16 results about "Residual generator" patented technology

The invention discloses a fault detection method for a ship power condenser system based on multi-scale feature fusion, relates to the fault detection method for the ship power condenser system based on the multi-scale feature fusion, and belongs to the field of fault diagnosis and safety monitoring of ship power systems. The objective of the invention is to solve the problems of insufficient detection precision and high false alarm rate of a traditional fault diagnosis method. The method comprises the following steps: step 1, acquiring input and output information of a condenser system; 2, constructing a multi-scale feature extraction model; 3, obtaining a trained multi-scale feature extraction model and parameters; 4, inputting online data of the condenser system into the trained multi-scale feature extraction model, and outputting predicted values of the liquid level and the vacuum degree of the condenser by the trained multi-scale feature extraction model; the residual generator obtains an online prediction error signal based on the prediction value; and step 5, performing fault diagnosis based on the online prediction error.

The invention provides a distributed state monitoring and fault diagnosis method for a DC micro-grid. Belongs to the technical field of DC micro-grids, and solves the technical problem that the existing state monitoring method in practical application cannot accurately monitor the DC micro-grid state with load disturbance, process uncertainty and measurement noise at the same time. According to the technical scheme, the method comprises the following steps: a, establishing a distributed state space model of each power generation unit in the DC micro-grid; b, designing a time-invariant parameter matrix of the distributed observer by using a full-rank decomposition technology, and determining a time-varying parameter matrix of the distributed observer under the meaning of a minimum mean square error; and c, constructing a distributed residual generator based on local state monitoring. The method has the beneficial effects that the difficulty of high false alarm rate caused by fault propagation is overcome, the communication calculation amount is reduced, the risk of network attack is reduced, and the system has higher reliability and expandability.

This invention discloses a distributed fault detection method for large-scale industrial processes based on subspace identification. A fault detection unit is established on each subsystem of the large-scale system. Local residual generators are directly identified using process data from local and neighboring industrial subsystems, and the residual covariance matrix under healthy conditions is estimated. Actuator faults in neighboring industrial subsystems are decoupled, enabling the detection of faults in both local and neighboring industrial subsystems. Using this invention, a fault detection unit can be constructed within each industrial subsystem using only local and neighboring data, achieving high-performance fault detection for both local and neighboring industrial subsystems. This method boasts high detection rates, low false alarm rates, and low false negative rates, reducing computational and data transmission burdens and making it suitable for dynamic industrial processes.

The application discloses a satellite attitude control system event-triggered STF fault detection method, and belongs to the technical field of detection, which comprises the following steps: establishing a fault model of a satellite attitude control system; introducing an event-triggered mechanism; adopting an STF method to design an event-triggered fault detection filter; obtaining an estimation error dynamic equation and a residual signal through linearization processing of the fault detection filter, realizing complete decoupling of the residual signal and the event-triggered error; converting a design problem of a residual generator into solving a gain matrix of the fault detection filter; calculating a residual evaluation function and comparing the residual evaluation function with a threshold value to judge whether a fault occurs or not. The application utilizes the STF method to design the fault detection filter, can enable the system to keep the tracking ability to a sudden state when reaching a stable state, adopts a brand-new event-triggered framework, realizes complete decoupling of the residual signal and the event-triggered error, and effectively improves the resource utilization rate under the premise of guaranteeing the system performance.

The invention discloses an optimization design method for a residual generator of a dynamic control system in a process industry, in order to solve the problems of a small fault detection time window and low fault detection sensitivity reflected by the residuals of an existing online residual signal generator applicable to a dynamic system. The invention targets two scenarios, namely, a known and an unknown mechanism model of a controlled object, and performs a unified optimization design based on the residuals of the two scenarios. The controlled system can be modeled as a linear dynamic system and its state space model is consistent. The residual signal is written as a parameterized form of a left coprime decomposition correlation matrix with the controlled system. The residual generator is designed offline through an optimization strategy, and is driven by input and output data collected online in real time, thereby realizing online optimal residual generation. The invention is suitable for residual generation of dynamic control systems in process industries.

The application relates to a reversible left manifold-based closed-loop system fault diagnosis method and system, which comprises the following steps: step 1, constructing a reversible left manifold according to a reversible neural network, and parameterizing a nonlinear closed-loop system; step 2, constructing a reversible residual generator of a nonlinear closed-loop control system according to the reversible neural network; and step 3, obtaining online data of the nonlinear closed-loop system, and performing online fault diagnosis based on a test statistic of the residual generator and a set diagnosis threshold. Compared with the prior art, the application has the advantages of low memory cost requirement and high fault diagnosis precision.

The application discloses a dynamic system data-driven fault detection method based on distributed typical correlation analysis, and comprises the following steps: in an offline process, historical data collected by sensors in each subsystem under normal working conditions is used to construct a centralized CCA residual generator; according to the network topology structure among the subsystems in the dynamic system, the weight coefficients of information transmission among the subsystems are determined based on an average consistency algorithm, an iteration matrix for solving CCA parameters of each subsystem is constructed, and the centralized CCA residual generator is converted into a distributed CCA residual generator; the CCA parameters of each subsystem are solved; in an online process, each subsystem uses the solved CCA parameters to construct a CCA-based residual generator, and the residual signals of each subsystem are distributedly fused based on the average consistency algorithm; finally, a control statistic is designed, a threshold is determined, and distributed optimal fault detection based on data driving in the dynamic system is carried out.

A kind of ship power condenser system fault detection method based on multiscale feature fusion, the present application relates to ship power condenser system fault detection method based on multiscale feature fusion, belongs to ship power system fault diagnosis and safety monitoring field.The present application aims to solve the problem of insufficient detection accuracy and high false alarm rate of traditional fault diagnosis method.Process is as follows:step one, obtain the input and output information of condenser system;Step two, construct multiscale feature extraction model;Step three, obtain trained multiscale feature extraction model and parameters;Step four, input the online data of condenser system into trained multiscale feature extraction model, and trained multiscale feature extraction model outputs the predicted value of condenser liquid level and vacuum degree;Residual generator obtains online prediction error signal based on predicted value;Step five, fault diagnosis based on online prediction error.

The invention provides a double-layer fault diagnosis method and system for an industrial interconnection system, and belongs to the technical field of fault diagnosis of the industrial interconnection system. The method comprises the following steps: firstly, based on a state space model of each subsystem in the industrial interconnection system, deducing input and output data of each subsystem of the industrial interconnection system, and realizing distributed identification of a subspace parameter matrix by using the input and output data of each subsystem so as to give full play to complementary advantages of mechanism modeling and data driving. Secondly, a Granger causality analysis method is used for calculating the coupling connection relation between the subsystems, and distributed optimization of a subspace parameter matrix is achieved in combination with an alternating direction multiplier method; and finally, distributed residual error generator design and residual error evaluation are carried out on the subsystem side, distributed fault detection of the industrial interconnection system is realized, residual error signals of the subsystems are transmitted to a centralized processing unit, and when a fault is detected, a fault source subsystem is found by calculating a comprehensive fault score of each subsystem.

The present invention relates to the technical field of state estimation and fault detection, solves the technical problem that traditional closed-loop fault diagnosis methods cannot effectively decouple control signals and residual signals, and particularly relates to a fault detection method for an uncertain stochastic time-varying system considering output feedback control, including: theoretically modeling using a linear discrete system with model uncertainty to obtain the dynamic mathematical model of the linear discrete system; constructing a closed-loop residual generator based on the dynamic mathematical model for generating residual signals reflecting the system state; designing a fault detection threshold; analyzing the fault detectability, and verifying that the linear discrete system can be effectively identified and located when a fault occurs. The present invention realizes the effective detection and diagnosis of system faults under the condition of norm-bounded model uncertainty, and ensures the minimization of the upper bound of the estimation error variance for each step of recursive calculation, thereby providing a reliable and efficient technical solution for fault diagnosis.

The present invention relates to the technical field of distributed process detection, and more specifically, to a distributed canonical correlation analysis process monitoring method and device based on partial sub-block communication. The present invention includes: dividing training sample data into blocks and determining a topological matrix; performing canonical correlation analysis modeling on each sub-block according to the topological matrix to construct a residual generator; generating a residual vector according to the residual generator and calculating a statistic; performing corresponding partitioning on new sampled data; substituting the partitioned sampled data into the corresponding canonical correlation analysis model respectively to obtain corresponding canonical correlation components; performing fault detection on each sub-block and obtaining the operating state of the sub-block; calculating an overall statistical index FD of all sub-blocks, and determining whether a fault occurs in the process by comparing the overall statistical index FD with a control limit. The present invention has the advantages of improving the sensitivity of monitoring, reducing the computational complexity of process monitoring and the load of data transmission, and realizing the preliminary range positioning of faults, etc.

The present invention relates to a fault monitoring method and system based on a complementary double residual generator of RNN. The monitoring method comprises the following steps: inputting the fault detection process into a front residual generator; obtaining a residual vector through the front residual generator; dividing the residual into a Gaussian residual part and a non-Gaussian residual part through a Gaussianity checker; correcting the non-Gaussian residual part into a Gaussian residual through a back residual generator; inputting the aggregated Gaussian residual into a result diagnostic device, and 2 Statistics are used to diagnose faults. The monitoring system includes a process input module, a front Gaussian residual generation module, a back Gaussian residual generation module and a result output module. The method provided by the present invention can output Gaussian residuals in the case of unknown noise, and finally can be used to diagnose faults through T 2 Statistics are used to diagnose faults, which improves the fault detection rate while ensuring a low fault alarm rate.

A static output feedback control method and storage medium for forklift stability control according to the present invention. The control method includes setting up a fuzzy system model, a singular observer module, a generalized observer module, a residual generator module, and a static output feedback control method module for forklift stability control. The singular observer estimates the state and faults of the system simultaneously; the generalized observer is used to generate a residual signal that is as sensitive as possible to faults and insensitive to disturbances; the residual generator minimizes the sensitivity of the system to disturbances and maximizes the sensitivity to faults; the static output feedback control method for forklift stability control uses the measurable signals such as faults and states provided by the observer to control the dynamic system. The present invention can, after a fault occurs in the system, based on the estimated state and fault vector, ensure the reconfiguration of the control law and restore the performance of the system before the fault as much as possible, greatly improving the lateral stability and active safety of the forklift.

The invention relates to the technical field of state estimation and fault detection, solves the technical problem that a traditional closed-loop fault diagnosis method cannot effectively decouple a control signal and a residual signal, and particularly relates to an uncertain random time-varying system fault detection method considering output feedback control. Comprising the following steps: carrying out theoretical modeling by adopting a linear discrete system with model uncertainty to obtain a dynamic mathematical model of the linear discrete system; constructing a closed-loop residual generator used for generating a residual signal reflecting a system state based on the dynamic mathematical model; designing a fault detection threshold value; and analyzing the fault detectability, and verifying that the linear discrete system can be effectively identified and positioned when the fault occurs. According to the method, effective detection and diagnosis of the system fault are realized under the condition of uncertainty of the norm bounded model, and minimization of the upper bound of the estimation error variance of each step of recursion calculation is ensured, so that a reliable and efficient fault diagnosis technical solution is provided.

The application discloses a neural network-based maglev train suspension system anti-disturbance control method and device, equipment and medium, and relates to the field of transportation, which comprises the following steps: determining a target space model, a target controlled object and a corresponding target nominal controller based on a target state variable and a suspension equilibrium point of a target maglev train, constructing a target loop through Youla parameterization and determining a corresponding target relationship matrix, and determining a corresponding target optimization function based on the target loop; training a parameter prediction model based on an original residual signal output by a residual generator in the target loop, the target relationship matrix and the target optimization function to obtain a target parameter prediction model, determining a prediction control parameter of a dynamic feedback gain based on a real-time residual signal by using the target parameter prediction model, and performing anti-disturbance control on the target maglev train based on the prediction control parameter. The application improves the wideband anti-disturbance capability of the maglev train control system.

The invention discloses a fault detection and detectability analysis method for a high-speed train traction motor, and belongs to the technical field of fault diagnos.The method comprises the steps that firstly, a T-S fuzzy dynamic modeling technology is adopted to construct a traction motor nominal system, and then a stable kernel characterization / stable image characterization and orthogonal projection residual error generator is established; effective detection of multiplicative faults is achieved, and robustness of control input changes is improved in combination with an adaptive threshold strategy. And then, further based on a traction motor fault system influenced by an intrinsic multiplicative fault under closed-loop control, analyzing residual dynamic characteristics by using time-varying K-Gap measurement, and proposing a detectability quantitative evaluation index, thereby forming a complete technical system from a detection method to detectability evaluation. According to the method, efficient multiplicative fault detection is achieved, theoretical analysis and quantitative basis is provided for detectable performance, and the method has remarkable advantages in the aspects of calculation efficiency and engineering applicability.