Entity

Time filter

Source Type


Yan H.-S.,Nanjing Southeast University | Yan H.-S.,MOE Key Laboratory of Measurement and Control of Complex Systems of Engineering | Wan X.-Q.,Nanjing Southeast University | Wan X.-Q.,MOE Key Laboratory of Measurement and Control of Complex Systems of Engineering | And 2 more authors.
International Journal of Computer Integrated Manufacturing | Year: 2016

This paper presents a new approach to the self-reconfiguration and optimisation of knowledge meshes (KMs), based on the user’s function requirements and similarity measure. A new similarity measure combined of the function similarity and layer similarity between similar knowledge points is defined, and the properties proved. A simple similarity algorithm for KMs is proposed. Aiming at user’s maximum function–satisfaction, the method to the self-reconfiguration of KMs is presented. First, several appropriate KMs according to the enterprise requirements are selected and preprocessed by similarity measure. Second, a similarity threshold is given and the similarity is calculated for every pair of knowledge points in the selected KMs. The two knowledge points can be recognised as the same when the similarity between them exceeds the given threshold, and then the knowledge point with the lower function–satisfaction degree is replaced by the one with the higher function–satisfaction degree. Third, the KM multiple set operation expression is optimised by the hybrid genetic-tabu algorithm. Finally, a new KM obtained by operations on KM multiple sets can be mapped into an agent mesh (AM) for automatic reconfiguration of complex software systems. Based upon the above, the KM’s optimisation are illustrated by an actual KM example which corresponds to the management information system (MIS) software used in a vehicle body plant at Nanjng in China, which shows the method to be very effective. © 2016 Taylor & Francis Source


Yan H.-S.,MOE Key Laboratory of Measurement and Control of Complex Systems of Engineering | Yan H.-S.,Nanjing Southeast University | Shang Z.-G.,MOE Key Laboratory of Measurement and Control of Complex Systems of Engineering | Shang Z.-G.,Nanjing Southeast University | Shang Z.-G.,Yancheng Institute of Technology
Applied Artificial Intelligence | Year: 2015

There exist problems of small samples and heteroscedastic noise in design time forecast. To solve them, support vector regression with probabilistic constraints (PC-SVR) is proposed in this article. The mean and variance functions are simultaneously constructed based on a heteroscedastic regression model. Probabilistic constraints are designed to make sure that for every sample, the forecast value is in a neighborhood of the target value with high probability. The optimization objective is formatted in the form of par-v-SVR. Prior knowledge about maximum completion time can be embedded in probabilistic constraints, and provides the size of the neighborhood of the target value. The results of application in injection mold design have confirmed the feasibility and validity of PC-SVR. Copyright © 2015 Taylor & Francis Group, LLC. Source

Discover hidden collaborations