation in multi-source integrated navigation systems.