Search

Online remaining charging-discharging cycle (RCDC) prognosis is of great significance for lithium-ion batteries. The conventional method is usually based on whether the state-of-health (SOH) of capacity reaches the end-of-life (EoL) threshold. However, the most available prediction methods have two problems that need to be solved. First, the SOH degradation curve of the lithium-ion battery is nonlinear and non-Gaussian, and the battery capacity regeneration phenomena (CRP) has a direct impact on RCDC estimation efficiency. These factors challenge the precise forecast of RCDC and increase the risk of prediction failure. Second, existing methods have insufficient early-stage prediction ability for capacity degradation because too little data are available to facilitate establishing and optimizing the prediction models. To overcome the above-mentioned drawbacks, this study introduces the Mann-Kendall trend analysis to generate an equivalent degradation indicator (EDI), and to replace the capacity-based SOH. The proposed EDI has good linearity and monotonicity, and is conducive to adopt a simple structured prediction model to determine the RCDC. Besides, this study is based on the “SOH-EDI” synchronization mapping relationship and applies an one-degree polynomial regression model to estimate the EoL threshold on the EDI curve. From the perspective of computational complexity, the proposed framework uses two polynomial prediction models with simple structures, which realizes a low computational burden and online RCDC prediction. To verify the efficiency of the proposed method, this paper introduces three methods for comparison. Experimental results show that the proposed framework has satisfied early-stage prediction ability of RCDC and has a superior prognosis efficiency. [ABSTRACT FROM AUTHOR]

The piecewise affine (PWA) model represents an attractive model structure for approximating nonlinear systems. In this paper, a procedure for obtaining the PWA model of the tire nonlinear cornering properties is introduced. In this approach, the highly nonlinear dynamic of the tire cornering properties is well approximated by a set of affine maps which relate inputs and outputs. These maps are defined in disjunctive regions in the regression space, itself composed of system inputs and outputs. The tire cornering properties tests are firstly carried out through a high-performance flat-plate test bench, thus the experimental data which can accurately reflect the tire cornering properties is obtained. On this basis, the PWA identification of the tire cornering properties is composed of the data clustering, the parameter estimation of the affine submodels and the calculation of the hyperplane coefficient matrices, which are respectively achieved by means of fuzzy c-means clustering, weighted least-squares and support vector machines. Finally, to verify the PWA model accuracy in approximating the tire nonlinear cornering properties, the comparison between the simulation results of the PWA identification model and the experimental data is conducted and the comparison results are analyzed. [ABSTRACT FROM AUTHOR]

High-precision fault diagnosis is vital for widely used multistage gearbox systems. Intelligent monitoring is difficult due to the fuzzy boundaries and a variety of unseen single or simultaneous faults of such complex machinery. To solve this problem, local mean decomposition is applied to extract features effectively from the original nonstationary and nonlinear vibration signals. By exploiting the diverse functionalities of extreme learning machines (ELM) in both regression and classification, a novel dual-ELM network is proposed, in which one ELM is employed to count the number of faults and the other is used to identify the specific single- or simultaneous-fault scenarios. The proposed dual-ELM-based multilabel classifier does not rely on an empirically specified threshold. Thus, it is more self-adaptive than the existing probabilistic-based classifiers. In addition, by inheriting the advantages of the original ELM, the dual-ELMs do not require iterative fine-tuning of parameters. Finally, the training speed of the dual-ELMs is much faster than other combinations of the existing classifiers. Experimental results under various loading conditions show that the proposed dual-ELM-based fault diagnostic framework is versatile at detecting single and simultaneous faults accurately and quickly. [ABSTRACT FROM AUTHOR]

Fault diagnosis is very important to maintain the operation of a gas turbine generator system (GTGS) in power plants, where any abnormal situations will interrupt the electricity supply. The fault diagnosis of the GTGS faces the main challenge that the acquired data, vibration or sound signals, contain a great deal of redundant information which extends the fault identification time and degrades the diagnostic accuracy. To improve the diagnostic performance in the GTGS, an effective fault feature extraction framework is proposed to solve the problem of the signal disorder and redundant information in the acquired signal. The proposed framework combines feature extraction with a general machine learning method, support vector machine (SVM), to implement an intelligent fault diagnosis. The feature extraction method adopts wavelet packet transform and time-domain statistical features to extract the features of faults from the vibration signal. To further reduce the redundant information in extracted features, kernel principal component analysis is applied in this study. Experimental results indicate that the proposed feature extracted technique is an effective method to extract the useful features of faults, resulting in improvement of the performance of fault diagnosis for the GTGS. [ABSTRACT FROM AUTHOR]

This study presents the optimization of biodiesel engine performance that can achieve the goal of fewer emissions, low fuel cost and wide engine operating range. A new biodiesel engine modeling and optimization framework based on extreme learning machine (ELM) is proposed. As an accurate model is required for effective optimization result, kernel-based ELM (K-ELM) is used instead of basic ELM because K-ELM can provide better generalization performance, and the randomness of basic ELM does not occur in K-ELM. By using K-ELM, a biodiesel engine model is first created based on experimental data. Logarithmic transformation of dependent variables is used to alleviate the problems of data scarcity and data exponentiality simultaneously. With the K-ELM engine model, cuckoo search (CS) is then employed to determine the optimal biodiesel ratio. A flexible objective function is designed so that various user-defined constraints can be applied. As an illustrative study, the fuel price in Macau is used to perform the optimization. To verify the modeling and optimization framework, the K-ELM model is compared with a least-squares support vector machine (LS-SVM) model, and the CS optimization result is compared with particle swarm optimization and experimental results. The evaluation result shows that K-ELM can achieve comparable performance to LS-SVM, resulting in a reliable prediction result for optimization. It also shows that the optimization results based on CS is effective. [ABSTRACT FROM AUTHOR]

Abstract: Real-time fault diagnostic system is very important to maintain the operation of the gas turbine generator system (GTGS) in power plants, where any abnormal situation will interrupt the electricity supply. The GTGS is complicated and has many types of component faults. To prevent from interruption of electricity supply, a reliable and quick response framework for real-time fault diagnosis of the GTGS is necessary. As the architecture and the learning algorithm of extreme learning machine (ELM) are simple and effective respectively, ELM can identify faults quickly and precisely as compared with traditional identification techniques such as support vector machines (SVM). This paper therefore proposes a new application of ELM for building a real-time fault diagnostic system in which data pre-processing techniques are integrated. In terms of data pre-processing, wavelet packet transform and time-domain statistical features are proposed for extraction of vibration signal features. Kernel principal component analysis is then applied to further reduce the redundant features in order to shorten the fault identification time and improve accuracy. To evaluate the system performance, a comparison between ELM and the prevailing SVM on the fault detection was conducted. Experimental results show that the proposed diagnostic framework can detect component faults much faster than SVM, while ELM is competitive with SVM in accuracy. This paper is also the first in the literature that explores the superiority of the fault identification time of ELM. [Copyright &y& Elsevier]

Abstract: This study aims to determine optimal biodiesel ratio that can achieve the goals of fewer emissions, reasonable fuel economy and wide engine operating range. Different advanced machine learning techniques, namely ELM (extreme learning machine), LS-SVM (least-squares support vector machine) and RBFNN (radial-basis function neural network), are used to create engine models based on experimental data. Logarithmic transformation of dependent variables is used to alleviate the problems of data scarcity and data exponentiality simultaneously. Based on the engine models, two optimization methods, namely SA (simulated annealing) and PSO (particle swarm optimization), are employed and a flexible objective function is designed to determine the optimal biodiesel ratio subject to various user-defined constraints. A case study is presented to verify the modeling and optimization framework. Moreover, two comparisons are conducted, where one is among the modeling techniques and the other is among the optimization techniques. Experimental results show that, in terms of the model accuracy and training time, ELM with the logarithmic transformation is better than LS-SVM and RBFNN with/without the logarithmic transformation. The results also show that PSO outperforms SA in terms of fitness and standard deviation, with an acceptable computational time. [Copyright &y& Elsevier]

Abstract: Modern automotive engines are controlled by an electronic control unit (ECU), and engine power performance is significantly affected by the selection of both ECU parameters and engine components. The engine performance tuning is usually done by a trial-and-error method. In the current literature, very little research has considered the selection of engine parts because engine parts are complicated objects that are usually represented as nominal data. These data are meaningless values in terms of computation. This paper presents a novel multiple-input/output least-squares support vector machine plus one-of-n remapping method for modelling engine power performance using both numerical (ECU parameters) and nominal data (candidate engine parts). The Quasi-Newton method, a genetic algorithm and particle swarm optimisation are then applied to the engine model to determine the optimal engine setup automatically. A simple binary code synthesis rule is also proposed to optimise the nominal variable. Both experimental and simulation results show that the proposed methodology can successfully yield an optimal engine setup. [Copyright &y& Elsevier]

Hysteresis nonlinearity degrades the positioning accuracy of a piezostage and requires a suppression for precision micro-/nanopositioning applications. This paper proposes two new approaches to modeling and compensating the rate-dependent hysteresis of a piezostage driven by piezoelectric stack actuators. By formulating the hysteresis modeling as an online nonlinear regression problem, online least squares support vector machine (SVM) (LS-SVM) and online relevance vector machine (RVM) models are proposed to capture the hysteretic behavior. Both hysteresis models are capable of updating continually with subsequent samples. After a comparative study on modeling performances, an inverse model-based feedforward combined with proportional–integral–derivative feedback control is presented to alleviate the hysteresis effect. Experimental results show that the LS-SVM model-based control scheme is over 86% more accurate than the RVM model-based one in the motion tracking task, whereas the latter is 14 times faster than the former in terms of updating time. Moreover, both LS-SVM and RVM model-based control schemes can suppress the rate-dependent hysteresis to a negligible level, which validates the feasibility and effectiveness of the proposed approaches. [ABSTRACT FROM AUTHOR]

Abstract: Hysteresis effect degrades the positioning accuracy of a piezostage, and hence the nonlinearity has to be suppressed for ultrahigh-precision positioning applications. This paper extends least squares support vector machines (LS-SVM) to the domain of hysteresis modeling and compensation for a piezostage driven by piezoelectric stack actuators. A LS-SVM model is proposed and trained by introducing the current input value and input variation rate as the input data set to formulate a one-to-one mapping. By adopting the radial basis function (RBF) as kernel function, the LS-SVM model only has two free hyperparameters, which are optimally tuned by resorting to Bayesian inference framework. The effectiveness of the presented model is verified as compared with two state-of-the-art approaches, namely, Bouc–Wen model and modified Prandtl–Ishlinskii (MPI) model. In addition, the LS-SVM inverse model based feedforward control combined with an incremental proportional–integral–derivative (PID) feedback control is designed to compensate the hysteresis nonlinearity. Experimental results show that the LS-SVM model based hybrid control scheme is superior to the Bouc–Wen model and MPI model based ones as well as either of the stand-alone controllers. The rate-dependent hysteresis is suppressed to a negligible level, which validates the effectiveness of the constructed controller. Owing to a simple procedure, the proposed LS-SVM based approach can be applied to modeling and control of other types of hysteretic systems as well. [Copyright &y& Elsevier]

Abstract: Suspended particulate matters (PM10) is considered as a harmful air pollutant. Many models attempt to predict numerical levels of PM10 but a simple, clearly defined classification of PM10 levels is more readily comprehensible to the general public rather than a numerical value. However, the PM10 prediction model often suffers from data imbalance problem in the training dataset that results in failure to forecast the minority class of severe cases. In this study, a warning system using extreme learning machine (ELM), compared with support vector machine (SVM), was constructed to forecast the class of PM10 level: Good, Moderate, and Severe. An imbalance strategy called prior duplication was also applied to improve the forecast of minority class. The experimental comparisons between ELM and SVM demonstrate that ELM produces superior accuracy relative to SVM in forecasting minority class (Severe) of PM10 level with or without the imbalance strategy. Furthermore, our results show that the required training time and model size in the ELM model are much shorter and smaller than those of SVM respectively, leading to a more efficient and practical implementation of prediction model for large dataset. The performance superiority of ELM is also discussed in this paper. [Copyright &y& Elsevier]