A Hybrid Neural Network and Box-Jenkins Models for Time Series Forecasting

Time series forecasting plays a significant role in numerous applications, including but not limited to, industrial planning, water consumption, medical domains, exchange rates and consumer price index. The main problem is insufficient forecasting accuracy. The present study proposes a hybrid forecasting methods to address this need. The proposed method includes three models. The first model is based on the autoregressive integrated moving average (ARIMA) statistical model; the second model is a back propagation neural network (BPNN) with adaptive slope and momentum parameters; and the third model is a hybridization between ARIMA and BPNN (ARIMA/BPNN) and artificial neural networks and ARIMA (ARIMA/ANN) to gain the benefits of linear and nonlinear modeling. The forecasting models proposed in this study are used to predict the indices of the consumer price index (CPI), and predict the expected number of cancer patients in the Ibb Province in Yemen. Statistical standard measures used to evaluate the proposed method include (i) mean square error, (ii) mean absolute error, (iii) root mean square error, and (iv) mean absolute percentage error. Based on the computational results, the improvement rate of forecasting the CPI dataset was 5%, 71%, and 4% for ARIMA/BPNN model, ARIMA/ANN model, and BPNN model respectively; while the result for cancer patients’ dataset was 7%, 200%, and 19% for ARIMA/BPNN model, ARIMA/ANN model, and BPNN model respectively. Therefore, it is obvious that the proposed method reduced the randomness degree, and the alterations affected the time series with data non-linearity. The ARIMA/ANN model outperformed each of its components when it was applied separately in terms of increasing the accuracy of forecasting and decreasing the overall errors of forecasting.

     

Application of Hybrid Learning Neural Fuzzy Systems in Reliability Prediction

This study presents a hybrid learning neural fuzzy system for accurately predicting system reliability. Neural fuzzy system learning with and without supervision has been successfully applied in control systems and pattern recognition problems. This investigation modifies the hybrid learning fuzzy systems to accept time series data and therefore examines the feasibility of reliability prediction. Two neural network systems are developed for solving different reliability prediction problems. Additionally, a scaled conjugate gradient learning method is applied to accelerate the training in the supervised learning phase. Several existing approaches, including feed‐forward multilayer perceptron (MLP) networks, radial basis function (RBF) neural networks and Box–Jenkins autoregressive integrated moving average (ARIMA) models, are used to compare the performance of the reliability prediction. The numerical results demonstrate that the neural fuzzy systems have higher prediction accuracy than the other methods. Copyright © 2005 John Wiley & Sons, Ltd.     

Modeling thermal conductivity enhancement of metal and metallic oxide nanofluids using support vector regression

Enhancing thermal conductivity of nanofluids is an important objective in heat transfer applications. Experimental measurement of thermal conductivity is time consuming, laborious and expensive. One of the common ways to address these limitations involves developing theoretical models to study thermo-physical properties of nanofluid. However, most classical and empirical models fail in predicting experimental results with good precision. In this study, we developed support vector regression (SVR) models that are capable of predicting the thermal conductivity enhancement for metallic and metallic-oxide nanofluids. The accuracy and reliability of the developed models were assessed using statistical parameters such as correlation coefficient (R²), root mean square error (RMSE) and mean absolute error (MAE). The models were characterized with very high correlation coefficients of 99.3 and 96.3% for the metallic and metallic oxide nanofluids, respectively. While the RMSE obtained were 1.11 and 1.33 for the metallic and metallic oxide nanofluids, respectively. In addition, the results of the models were compared with Hamilton-Crosser (HC) model and other empirical models. The SVR models performed much better than all the models examined. Furthermore, the effects of temperature, volume fractions, nanoparticle size and type, and basefluids types were correlated with experimental data in order to assess the performance of the developed models. The results indicate that SVR predictions were accurate and better than common theoretical models.     

Predicting the Superconducting Transition Temperature <Emphasis Type="Italic">T</Emphasis><Subscript>c</Subscript> of BiPbSrCaCuOF Superconductors by Using Support Vector Regression

According to an experimental data set on the superconducting transition temperature (T _c) of 21 BiPbSrCaCuOF superconductors under different process parameters including the amount of bismuth (n(Bi)), amount of oxygen (n(O)), sintering time (t) and sintering temperature (T), support vector regression (SVR) combined with particle swarm optimization (PSO) for its parameter optimization, was proposed to establish a model for prediction of the T _c of BiPbSrCaCuOF superconductors. The performance of SVR model was compared with that of back-propagation neural network (BPNN) and multivariable linear regression (MLR) model. The results show that the mean absolute error (MAE) and mean absolute percentage error (MAPE) of test samples achieved by SVR are smaller than those achieved by MLR or BPNN. This study suggests that SVR as a novel approach has a theoretical significance and potential practical value in development of high-T _c superconductor via guiding experiment.     

An innovative air-conditioning load forecasting model based on RBF neural network and combined residual error correction

Accurate air-conditioning load forecasting is the precondition for the optimal control and energy saving operation of HVAC systems. They have developed many forecasting methods, such as multiple linear regression (MLR), autoregressive integrated moving average (ARIMA), grey model (GM) and artificial neural network (ANN), in the field of air-conditioning load prediction. However, none of them has enough accuracy to satisfy the practical demand. On the basis of these models existed, a novel forecasting method, called ‘RBF neural network (RBFNN) with combined residual error correction’, is developed in this paper. The new model adopts the advanced algorithm of neural network based on radial basis functions for the air-conditioning load forecasting, and uses the combined forecasting model, which is the combination of MLR, ARIMA and GM, to estimate the residual errors and correct the ultimate foresting results. A study case indicates that RBFNN with combined residual error correction has a much better forecasting accuracy than RBFNN itself and RBFNN with single-model correction.     

An enhanced chiller FDD strategy based on the combination of the LSSVR-DE model and EWMA control charts

Development of the fault detection and diagnosis (FDD) for chiller systems is very important for improving the equipment reliability and saving energy consumption. The results of FDD performance are strongly dependent on the accuracy of chiller models. Since the accuracy of the chiller models depends on the indefinite model parameters which are normally chosen by experiments or experiences, an accurate chiller model is difficult to build. Therefore, optimization of model parameters is very useful to increase the accuracy of chiller models. This paper presents a new FDD strategy for centrifugal chillers of building air-conditioning systems, which is the combination between the nonlinear least squares support vector regression (LSSVR) based on the differential evolution (DE) algorithm and the exponentially weighted moving average (EWMA) control charts. In this strategy, the nonlinear LSSVR, which is a reformulation of SVR model with better generalization performances, is adopted to develop the reference feature parameter models in a typical non-linear chiller system. The DE algorithm which is a real-coding optimal algorithm with powerful global searching capacity is employed to enhance the accuracy of LSSVR models. The exponentially weighted moving average (EWMA) control charts are introduced to improve the fault detection capability as well as to reduce the Type II errors in a t-statistics-based way. Six typical faults of the chiller from the real-time experimental data of ASHRAE RP-1043 project are chosen to validate proposed FDD methods. Comprehensive comparisons between the proposed method and two similarly previous studies are performed. The comparison results show that the proposed method has achieved significant improvement in accuracy and reliability, especially at low severity levels. The proposed DE-LSSVR-EWMA strategy is robust for fault detection and diagnosis in centrifugal chiller systems.     

基于OVMD与SVR的水电机组振动趋势预测

为更好地预测水电机组振动趋势,研究提出了一种基于最优变分模态分解（OVMD）与支持向量回归（SVR）的水电机组振动趋势预测模型。首先基于中心频率观察法与残差指标最小化准则确定OVMD的分解参数,采用OVMD将非平稳振动序列分解为一系列模态函数,并对各模态函数分别进行相空间重构,构建状态矩阵,进而得到SVR回归预测模型的输入、输出,再采用交叉验证的网格搜索策略优化各SVR模型的参数,并分别进行回归预测,最后对所有SVR预测结果进行求和,得到原始振动趋势的预测值。研究对某大型混流式水电机组的振动监测数据进行预测试验,并进行对比分析,结果表明该模型可有效预测水电机组振动趋势。     

基于GM-噪声SVR方法的矿山设备可靠性参数估计

为了有效估计小子样条件下矿山设备的三参数威布尔分布可靠性模型参数,提出基于GM-噪声SVR的参数估计方法。该方法以灰色估计法(GM)为基础估计模型的位置参数,采用基于训练样本数量和噪声参数寻优的ε - 带支持向量回归机(ε-SVR)估计尺度参数和形状参数,并通过拟合的三参数威布尔分布函数分析预测和解决设备的可靠性问题。算例结果表明,GM-噪声SVR方法可以很好地用于矿山设备可靠性模型参数估计,估计某带式输送机三参数威布尔分布可靠性模型的位置参数、尺度参数和形状参数依次为3.1525、188.3763、1.0476,平均无故障时间为188 h,标准均方根误差NRMSE为0.0519。这表明该方法的可行性和有效性。     

Hybrid approach for remaining useful life prediction of ball bearings

Remaining useful life (RUL) prediction plays an important role in predictive maintenance systems to support decision‐makers for arranging maintenance tasks and related resources. We propose a hybrid approach that is combined an exponential weighted moving average (EWMA) control chart for anomaly detection and machine learning models such as support vector regression (SVR) and random forest regression (RFR) with differential evolution (DE) algorithm to predict the RULs of ball bearings. Here, DE algorithm is used to find the optimal hyperparameters of SVR model. The datasets of ball bearings from the Prognostics Data Repository of NASA are used to compare the prediction performance of different methods. The degradation behavior of training data from the anomaly time to the end of life is used to transfer learning for the testing data in the SVR and RFR models. The results indicate that the proposed methods outperform the other four existing methods in terms of score. Therefore, the proposed hybrid approach is a reliable tool for the RUL prediction of ball bearings.     

Forecasting Model Based on Information-Granulated GA-SVR and ARIMA for Producer Price Index

The accuracy of predicting the Producer Price Index (PPI) plays an indispensable role in government economic work. However, it is difficult to forecast the PPI. In our research, we first propose an unprecedented hybrid model based on fuzzy information granulation that integrates the GA-SVR and ARIMA (Autoregressive Integrated Moving Average Model) models. The fuzzy-information-granulation-based GA-SVR-ARIMA hybrid model is intended to deal with the problem of imprecision in PPI estimation. The proposed model adopts the fuzzy information-granulation algorithm to pre-classification-process monthly training samples of the PPI, and produced three different sequences of fuzzy information granules, whose Support Vector Regression (SVR) machine forecast models were separately established for their Genetic Algorithm (GA) optimization parameters. Finally, the residual errors of the GA-SVR model were rectified through ARIMA modeling, and the PPI estimate was reached. Research shows that the PPI value predicted by this hybrid model is more accurate than that predicted by other models, including ARIMA, GRNN, and GA-SVR, following several comparative experiments. Research also indicates the precision and validation of the PPI prediction of the hybrid model and demonstrates that the model has consistent ability to leverage the forecasting advantage of GA-SVR in non-linear space and of ARIMA in linear space.