36 results about "Theory of evidence" patented technology

The invention discloses a high-voltage circuit breaker mechanical fault diagnosis method based on a multi-data fusion technology. A plurality of sensors are mounted on a high-voltage circuit breaker, fault information is acquired by utilizing a data processing algorithm, and by combining typical fault signal feature vectors stored in a fault database, membership degrees that a circuit breaker state belongs to various different typical faults are determined; by introducing a generalized information entropy concept, evidence reliability of each sensor is obtained so as to obtain weighted evidences; and finally, a D-S evidence theory combination rule is adopted to complete fault fusion so as to obtain a decision diagnosis result. According to the high-voltage circuit breaker mechanical fault diagnosis method disclosed by the invention, a weighted evidence theory and the multi-data fusion technology are adopted, not only a result of obtaining each fault membership degree is considered, but also reliability of each evidence is considered, and accuracy of system diagnosis is effectively improved.

The invention discloses an airport runway allocation decision method based on a fuzzy analytic hierarchy process and an evidence theory, belonging to the technical field of runway distribution. The method includes analyzing factors influencing the distribution of the approach and departure runways, and establishing an analytic hierarchy model; according to the specific situation of the current runway distribution problem, defining a triangular fuzzy pairwise comparison matrix of the hierarchical model; constructing the evidences given by different controllers and uncertainty by means of the triangular fuzzy pairwise comparison matrix and the consistency information; comprehensively considering the conflict between evidences and the prior reliability of the controllers, and fusing differentevidences by using an evidence theory; calculating a trust interval of the fusion result and making a decision; finally, comparing the decision result of each decision maker with an execution result,and updating the prior reliability of the controllers for the next runway allocation decision. According to the method, the subjective factors in the runway distribution process are fully considered,and the subjective factors are converted into the uncertainty of the evidence for decision, so that the runway distribution result is more consistent with reality.

The invention discloses a fault diagnosis system based on the evidence theory, and the system comprises a sensor acquisition module, a data preprocessing module, a primary diagnosis module, a comprehensive diagnosis module and a result display module. The sensor acquisition module collects data of transformer parameters through a plurality of sensors. The data preprocessing module is used for carrying out the preprocessing of the data, and the primary diagnosis module is used for carrying out the primary diagnosis of a device according to the preprocessed sensor data. The comprehensive diagnosis module uses the evidence theory to carry out the comprehensive diagnosis of the device according to the primary diagnosis result. The result display module uses an LED display to display the faultdiagnosis result in real time, and performs early warning when the device is diagnosed to have a fault. The beneficial effects of the invention are that the system employs the neural network for processing the sensor data after fuzzification to obtain a primary diagnosis result of transformer fault; the system employs the evidence theory for further diagnosing the transformer fault according to the primary diagnosis result, thereby improving the accuracy of the diagnosis result.

The invention discloses an evidence theory-based electromechanical product simulation model precision improvement method. The method comprises the following steps: 1, carrying out a small amount of test measurement on an electromechanical product, carrying out statistical analysis on measured response data, and analyzing the measured response data by utilizing an evidence theory; 2, establishing amechanical and electrical product simulation model, obtaining a calculation response, and establishing an objective function for identifying an electromechanical product modeling parameter interval range; 3, further dividing the identified modeling parameter interval into a plurality of sub-intervals, and preliminarily allocating a certain modeling parameter probability to each sub-interval; and4, establishing an objective function for identifying a modeling parameter quantum interval probability value by utilizing the electromechanical product simulation model and the allocated sub-intervalprobability, and identifying accurate probability allocation on the modeling parameter quantum interval through an optimization process. According to the method, the value interval and probability distribution of the modeling parameters can be accurately obtained under the small amount of measurement response, and the precision level of the electromechanical product simulation model is effectively improved.

The invention discloses a Dempster-shafer (D-S) evidence theory method capable of achieving micro-blog inclusion traffic information fusion. The D-S evidence theory method includes determining an evidence theory identification framework and proposition space according to traffic congestion degrees; capturing micro-blog contents relevant to traffic information themes according to time windows and road sections to form a micro-blog data collection which is required to be fused; pre-processing the micro-blog data collection; calculating word meaning similarity degrees of description vocabularies of micro-blog data collection traffic states, introducing Chinese language corpus resources and improving calculation accuracy of the word meaning similarity degrees; calculating weighting evaluation of the micro-blog word meaning similarity degrees and constructing a basic probability assignment function of an evidence theory; and subjecting a plurality of micro-blog evidence sources to evidence synthesis according to a Dempster combination rule, determining confidence intervals of propositions in the identification space, and selecting a proposition of the maximum confidence function in the confidence intervals to be a fusion result. By means of the D-S evidence theory method capable of achieving micro-blog inclusion traffic information fusion, the fusion of micro-blog inclusion traffic information can be achieved, and an important data source is provided for the city traffic information collection.

The invention belongs to the field of information retrieval and evaluation and particularly relates to an evidence theory based Chinese microblog credibility evaluation method. Started with intrinsic characteristics of Chinese microblogs, a multidimensional evidence based microblog credibility evaluation method used for integrating three heterogeneous dimensions is provided after measurability and practical tasks of the intrinsic characteristics are taken into account, credibility measuring indexes of Chinese microblog information are systematically ordered and are classified into three high-level dimensions including text information, information sources and information dissemination. Compared with an evaluation method for a single characteristic of web texts or interconnection relation in the prior art, the evidence theory based Chinese microblog credibility evaluation method is more comprehensive and reasonable, is capable of preferring to reliable sources and spreading information widely under the same query condition.

The invention discloses a high-voltage circuit breaker mechanical fault diagnosis method based on a multi-data fusion technology. A plurality of sensors are mounted on a high-voltage circuit breaker, fault information is acquired by utilizing a data processing algorithm, and by combining typical fault signal feature vectors stored in a fault database, membership degrees that a circuit breaker state belongs to various different typical faults are determined; by introducing a generalized information entropy concept, evidence reliability of each sensor is obtained so as to obtain weighted evidences; and finally, a D-S evidence theory combination rule is adopted to complete fault fusion so as to obtain a decision diagnosis result. According to the high-voltage circuit breaker mechanical fault diagnosis method disclosed by the invention, a weighted evidence theory and the multi-data fusion technology are adopted, not only a result of obtaining each fault membership degree is considered, but also reliability of each evidence is considered, and accuracy of system diagnosis is effectively improved.

The present invention is based on the correlation coefficient distance and iterative improved evidence theory fault state identification method, including the steps: first, using multi-sensors to collect data signals during the operation of the equipment, so as to obtain multiple basic probability assignments of the current operation state of the equipment; second Second, calculate the distance between each BPA through the distance of the Correlation correlation coefficient and the distance of the Spearman correlation coefficient to generate a distance matrix; third, assign the corresponding weight to the evidence body based on the distance matrix; fourth, use the generated double weight The weighted average evidence is obtained by performing weighted correction on the original evidence body BPA; fifthly, the weighted average evidence is combined n-1 times according to the proposed iteratively improved new fusion rule to obtain the fusion result. The present invention utilizes the double distance function to optimize the evidence theory and at the same time introduces the idea of ​​iterative improvement to improve the combination rules of the evidence theory, thus solving the problem of information conflict, effectively improving the reliability of fault state identification, and accelerating the fusion convergence speed.

The invention discloses a software system structure safety evaluation method based on evidence synthesis theory, which belongs to the technical field of software safety evaluation; firstly, the system structure model of the certain software system is constructed, and the safety elements involved in the components are fuzzy-mathematicalized Then use the software architecture analysis method to obtain the transition probability of the component and the transition probability of the operation path in the whole system, and then use the Dempster-Shafer (D-S) evidence synthesis theory, combined with the use weight of the software operation path, to calculate the components Perform safety synthesis to obtain the safety level evaluation results of each component, thereby calculating the safety level evaluation results of the running path and the system safety level evaluation results; the present invention uses a bottom-up software engineering analysis method to realize the software system Dynamic security analysis and evaluation.

The invention discloses a network security situation evaluation method and a network security situation evaluation system for improving the application range and accuracy of network security situation evaluation. The method comprises: classifying all security events in a preset time period according to attack type to form at least one event collection; accumulating the attack risk grades of the security events in each event collection respectively, and determining the accumulated values as the rise degree values of the event collections; substituting the risk degree values of the event collections as independent variables into empirical functions fi() corresponding to the event collections to obtain the values of the credibility of the fact that the event collections render a network in an unsecure state; and using the values of the credibility of the event collections as weights of evidences, combining the weights of evidences by using a synthesis rule of the theory of evidence, and obtaining the credibility of the fact that the network is in an unsecure state in the preset time period. Thus, the technical scheme realizes the quantitative evaluation of the security situation of the whole network and improves the application range and accuracy of the network security situation evaluation.

The invention belongs to the field of technical detection, and in particular relates to a method for predicting the failure of a cone crusher. It is characterized in that the method of fuzzy reasoning is used to increase the anti-interference ability of the fault prediction system, effectively reducing the probability of false alarm and the rate of missed detection; in the fuzzification process, the membership function chooses the combination of triangular membership function and trapezoidal membership function It avoids the unreasonable division of the domain of discourse caused by the simple use of the triangular membership function; the evidence theory is used to fuse the reasoning results so that the diagnosis results can make full use of the information of the crusher and the fault prediction results are more reliable; the classification of the membership degree is 1 or 0 It does not participate in the fusion of evidence theory, avoiding the evidence conflict of evidence theory, thus ensuring the feasibility of the algorithm; introducing the trend information of historical data as auxiliary diagnosis, further reducing the missed detection rate of fault prediction and improving the accuracy of fault prediction The overall level.