33 results about "Fuzzy correlation" patented technology

The invention discloses a design intention-oriented product correlation information modeling method. Based on a fuzzy set theory, establishment and quantitative expression of multiple constraint criterions are performed according to a correlation relationship among product parts; each constraint correlation is assigned with a triangular fuzzy number; a part identification frame with the multiple constraint criterions is established; data is extracted from a design knowledge database and is subjected to analysis processing in a multiple constraint criterion sorting fusion mode; a final evidence body of multiple constraint criterion fusion is obtained; fuzzy correlation intensity is defuzzified; comprehensive correlation intensity of products is obtained; and a quantitative product design structure matrix is formed. The method has the advantages of high design accuracy and accordance with a design intention for the problem that the design intention cannot be accurately expressed due to fuzzy and incomplete correlation data in a conventional complicated product correlation information modeling process.

The present invention provides a classification fuzziness analysis method and device. The method includes: screening N pieces of corpus to be marked from the knowledge base; N is an integer greater than 1; respectively receiving M pieces of corpus for each of the N pieces of corpus Classification labeling; M is an integer greater than 1; Each two classification labels in the M classification labels of each corpus are respectively formed into a classification label pair; respectively determine the first fuzzy correlation coefficient of each said classification label pair; according to The first fuzzy correlation coefficients of all the classification label pairs are used to calculate the fuzziness index of each category in the K categories; the K categories are determined according to all the category labels, and K is a positive integer. Through the classification fuzziness analysis method provided by the invention, the objectivity of the fuzziness analysis of knowledge base classification can be improved, so that the reliability of the obtained analysis results is stronger.

The invention relates to a method for positioning a temporary voltage drop source on line by adopting fuzzy similarity match. The method is characterized by comprising the following steps: establishing a node positive sequence voltage match index calculation model by taking the positive sequence voltage of existing nodes of the whole network as a characteristic quantity, and positioning the temporary voltage drop source by utilizing the fuzzy similarity of voltage match indexes and the match index similarity of monitored voltage vectors. The method disclosed by the invention can be used for accurately positioning the temporary voltage drop source by utilizing existing limited monitoring point information. The method disclosed by the invention can be used for calculating the voltage match index of the positive sequence voltage of a node during temporary voltage drop and matching and identifying by utilizing fuzzy correlation degree and a line fault characteristic set established off line, thereby being insensitive to data accuracy. Besides, the method disclosed by the invention can be used for integrally judging and identifying the temporary voltage drop source by simultaneously adopting the information of all monitoring nodes and the information of a network topology, is rich in data source and has certain fault tolerance, and thus high accuracy and universality are achieved in positioning the temporary voltage drop source by utilizing the method.

The present invention provides a method for predicting the quality of medium and heavy plates based on evolutionary fuzzy association rules, which can replace the aftermath of fuzzy association rules with fitting functions, so that the fuzzy association rules can also realize regression prediction on the basis of realizing the classification function Function. The method includes: obtaining fuzzy association rules corresponding to steel rolling data, wherein the steel rolling data is steel rolling data of medium and thick plates; learning the aftermath of the fuzzy association rules, and constructing a fitting on the basis of the aftermath of the fuzzy association rules Function; get the test data, judge whether the test data matches the fuzzy association rules, if they match, use the fitting function generated by the matching rules to make predictions, otherwise, use the weighting of the fitting functions of all fuzzy association rules at the current moment to obtain the prediction results . The invention relates to the technical field of data mining.

A case retrieval method that combines correlation function and D-HS index, including: combined with fuzzy numbers, proposed the concept of fuzzy correlation function and corresponding calculation formula, combined with AHP to propose a similarity measurement method for single-dimensional correlation function combination, compared with Based on the calculation method of full-dimensional correlation function, this method not only ensures the indexing accuracy but also improves the indexing speed in the face of high-dimensional retrieval; it uses the Sigmoid function to perform nonlinear transformation on the data, which effectively solves the problem of the traditional D-HS indexing method due to data The problem of low index accuracy caused by uneven distribution; combining the above improved methods not only improves the rigor and accuracy of the traditional D-HS index, but also avoids the cumbersome calculation of the similarity of the entire instance database instance for the correlation function. To a certain extent, the retrieval utility problem is solved.

The invention relates to an image retrieval method. The method comprises the following steps of extracting color characteristics of an image by using a color histogram, and taking two characteristics such as a color vector of the color histogram and the height of a color column as the retrieval basis; calculating similarity by using the fuzzy membership function in a fuzzy set theory, judging the similarity through alpha fuzzy relation; introducing non-subsampled contourlet transform (NSCT) to extract the texture characteristic of the image at the same time; resolving the image by NSCT; extracting the mean value and standard deviation of sub-band coefficient in multiple directions of different layers and taking the mean value and standard deviation as feature vectors and index of the image in an image library, calculating similarity of the images by using the fuzzy membership function in a fuzzy set theory, wherein because the multiscale, multidirectionality and translation invariance property, great direction information can be kept after resolving, the method can completely describe the textural features of the image; finally, the two algorithms are combined, retrieving the image by using comprehensive features.

The invention discloses a method for dividing complex process modules oriented to mass customization, and proposes a method for dividing models at the process level by means of the characteristic relationship between processes corresponding to workpieces, by constructing a fuzzy correlation matrix between process modules , use the fuzzy clustering analysis method to convert and solve it, obtain the transitive closure matrix, form a module cluster diagram according to different partition threshold sequences, and obtain different module division schemes by selecting different λ values, with tight logic, precise control, and Efficient, in order to achieve fast and efficient production of personalized finished products that adapt to market and technological changes and high-level requirements for perfect craftsmanship.

The invention provides a wireless data transmission equipment testing data mining system and method based on LabVIEW and Matlab hybrid programming, and relates to testing data mining systems and methods. The wireless data transmission equipment testing data mining system and method based on LabVIEW and Matlab hybrid programming solve the problems that according to a manual identification method, accurate identification and extraction of the relevance between testing data are difficult, the workload is high, LabVIEW is difficult to use, and operation convenience and graphical attractiveness of a graphical user interface of Matlab are poorer than those of the LabVIEW. The system comprises a data preprocessing module, a parameter sequence extraction module, a waveform display module, a grey correlation analysis module and a fuzzy correlation rule mining module. The system is used in the following steps that firstly, simplified arrays are obtained; secondly, graphical display is conducted on double-precision numeric data; thirdly, the improved grey correlation degree r* is calculated; fourthly, strong correlation rule array expression rules are systemized; fifthly, the correlation relationship between parameter sequences is worked out. The wireless data transmission equipment testing data mining system and method based on LabVIEW and Matlab hybrid programming are applied to the field of testing data mining.