38results about How to "Troubleshooting Troubleshooting Issues" patented technology

The invention relates to an industrial process fault diagnosis method based on a direction kernel partial least square. The method is characterized in that historical normal data of an input variable and an output variable of an industrial process is acquired, wherein a fault is easily generated in the industrial process; an operation based on the direction kernel partial least square is performed on the historical normal data; a control limit of Hotelling statistics of the historical normal data and a control limit of a squared prediction error of the historical normal data are calculated; sampling data of the input variable of the industrial process is collected and the operation based on the direction kernel partial least square is performed on the sampling data so as to acquire process monitoring statistics of the sampling data and a squared prediction error of the sampling data are obtained; when the process monitoring statistics control limit of the sampling data or the squared prediction error of the sampling data exceeds the control limit, the sampling data possesses one kind of fault; historical fault data of a known fault type is acquired; reconstruction based on the Hotelling statistics and reconstruction based on the squared prediction error are performed on the historical fault data of the known fault type and a fault type of the sampling data is determined.

The invention relates to an industrial process fault diagnosis method based on a direction kernel partial least square. The method is characterized in that historical normal data of an input variable and an output variable of an industrial process is acquired, wherein a fault is easily generated in the industrial process; an operation based on the direction kernel partial least square is performed on the historical normal data; a control limit of Hotelling statistics of the historical normal data and a control limit of a squared prediction error of the historical normal data are calculated; sampling data of the input variable of the industrial process is collected and the operation based on the direction kernel partial least square is performed on the sampling data so as to acquire process monitoring statistics of the sampling data and a squared prediction error of the sampling data are obtained; when the process monitoring statistics control limit of the sampling data or the squared prediction error of the sampling data exceeds the control limit, the sampling data possesses one kind of fault; historical fault data of a known fault type is acquired; reconstruction based on the Hotelling statistics and reconstruction based on the squared prediction error are performed on the historical fault data of the known fault type and a fault type of the sampling data is determined.

The invention discloses a fault diagnosis method for an intelligent substation considering the tampering of fault information in a control center. Firstly, a fuzzy C-means clustering algorithm is used to find suspected faulty components, and then remote control is performed by calculating the grouping coefficient of the voltage sampling value of each suspected faulty component. The degree of measurement uncertainty is evaluated, and then the input data of the faulty component identification model is determined. Finally, a faulty component identification model based on the multivariate pulse neural membrane system and its corresponding multivariate pulse matrix reasoning algorithm are proposed, and the suspected faulty component is obtained by solving Fault diagnosis results. The invention can not only effectively solve the fault diagnosis problem of the intelligent substation under the condition that the fault information of the control center is tampered with, but also solve the problem of high uncertainty and inaccuracy of the fault information caused by the tampering of the fault information which cannot be handled by the existing methods .

The invention relates to a multiple sectioned Bayesian network-based electronic circuit fault diagnosis method. Common electronic circuit fault diagnosis methods include a fuzzy set fault dictionary method, a neural network approach, a Bayesian network method and the like, and have low fault resolution, interpretability and real-time property. The method comprises the following steps of: setting two adjacent fault diagnosis reasoning credibility threshold parameters, and determining the number of intelligent agents; obtaining Bayesian subnetwork structures, mapping a fault cause source to each Bayesian subnetwork, and learning credibility condition probability parameters among nodes of a Bayesian subnetwork model by using an expectation-maximization (EM) algorithm; using nodes corresponding to overlapped signals as overlapped subareas of the network to form a complete multiple sectioned Bayesian network (MSBN) so as to construct a linked junction forest; and inputting respective k target characteristic signals serving as observation evidence into each Bayesian subnetwork. A spatial multi-source information fusion method is adopted, the fault diagnosis capacity of a system is improved, the method is suitable for complicated and uncertain systems, and the fault diagnosis accuracy and speed are greatly improved.