Relevance vector machines based modelling and optimisation for collaborative control parameter design: a case study

A new collaborative control parameter design strategy is proposed for economic plant control process. The relevance vector machines (RVMs) and genetic algorithms (GAs) are combined to generate the optimal control index table for controllers. More specifically, the probabilistic model based on RVMs is utilised to describe the non-linear behaviours according to the experimental dataset. The evolution-based optimisation model based on GAs is used for collaborative design of the optimum control parameter combinations. A variable-rate fertilising system is presented as an application case for collaborative generation of control index table with the combined accuracy, energy saving and fertilising-consistency optimisation objectives. The experimental results show the effectiveness of the proposed hybrid approach.

[1]  Tao Yu,et al.  Integrating relevance vector machines and genetic algorithms for optimization of seed-separating process , 2007, Eng. Appl. Artif. Intell..

[2]  Naiqian Zhang,et al.  A real-time, embedded, weed-detection and spray-control system. , 2003 .

[3]  Andrew Blake,et al.  Sparse Bayesian learning for efficient visual tracking , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Moustafa A. Fadel.  Performance Assessment of VRT-based Granular Fertilizer Broadcasting Systems , 2004 .

[5]  Arnold W. Schumann,et al.  Variable Rate Applications of Granular Fertilizer for Citrus Test Plots , 2005 .

[6]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevance Vector Machine , 2001 .

[7]  Chenghai Yang,et al.  A Variable Rate Applicator for Controlling Rates of Two Liquid Fertilizers , 2001 .

[8]  J. De Baerdemaeker,et al.  On-the-go variable-rate phosphorus fertilisation based on a visible and near-infrared soil sensor , 2008 .

[9]  J. Holland.  Searching nonlinear functions for high values , 1989 .

[10]  Sheng Chen,et al.  The relevance vector machine technique for channel equalization application , 2001, IEEE Trans. Neural Networks.

[11]  David J. C. MacKay,et al.  The Evidence Framework Applied to Classification Networks , 1992, Neural Computation.

[12]  J. Hummelb,et al.  On-the-go soil sensors for precision agriculture , 2004 .

[13]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[14]  G. Gary Wang,et al.  Review of Metamodeling Techniques in Support of Engineering Design Optimization , 2007, DAC 2006.

[15]  Joaquin Quiñonero-Candela,et al.  Learning with Uncertainty: Gaussian Processes and Relevance Vector Machines , 2004 .

[16]  Ankur Agarwal,et al.  3D human pose from silhouettes by relevance vector regression , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[17]  N. Zhang,et al.  Precision agriculture—a worldwide overview , 2002 .