Fast automatic two-stage nonlinear model identification based on the extreme learning machine

It is convenient and effective to solve nonlinear problems with a model that has a linear-in-the-parameters (LITP) structure. However, the nonlinear parameters (e.g. the width of Gaussian function) of each model term needs to be pre-determined either from expert experience or through exhaustive search. An alternative approach is to optimize them by a gradient-based technique (e.g. Newton’s method). Unfortunately, all of these methods still need a lot of computations. Recently, the extreme learning machine (ELM) has shown its advantages in terms of fast learning from data, but the sparsity of the constructed model cannot be guaranteed. This paper proposes a novel algorithm for automatic construction of a nonlinear system model based on the extreme learning machine. This is achieved by effectively integrating the ELM and leave-one-out (LOO) cross validation with our two-stage stepwise construction procedure [1]. The main objective is to improve the compactness and generalization capability of the model constructed by the ELM method. Numerical analysis shows that the proposed algorithm only involves about half of the computation of orthogonal least squares (OLS) based method. Simulation examples are included to confirm the efficacy and superiority of the proposed technique.

Predicting organic acid concentration from UV/vis spectrometry measurements - A comparison of machine learning techniques

The concentration of organic acids in anaerobic digesters is one of the most critical parameters for monitoring and advanced control of anaerobic digestion processes. Thus, a reliable online-measurement system is absolutely necessary. A novel approach to obtaining these measurements indirectly and online using UV/vis spectroscopic probes, in conjunction with powerful pattern recognition methods, is presented in this paper. An UV/vis spectroscopic probe from S::CAN is used in combination with a custom-built dilution system to monitor the absorption of fully fermented sludge at a spectrum from 200 to 750 nm. Advanced pattern recognition methods are then used to map the non-linear relationship between measured absorption spectra to laboratory measurements of organic acid concentrations. Linear discriminant analysis, generalized discriminant analysis (GerDA), support vector machines (SVM), relevance vector machines, random forest and neural networks are investigated for this purpose and their performance compared. To validate the approach, online measurements have been taken at a full-scale 1.3-MW industrial biogas plant. Results show that whereas some of the methods considered do not yield satisfactory results, accurate prediction of organic acid concentration ranges can be obtained with both GerDA and SVM-based classifiers, with classification rates in excess of 87% achieved on test data.

Optimising sorting and washing of home-grown maize to reduce fumonisin contamination under laboratory-controlled conditions

Subsistence farming communities with low socio-economic status reliant on a mono cereal maize diet are exposed to fumonisin levels that exceed the provisional maximum tolerable daily intake of 2 mu g kg(-1) body weight day(-1) recommended by the Joint FAO/WHO Expert Committee on Food Additives. In the rural Centane magisterial district, Eastern Cape Province, South Africa, it is customary during food preparation to sort visibly infected maize kernels from good maize kernels and to wash the good kernels prior to cooking. However, this customary practice seems not to sufficiently reduce the fumonisin levels. This is the first study to optimise the reduction of fumonisin mycotoxins in home-grown maize based on customary methods of a rural population, under laboratory-controlled conditions. Maize obtained from subsistence farmers was analysed for the major naturally occurring fumonisins (FB1, FB2 and FB3) by fluorescence HPLC. Large variations were observed in the unsorted and the experimental maize batches attributable to the non-homogeneous distribution of fumonisin contamination in maize kernels. Optimised hand-sorting of maize kernels by removing the visibly infected/damaged kernels (fumonisins, 53.7 +/- 15.0 mg kg(-1), 2.5% by weight) reduced the mean fumonisins from 2.32 +/- 1.16 mg kg(-1) to 0.68 +/- 0.42 mg kg(-1). Hand washing of the sorted good maize kernels for a period of 10 min at 25 degrees C resulted in optimal reduction with no additional improvement for wash periods up to 15 h. The laboratory optimised sorting reduced the fumonisins by 71 +/- 18% and an additional 13 +/- 12% with the 10 min wash. Based on these results and on local practices and practicalities the protocol that would be recommended to subsistence farmers consists of the removal of the infected/damaged kernels from the maize followed by a 10 min ambient temperature water wash. (C) 2010 Elsevier Ltd. All rights reserved.

Kinematic Analysis and Dimensional Synthesis of Exechon Parallel Kinematic Machine for Large Volume Machining

A parallel kinematic machine (PKM) topology can only give its best performance when its geometrical parameters are optimized. In this paper, dimensional synthesis of a newly developed PKM is presented for the first time. An optimization method is developed with the objective to maximize both workspace volume and global dexterity of the PKM. Results show that the method can effectively identify design parameter changes under different weighted objectives. The PKM with optimized dimensions has a large workspace to footprint ratio and a large well-conditioned workspace, hence justifies its suitability for large volume machining.