Improved Nonlinear PCA for Process Monitoring Using Support Vector Data Description

Nonlinear principal component analysis (PCA) based on neural networks has drawn significant attention as a monitoring tool for complex nonlinear processes, but there remains a difficulty with determining the optimal network topology. This paper exploits the advantages of the Fast Recursive Algorithm, where the number of nodes, the location of centres, and the weights between the hidden layer and the output layer can be identified simultaneously for the radial basis function (RBF) networks. The topology problem for the nonlinear PCA based on neural networks can thus be solved. Another problem with nonlinear PCA is that the derived nonlinear scores may not be statistically independent or follow a simple parametric distribution. This hinders its applications in process monitoring since the simplicity of applying predetermined probability distribution functions is lost. This paper proposes the use of a support vector data description and shows that transforming the nonlinear principal components into a feature space allows a simple statistical inference. Results from both simulated and industrial data confirm the efficacy of the proposed method for solving nonlinear principal component problems, compared with linear PCA and kernel PCA.

Two-stage RBF network construction based on particle swarm optimization

The conventional radial basis function (RBF) network optimization methods, such as orthogonal least squares or the two-stage selection, can produce a sparse network with satisfactory generalization capability. However, the RBF width, as a nonlinear parameter in the network, is not easy to determine. In the aforementioned methods, the width is always pre-determined, either by trial-and-error, or generated randomly. Furthermore, all hidden nodes share the same RBF width. This will inevitably reduce the network performance, and more RBF centres may then be needed to meet a desired modelling specification. In this paper we investigate a new two-stage construction algorithm for RBF networks. It utilizes the particle swarm optimization method to search for the optimal RBF centres and their associated widths. Although the new method needs more computation than conventional approaches, it can greatly reduce the model size and improve model generalization performance. The effectiveness of the proposed technique is confirmed by two numerical simulation examples.

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.

Nonlinear time series prediction based on a power-law noise model

In this paper we investigate the influence of a power-law noise model, also called noise, on the performance of a feed-forward neural network used to predict time series. We introduce an optimization procedure that optimizes the parameters the neural networks by maximizing the likelihood function based on the power-law model. We show that our optimization procedure minimizes the mean squared leading to an optimal prediction. Further, we present numerical results applying method to time series from the logistic map and the annual number of sunspots demonstrate that a power-law noise model gives better results than a Gaussian model.

The Influence of Structural Modeshape Variability on Limit Cycle Oscillation Behaviour

Modal analysis is a popular approach used in structural dynamic and aeroelastic problems due to its efficiency. The response of a structure is compo
sed of the sum of orthogonal eigenvectors or modeshapes and corresponding modal frequencies. This paper investigates the importance of modeshapes on the aeroelastic response of the Goland wing subject to structural uncertainties. The wing undergoes limit cycle oscillations (LCO) as a result of the inclusion of polynomial stiffness nonlinearities. The LCO computations are performed using a Harmonic Balance approach for speed, the modal properties of the system are extracted from MSC NASTRAN. Variability in both the wing’s structure and the store centre of gravity location is investigated in two cases:- supercritical and subcritical type LCOs. Results show that the LCO behaviour is only sensitive to change in modeshapes when the nature of the modes are changing significantly.

Transonic Nonlinear Aeroelastic Simulations Using An Harmonic Balance Method

This paper presents an approach to compute transonic Limit Cycle O
scillations using a coupled Harmonic Balance formulation based on the Euler equations for fluid dynamics and finite element models. The paper will investigate the role of aerodynamic (shocks) and structural nonlinearities in driving the limit cycle behaviour. Part icular attention will be given to nonlinear interactions for subcritical LCOs. The Aero elastic Harmonic Balance formulation, allows for solutions of the coupled structural dynamics and CFD system at a reduced cost.

Learning from time series:Supervised Aggregative Feature Extraction

Many modeling problems require to estimate a scalar output from one or more time series. Such problems are usually tackled by extracting a fixed number of features from the time series (like their statistical moments), with a consequent loss in information that leads to suboptimal predictive models. Moreover, feature extraction techniques usually make assumptions that are not met by real world settings (e.g. uniformly sampled time series of constant length), and fail to deliver a thorough methodology to deal with noisy data. In this paper a methodology based on functional learning is proposed to overcome the aforementioned problems; the proposed Supervised Aggregative Feature Extraction (SAFE) approach allows to derive continuous, smooth estimates of time series data (yielding aggregate local information), while simultaneously estimating a continuous shape function yielding optimal predictions. The SAFE paradigm enjoys several properties like closed form solution, incorporation of first and second order derivative information into the regressor matrix, interpretability of the generated functional predictor and the possibility to exploit Reproducing Kernel Hilbert Spaces setting to yield nonlinear predictive models. Simulation studies are provided to highlight the strengths of the new methodology w.r.t. standard unsupervised feature selection approaches. © 2012 IEEE.

Advanced Modelling and Optimization of Infared Oven in Injection Stretch Blow-moulding for Energy Saving

In the production process of polyethylene terephthalate (PET) bottles, the initial temperature of preforms plays a central role on the final thickness, intensity and other structural properties of the bottles. Also, the difference between inside and outside temperature profiles could make a significant impact on the final product quality. The preforms are preheated by infrared heating oven system which is often an open loop system and relies heavily on trial and error approach to adjust the lamp power settings. In this paper, a radial basis function (RBF) neural network model, optimized by a two-stage selection (TSS) algorithm combined with partial swarm optimization (PSO), is developed to model the nonlinear relations between the lamp power settings and the output temperature profile of PET bottles. Then an improved PSO method for lamp setting adjustment using the above model is presented. Simulation results based on experimental data confirm the effectiveness of the modelling and optimization method.

A self-learning teaching-learning based optimization for dynamic economic/environmental dispatch considering multiple plug-in electric vehicle loads

Economic and environmental load dispatch aims to determine the amount of electricity generated from power plants to meet load demand while minimizing fossil fuel costs and air pollution emissions subject to operational and licensing requirements. These two scheduling problems are commonly formulated with non-smooth cost functions respectively considering various effects and constraints, such as the valve point effect, power balance and ramp rate limits. The expected increase in plug-in electric vehicles is likely to see a significant impact on the power system due to high charging power consumption and significant uncertainty in charging times. In this paper, multiple electric vehicle charging profiles are comparatively integrated into a 24-hour load demand in an economic and environment dispatch model. Self-learning teaching-learning based optimization (TLBO) is employed to solve the non-convex non-linear dispatch problems. Numerical results on well-known benchmark functions, as well as test systems with different scales of generation units show the significance of the new scheduling method.

Differential evolution combined with clonal selection for dynamic economic dispatch

Dynamic economic load dispatch (DELD) is one of the most important steps in power system operation. Various optimisation algorithms for solving the problem have been developed; however, due to the non-convex characteristics and large dimensionality of the problem, it is necessary to explore new methods to further improve the dispatch results and minimise the costs. This article proposes a hybrid differential evolution (DE) algorithm, namely clonal selection-based differential evolution (CSDE), to solve the problem. CSDE is an artificial intelligence technique that can be applied to complex optimisation problems which are for example nonlinear, large scale, non-convex and discontinuous. This hybrid algorithm combines the clonal selection algorithm (CSA) as the local search technique to update the best individual in the population, which enhances the diversity of the solutions and prevents premature convergence in DE. Furthermore, we investigate four mutation operations which are used in CSA as the hyper-mutation operations. Finally, an efficient solution repair method is designed for DELD to satisfy the complicated equality and inequality constraints of the power system to guarantee the feasibility of the solutions. Two benchmark power systems are used to evaluate the performance of the proposed method. The experimental results show that the proposed CSDE/best/1 approach significantly outperforms nine other variants of CSDE and DE, as well as most other published methods, in terms of the quality of the solution and the convergence characteristics.

An improved TLBO with elite strategy for parameters identification of PEM fuel cell and solar cell models

Clean and renewable energy generation and supply has drawn much attention worldwide in recent years, the proton exchange membrane (PEM) fuel cells and solar cells are among the most popular technologies. Accurately modeling the PEM fuel cells as well as solar cells is critical in their applications, and this involves the identification and optimization of model parameters. This is however challenging due to the highly nonlinear and complex nature of the models. In particular for PEM fuel cells, the model has to be optimized under different operation conditions, thus making the solution space extremely complex. In this paper, an improved and simplified teaching-learning based optimization algorithm (STLBO) is proposed to identify and optimize parameters for these two types of cell models. This is achieved by introducing an elite strategy to improve the quality of population and a local search is employed to further enhance the performance of the global best solution. To improve the diversity of the local search a chaotic map is also introduced. Compared with the basic TLBO, the structure of the proposed algorithm is much simplified and the searching ability is significantly enhanced. The performance of the proposed STLBO is firstly tested and verified on two low dimension decomposable problems and twelve large scale benchmark functions, then on the parameter identification of PEM fuel cell as well as solar cell models. Intensive experimental simulations show that the proposed STLBO exhibits excellent performance in terms of the accuracy and speed, in comparison with those reported in the literature.

On Infinite Time Performance of Nonlinear Model Predictive Controllers

This paper addresses the problem of infinite time performance of model predictive controllers applied to constrained nonlinear systems. The total performance is compared with a finite horizon optimal cost to reveal performance limits of closed-loop model predictive control systems. Based on the Principle of Optimality, an upper and a lower bound of the ratio between the total performance and the finite horizon optimal cost are obtained explicitly expressed by the optimization horizon. The results also illustrate, from viewpoint of performance, how model predictive controllers approaches to infinite optimal controllers as the optimization horizon increases.

Building information modeling based building design optimization for sustainability

Environmental problems, especially climate change, have become a serious global issue waiting for people to solve. In the construction industry, the concept of sustainable building is developing to reduce greenhouse gas emissions. In this study, a building information modeling (BIM) based building design optimization method is proposed to facilitate designers to optimize their designs and improve buildings’ sustainability. A revised particle swarm optimization (PSO) algorithm is applied to search for the trade-off between life cycle costs (LCC) and life cycle carbon emissions (LCCE) of building designs. In order tovalidate the effectiveness and efficiency of this method, a case study of an office building is conducted in Hong Kong. The result of the case study shows that this method can enlarge the searching space for optimal design solutions and shorten the processing time for optimal design results, which is really helpful for designers to deliver an economic and environmental friendly design scheme.

Performance Limits of MIMO Systems with Nonlinear Power Amplifiers

The development of 5G enabling technologies brings new challenges to the design of power amplifiers (PAs). In particular, there is a strong demand for low-cost, nonlinear PAs which, however, introduce nonlinear distortions. On the other hand, contemporary expensive PAs show great power efficiency in their nonlinear region. Inspired by this trade-off between nonlinearity distortions and efficiency, finding an optimal operating point is highly desirable. Hence, it is first necessary to fully understand how and how much the performance of multiple-input multiple-output (MIMO) systems deteriorates with PA nonlinearities. In this paper, we first reduce the ergodic achievable rate (EAR) optimization from a power allocation to a power control problem with only one optimization variable, i.e. total input power. Then, we develop a closed-form expression for the EAR, where this variable is fixed. Since this expression is intractable for further analysis, two simple lower bounds and one upper bound are proposed. These bounds enable us to find the best input power and approach the channel capacity. Finally, our simulation results evaluate the EAR of MIMO channels in the presence of nonlinearities. An important observation is that the MIMO performance can be significantly degraded if we utilize the whole power budget.

A high-energy, high-flux source of gamma-rays from all-optical nonlinear Thomson scattering

γ-Ray sources are among the most fundamental experimental tools currently available to modern physics. As well as the obvious benefits to fundamental research, an ultra-bright source of γ-rays could form the foundation of scanning of shipping containers for special nuclear materials and provide the bases for new types of cancer therapy.

However, for these applications to prove viable, γ-ray sources must become compact and relatively cheap to manufacture. In recent years, advances in laser technology have formed the cornerstone of optical sources of high energy electrons which already have been used to generate synchrotron radiation on a compact scale. Exploiting the scattering induced by a second laser, one can further enhance the energy and number of photons produced provided the problems of synchronisation and compact γ-ray detection are solved.

Here, we report on the work that has been done in developing an all-optical and hence, compact non-linear Thomson scattering source, including the new methods of synchronisation and compact γ-ray detection. We present evidence of the generation of multi-MeV (maximum 16–18 MeV) and ultra-high brilliance (exceeding 10²⁰ photons s⁻¹mm⁻²mrad⁻² 0.1% BW at 15 MeV) γ-ray beams. These characteristics are appealing for the paramount practical applications mentioned above.