Search

Abstract Soft sensor plays a decisive role in making control strategies and production plans. However, the difficulty in establishing accurate and robust soft sensors using an individual model is continuously increasing due to the increasing scale and complexity in modeling data. To handle this problem, an effective ensemble model using partial least squares regression (PLSR) integrated with extreme learning machine (ELM) with multiple activation functions (PLSR-MAFELM) is proposed in this paper. The proposed PLSR-MAFELM is simple in construction: firstly, train several ELM models assigned with different activation functions using the least squares solution; secondly, combine ELM models for enhancing accuracy and stability performance; finally, obtain the optimal ensemble outputs by aggregating the outputs of individual ELM models using PLSR. To test the performance of the proposed PLSR-MAFELM model, a UCI benchmark dataset and two real-world applications are selected to carry out simulation case studies. Simulation results show that PLSR-MAFELM can achieve good stability and accuracy performance, which indicates that the generalization capability of soft sensors can be improved through combining some single models. Highlights • A multi-activation functions based extreme learning machine ensemble is proposed. • The ensemble model utilizes different and effective nonlinear activation functions. • Partial least squares regression is used to aggregate the outputs of single models. • The ensemble model can be accurate, stable and efficient in intelligent measurement. • Simulation results confirm the effectiveness of the proposed ensemble framework. [ABSTRACT FROM AUTHOR]

Some key variables in the complex chemical processes are very difficult to measure due to the nonlinearity, the disturbances, and the technological limitations. In order to accurately predict the difficult-to-measure variables, soft sensor based on a novel robust bagging nonlinear model integrating improved extreme learning machine with partial least square (RB-PLSIELM) is developed. Motivated by the ensemble ideas, the proposed RB-PLSIELM model is based on the bagging ensemble scheme to combine some individual nonlinear models integrating improved extreme learning machine with partial least square (PLSIELM). The sub-data for building the individual PLSIELM model are re-sampled from the original training data using the bagging tool. The problem of over-training in the PLSELM model can be avoided by using the bagging re-sampling technology. The proposed RB-PLSIELM model was demonstrated by applying it to predicting the key variables of the Tennessee Eastman Process (TEP) and the Purified Terephthalic Acid Process (PTAP). The simulation results obtained by RB-PLSIELM are compared with those obtained by the individual PLSELM model, the ELM model, and the partial least square regression (PLSR) model. Compared with the other models, the RB-PLSIELM can achieve higher prediction accuracy and stability. [ABSTRACT FROM AUTHOR]

Extreme learning machine (ELM) is an effective learning algorithm for single-hidden-layer feed-forward neural networks (SLFNNs). Due to its easiness in theory and implementation, ELM has been widely used in many fields. In order to further enhance the generalization performance of ELM, a positive and negative correlation input attributes oriented subnets based double parallel extreme learning machine (PCNCIAOS-DPELM) is proposed in this paper. A salient feature in the PNIAOS-DPELM is that there are two special subnets. In one of the two subnets, the input attributes have a positive correlation to the outputs. In another subnet, the input attributes have a negative correlation to the outputs. The two kinds of input attributes can be obtained by separating the input attributes into two categories using the correlation coefficient analysis. Then according to the categories, the two subnets can be established. The two subnets are based on well-trained auto-associative neural networks (AANNs), which can extract the nonlinear information of the input attributes and remove the redundant information. An advantage in PNIAOS-DPELM is that the proper number of the nodes in the hidden layer can be determined. To test the validity of PNIAOS-DPELM, it is applied to monitoring three chemical processes in steady state. Meanwhile, ELM, double parallel ELM (DP-ELM), and ELM with kernel (ELMK) were developed for comparisons. Experimental results demonstrated that PNIAOS-DPELM could achieve better regression precision and have better stable ability than ELM, DP-ELM, and ELMK did during the generalization phase. [ABSTRACT FROM AUTHOR]

Abstract Nowadays, petrochemical industries with many integrated units and equipment have characteristics of high uncertainty and nonlinearity. Therefore, it becomes more and more difficult to make reliable and accurate point measurement of energy modeling. To tackle this problem, a novel prediction intervals (PIs) method integrating error & self-feedback extreme learning machine (ESF-ELM) with particle swarm optimization (PSO) is proposed. For improving the energy modeling accuracy of extreme learning machine (ELM), the input weights are initialized using cosine similarity coefficients but not randomly initialized. In addition, an error-feedback layer and a self-feedback layer are added to the input layer and the hidden layer for enhancing generalization performance, respectively. Finally, PSO with a comprehensive measure is developed to evaluate the mean coverage probability and the mean width percentage of PIs. The proposed ESF-ELM with PSO is applied to constructing PIs of energy consumption for a Purified Terephthalic Acid production process. Simulation results show the proposed model can generate high-quality PIs with large coverage probability, narrow width, and superiority in adaptability and reliability, which provides guidance for decision makers to maximize benefits and give reasonable future plans. Highlights • A novel effective energy consumption prediction intervals method is proposed. • An Error feedback and a self-feedback layer are added to extreme learning machine. • Prediction intervals are optimized by using particle swarm optimization. • A case study of Purified Terephthalic Acid is executed for performance validation. • Simulation results show the proposed method can obtain good prediction intervals. [ABSTRACT FROM AUTHOR]

Extreme learning machine (ELM), which is a simple single-hidden-layer feed-forward neural network with fast implementation, has been widely applied in many engineering fields. However, it is difficult to enhance the modeling ability of extreme learning in disposing the high-dimensional noisy data. And the predictive modeling method based on the ELM integrated fuzzy C-Means integrating analytic hierarchy process (FAHP) (FAHP-ELM) is proposed. The fuzzy C-Means algorithm is used to cluster the input attributes of the high-dimensional data. The Analytic Hierarchy Process (AHP) based on the entropy weights is proposed to filter the redundant information and extracts characteristic components. Then, the fusion data is used as the input of the ELM. Compared with the back-propagation (BP) neural network and the ELM, the proposed model has better performance in terms of the speed of convergence, generalization and modeling accuracy based on University of California Irvine (UCI) benchmark datasets. Finally, the proposed method was applied to build the energy saving and predictive model of the purified terephthalic acid (PTA) solvent system and the ethylene production system. The experimental results demonstrated the validity of the proposed method. Meanwhile, it could enhance the efficiency of energy utilization and achieve energy conservation and emission reduction. [ABSTRACT FROM AUTHOR]

Energy optimization and analysis of complex chemical processes play a significant role in the sustainable development procedure. In order to deal with the high-dimensional and noise data in complex chemical processes, we present an energy optimization and analysis method based on extreme learning machine integrating the index decomposition analysis. First, index decomposition analysis has been used to decompose the high-dimensional data to three energy performance indexes of the activity effect, the structure effect and the intensity. And then, those indexes and the production/conductivity of the chemical process are defined as inputs and outputs of the extreme learning machine respectively to build energy optimization and analysis model. Finally, the proposed method has been applied to optimizing and analyzing energy status of the ethylene system and the purified terephthalic acid solvent system in complex chemical processes. The experiment results show that the proposed method has the characteristics of fast learning, stable network outputs and high model accuracy in handling with the high-dimensional data. Moreover, it can optimize energy of chemical processes and guide the production operation. In our experiment, the production of ethylene plants can be increased by 5.33%, and the conductivity of purified terephthalic acid plants can be reduced by 0.046%. [ABSTRACT FROM AUTHOR]

With the increasing complexity of large-scale industrial production processes, the number of variable factors is increasing. As a result, it is demanding to predict process key variables accurately. Currently, most of soft sensor models using support vector regression and artificial neural networks are based on point prediction. The soft measurement models using the technique of point prediction can only track or fit set values. It is difficult to deal with the problem of system uncertainty and to make reliability analysis using the point prediction based soft sensors. To address this problem, this paper proposes a development method of soft sensor using the technique of prediction intervals. Under this condition, the prediction intervals instead of the point prediction of the stable operation of the industrial process system are used. The interval boundaries of the trend change can be utilized to quantify and estimate the associated uncertainty. The proposed prediction intervals based soft sensor is based on fuzzy information granularity and improved recurrent extreme learning machine. First, the fuzzy information granularity is adopted to get the lower bound, trend and upper bound of the interval. Secondly, an improved recurrent extreme learning machine is built to further enhance the ability of prediction intervals. In the improved extreme learning machine model, a feedback layer is adopted to store the hidden layer output, calculate the data trend change and dynamically update the outputs of the feedback layer. Third, the comprehensive interval evaluation function is used to evaluate the rationality of the interval results. Through case studies using a University of California Irvine dataset and the purified Terephthalic acid solvent system, the provided prediction intervals method can directly generate the upper and lower bounds for process key variables with high accuracy. • Novel soft sensor development based on prediction intervals is presented. • PIs using fuzzy information granularity and IRELM is proposed to predict variables. • Simulation results confirm the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]