Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

35results about How to "Facilitates automated implementation" patented technology

Fault classification method based on self-adaption integrated semi-supervision Fisher discrimination

The invention discloses an industrial process fault classification method based on self-adaption integrated semi-supervision Fisher discrimination. The method comprises the steps of when off-line modeling is conducted, firstly conducting off-line modeling on unlabeled data, and constituting a semi-supervision random training subset by combining labeled data with the unlabeled data; when iteration training is conducted on a sub classifier each time, conducting semi-supervision Fisher dimensionality reduction to obtain a Fisher discrimination matrix, and obtaining a posterior probability matrix, a combined weight of the sub classifier and a sample weight of the labeled data during next time iteration with the labeled sample data after dimensionality reduction according to a Bayesian statistics method; adopting the posterior probability matrix of the labeled data and a label of the matrix as a training set of a fusion algorithm K near neighbor; during online classification, calling each sub classifier to obtain the posterior probability matrix of an online sample to be detected, and inputting the posterior probability matrix into a fusion K near neighbor classifier with the weight to obtain a final result. Compared with an existing method, the industrial process fault classification method based on the self-adaption integrated semi-supervision Fisher discrimination improves the fault classification result of an industrial process, and more facilitates automated implementation of the industrial process.
Owner:ZHEJIANG UNIV

Semiconductor process monitoring method based on independent component analysis and Bayesian inference

The invention discloses a semiconductor process monitoring method based on independent component analysis and Bayesian inference, comprising the following step of: firstly, dividing working conditions according to the mixed data of the semiconductor process, conducting the independent component analysis for each working condition data, and establishing a corresponding independent component analysis model; and then integrating and combining the monitoring information under the different working conditions by a Bayesian inference method to obtain a final monitoring result. In addition, the invention can also acquire the working condition information of current monitoring data by a posterior probability analysis method, that is to say, the invention can judge that the current monitoring data is in what process operation working condition; compared with the present other methods, the invention can not only greatly enhance the monitoring effect of the semiconductor process, but also largely improve the dependence of the monitoring method on process knowledge and enhance the comprehensive ability and the operating confidence of process operators on the process, thereby being more beneficial to the implementation of the automation of the semiconductor process.
Owner:ZHEJIANG UNIV

Packaging and stacking integrated device used for finished pen

The invention provides a packaging and stacking integrated device used for finished pens. The packaging and stacking integrated device comprises a packaging box opening mechanism, a material combiningconveying mechanism, a box closing device body, a stacking mechanism and a detecting device. The packaging box opening mechanism is used for expanding a first box body to form a second box body. Thematerial combining conveying mechanism is used for conveying the finished pens to the packaging position of a packaging box so that the finished pens can enter the second box body, and a third box body is formed. The box closing device body is used for collecting an opened side tongue and an insertion piece of the third box body into the box body so as to form a fourth box body. The detecting device is arranged at the rear portion of the box closing device body. The detecting device comprises a gravity detection assembly. The gravity detection assembly is used for detecting the weight of the fourth box body. By means of the packaging and stacking integrated device, automatic filling, packaging and stacking of the finished pens are achieved, the finished pen boxing space is saved, the finished pen boxing automation degree is improved, and the overall production efficiency is improved. The packaging and stacking integrated device is reasonable in design, ingenuous in conception, capableof facilitating automatic implementation and beneficial to application and popularization in the pen industry.
Owner:SUZHOU PAIFEITE AUTOMATION TECH CO LTD

Formal description and decomposition method for metamorphic relation

The invention discloses a formal description and decomposition method for a metamorphic relation. The method includes the following steps: (1) according to targeted tested software, extracting and designing the metamorphic relation that the software mush satisfy to create the metamorphic relation; (2) performing formal modeling on the obtained metamorphic relation on the basis of symbolic logic, determining constraint conditions under which the metamorphic relation is established, performing formal description, then describing input parameters and output parameters of the metamorphic relation on the basis of the symbolic logic, and establishing a formal description model of the metamorphic relation; (3) on the basis of the formal model, respectively extracting subrelations forming the metamorphic relation and a set description form of a metamorphic relation composition model, and establishing a metamorphic relation decomposition model. The method is simple and clear, description capacity and application range of the formal model are guaranteed through symbolic logic description, the accurate, standard and effective method is provided for description of the metamorphic relation, and the method is more conducive to automated implementation of subsequent metamorphic testing.
Owner:PLA UNIV OF SCI & TECH

Finished pen packaging box stacking device

The invention provides a finished pen packaging box stacking device which comprises a stacking mechanism and a detecting device. The detecting device is arranged at the front end of the stacking mechanism and comprises a gravity detection assembly and an inferior-quality product ejection assembly. The gravity detection assembly is used for detecting the weight of fourth box bodies. The inferior-quality product ejection assembly is used for ejecting the fourth box bodies with unqualified weight. The stacking mechanism comprises a stacking conveying assembly, a stacking material pushing assemblyand a stacking material ejection assembly. The stacking conveying assembly is used for conveying the fourth box bodies with qualified weight to the position of the stacking material ejection assembly. The stacking material ejection assembly is used for ejecting the fourth box bodies to the position in front of the stacking material push assembly from the lower portion. The stacking material pushassembly is used for pushing out the stacked fourth box bodies. By means of the finished pen packaging box stacking device, a gravity detection manner is adopted for detecting finished pen packages, the overall production qualification rate is increased, meanwhile, the bottom-to-top stacking mechanism is adopted, the automation degree of finished pen boxing is improved, and the overall productionefficiency is improved. By means of the finished pen packaging box stacking device, automatic implementation is facilitated, and application and popularization in the pen industry are facilitated.
Owner:SUZHOU PAIFEITE AUTOMATION TECH CO LTD

A Classification Method for Industrial Process Faults Based on Analytic Hierarchy Process and Fuzzy Fusion

The invention discloses an industrial process fault classification method based on analytic hierarchy process and fuzzy fusion. The method comprises the steps that a training data set is used to carry out offline modeling on a number of classifier methods to acquire a number of models; the classification performance of the classifiers is presented in the form of a fusion matrix; and the analytic hierarchy process is used to score and evaluate a number of classifier models, so that a corresponding weight is given to each classifier; the classifier models are called; a discriminant matrix is calculated according to the classification result of each classifier; and the discriminant matrix and the scoring result of the analytic hierarchy process are used to integrate the classification results of a number of classifier through a fuzzy fusion method to acquire a final fault classification result. Compared with other methods, the method provided by the invention has the advantages that the diagnostic effect of an industrial process is improved; the process operator's confidence in grasping and operating a process is enhanced; and the limitation of a single fault classification method is greatly improved, which is conductive to automated implementation of industrial processes.
Owner:ZHEJIANG UNIV

An Integrated Semi-Supervised Fisher Discriminant Based Fault Classification Method for Industrial Processes

The invention discloses an integrated semi-supervised Fisher's discrimination-based industrial process fault classifying method. In the method, offline modeling is first conducted; non-labeled data is randomly sampled and together with labeled data form a plurality of random training subsets; then semi-supervised Fisher dimensionality reduction is conducted to acquire a plurality of Fisher's discrimination matrixes; sampled data with dimensionality reduction is operated according to a Bayesian statistics method to acquire a series of posterior probability matrixes; the posterior probability matrixes of the labeled data and corresponding labels work as training samples adjacent to a measurement layer fusion algorithm K; during online classification, above semi-supervised Fisher's discrimination classifiers are called to acquire a posterior probability matrix of each online to-be-measured sample; and then the posterior probability matrix is input to a measurement layer fusion K adjacent classifier to acquire a final fault classification result. Compared with other methods, industrial process fault classification effect can be improved, knowledge and operation confidence to the process can be enhanced for operators and automatic implantation of the industrial process can be facilitated.
Owner:ZHEJIANG UNIV

A Formal Description and Decomposition Method of Metamorphic Relationship

The invention discloses a formal description and decomposition method for a metamorphic relation. The method includes the following steps: (1) according to targeted tested software, extracting and designing the metamorphic relation that the software mush satisfy to create the metamorphic relation; (2) performing formal modeling on the obtained metamorphic relation on the basis of symbolic logic, determining constraint conditions under which the metamorphic relation is established, performing formal description, then describing input parameters and output parameters of the metamorphic relation on the basis of the symbolic logic, and establishing a formal description model of the metamorphic relation; (3) on the basis of the formal model, respectively extracting subrelations forming the metamorphic relation and a set description form of a metamorphic relation composition model, and establishing a metamorphic relation decomposition model. The method is simple and clear, description capacity and application range of the formal model are guaranteed through symbolic logic description, the accurate, standard and effective method is provided for description of the metamorphic relation, and the method is more conducive to automated implementation of subsequent metamorphic testing.
Owner:PLA UNIV OF SCI & TECH

Semiconductor process monitoring method based on independent component analysis and Bayesian inference

The invention discloses a semiconductor process monitoring method based on independent component analysis and Bayesian inference, comprising the following step of: firstly, dividing working conditions according to the mixed data of the semiconductor process, conducting the independent component analysis for each working condition data, and establishing a corresponding independent component analysis model; and then integrating and combining the monitoring information under the different working conditions by a Bayesian inference method to obtain a final monitoring result. In addition, the invention can also acquire the working condition information of current monitoring data by a posterior probability analysis method, that is to say, the invention can judge that the current monitoring data is in what process operation working condition; compared with the present other methods, the invention can not only greatly enhance the monitoring effect of the semiconductor process, but also largely improve the dependence of the monitoring method on process knowledge and enhance the comprehensive ability and the operating confidence of process operators on the process, thereby being more beneficial to the implementation of the automation of the semiconductor process.
Owner:ZHEJIANG UNIV

Fault Classification Method Based on Adaptive Ensemble Semi-Supervised Fisher Discriminant

The invention discloses an industrial process fault classification method based on self-adaption integrated semi-supervision Fisher discrimination. The method comprises the steps of when off-line modeling is conducted, firstly conducting off-line modeling on unlabeled data, and constituting a semi-supervision random training subset by combining labeled data with the unlabeled data; when iteration training is conducted on a sub classifier each time, conducting semi-supervision Fisher dimensionality reduction to obtain a Fisher discrimination matrix, and obtaining a posterior probability matrix, a combined weight of the sub classifier and a sample weight of the labeled data during next time iteration with the labeled sample data after dimensionality reduction according to a Bayesian statistics method; adopting the posterior probability matrix of the labeled data and a label of the matrix as a training set of a fusion algorithm K near neighbor; during online classification, calling each sub classifier to obtain the posterior probability matrix of an online sample to be detected, and inputting the posterior probability matrix into a fusion K near neighbor classifier with the weight to obtain a final result. Compared with an existing method, the industrial process fault classification method based on the self-adaption integrated semi-supervision Fisher discrimination improves the fault classification result of an industrial process, and more facilitates automated implementation of the industrial process.
Owner:ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products