5results about How to "Improve troubleshooting performance" patented technology

The invention discloses a reusable launch vehicle maintenance logic decision method based on FMEA and TOPSIS methods, and the method comprises the steps: carrying out the structural decomposition analysis of a reusable launch vehicle system, and determining a device which may have a fault; fMEA analysis is carried out on equipment which may have faults, an FMEA table is compiled, fault modes, fault reasons and fault influences of all the equipment are clarified, FMEA analysis results are analyzed, evaluation indexes are constructed for all the equipment, and the importance degree of all the equipment is determined; according to the importance degree of the equipment, calculating the importance degree sorting ratio of the equipment, dividing the equipment which possibly breaks down into three classes, and determining an equipment maintenance mode for each class of equipment by adopting a corresponding RCM logic decision process; and an entropy weight TOPSIS method is adopted to determine an optimal maintenance mode, so that the provided maintenance decision achieves economic benefit maximization on the basis of meeting related requirements of maintainability and reliability, and industrialization and large-scale development of related technologies in the future is facilitated.

The invention provides a cross interconnection cable fault diagnosis method and system based on improved Bayesian optimization XGBoost, and aims to solve the problems of insufficient precision and low efficiency of an existing cable fault detection method in a complex environment. Firstly, a Bayesian optimization algorithm is improved, for a Gaussian process in a prior function, a Marton kernel function and a square index kernel function are multiplied and compounded to serve as a kernel function, an improved Markov chain Monte Carlo method is used for optimizing parameters of the kernel function, and secondly, for an acquisition function, a kernel function is obtained. And if yes, adjusting parameters in the traditional confidence boundary strategy are improved. And finally, performing intelligent search and optimization on the hyper-parameters of the XGBoost by using an improved Bayesian optimization algorithm, thereby effectively improving the prediction performance and generalization ability of the model, and realizing efficient and accurate diagnosis of the fault of the cross interconnection cable. According to the implementation of the method, the automation level of cable fault processing can be improved, the operation and maintenance cost is reduced, and the method has important practical application value and popularization prospects.

This invention discloses a multimodal gearbox fault diagnosis method based on deep transfer learning, addressing the problem of poor gearbox fault diagnosis capability under unlabeled sample conditions, belonging to the field of gearbox fault diagnosis technology. The method includes: collecting raw vibration signals under different operating conditions, defining them as source and target domains; fusing multimodal information in the time and frequency domains using a data-level fusion method and dividing the collected signals into samples; constructing a deep multimodal adversarial transfer network model, extracting fault information features from the source and target domains through iterative adversarial training to adapt to the joint probability distribution of the source and target domains, and utilizing the abundant fault label information in the source domain to ensure accurate fault category discrimination; finally, obtaining a trained transfer diagnosis model for the target domain. This method is applicable to gearbox fault diagnosis under different operating conditions, i.e., transfer diagnosis between different operating conditions or different fault types, exhibiting high accuracy and good generalization performance.

The utility model discloses a high-precision quick-response electro-hydraulic actuator which comprises an oil tank, a plunger pump, a servo motor, a one-way valve, a pressure limiting valve, a hydraulic lock, a three-position four-way electromagnetic valve, an oil cylinder and an electric controller, the plunger pump is driven by the servo motor, an inlet of the plunger pump is connected with the oil tank, and an outlet of the plunger pump is connected with a port P of the three-position four-way electromagnetic valve through an oil inlet pipe; a one-way valve and a flow sensor are connected to the oil inlet pipe in series, a T port of the three-position four-way electromagnetic valve is connected with the oil tank through an oil return pipe, an inlet of the pressure limiting valve is connected to a pipeline between the one-way valve and the plunger pump, an outlet of the pressure limiting valve is connected with the oil return pipe, and an A port and a B port of the three-position four-way electromagnetic valve are connected with two P ports of the hydraulic lock through oil pipes in a one-to-one mode. Two A ports on the hydraulic lock are respectively connected with two cavities of the oil cylinder in a one-to-one mode through pressure oil pipes, and the two pressure oil pipes are respectively connected with a pressure sensor in series and are further provided with a displacement sensor. The electro-hydraulic actuator can achieve high stability, high precision and quick response.

The application discloses a kind of complex equipment fault diagnosis methods based on polynomial improved graph convolution network.It includes the following steps: (1) the vibration signal of complex equipment operation is collected;(2) using cross-correlation coefficient, construct multi-objective fitness function, combine particle swarm optimization algorithm to optimize the selection of variational mode decomposition parameters;(3) according to the parameter obtained by optimization, the vibration signal is decomposed by variational mode, obtains several modal components and reconstructs to obtain denoising signal;(4) the signal after reconstruction is divided to construct graph;(5) the graph structure is input into the graph convolution model improved by Hermite polynomial to complete the diagnosis of fault.The application is used for the fault diagnosis of complex equipment, uses modal decomposition to denoise signal and improves the graph convolution model, improves the accuracy of diagnosis, and is suitable for the technical field of complex equipment fault diagnosis.