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]

This paper considers the numerical approximation for the optimal supporting position and related optimal control of a catalytic reaction system with some control and state constraints, which is governed by a nonlinear partial differential equations with given initial and boundary conditions. By the Galerkin finite element method, the original problem is projected into a semi-discrete optimal control problem governed by a system of ordinary differential equations. Then the control parameterization method is applied to approximate the control and reduce the original system to an optimal parameter selection problem, in which both the position and related control are taken as decision variables to be optimized. This problem can be solved as a nonlinear optimization problem by a particle swarm optimization algorithm. The numerical simulations are given to illustrate the effectiveness of the proposed numerical approximation method. [ABSTRACT FROM AUTHOR]

This paper proposes a numerical approximation method for computational optimal control of a time fractional convection-diffusion-reaction system. The proposed method involves discretizing the spatial domain by finite element method, approximating the admissible controls by control parameterization, and then obtaining an optimal parameter selection problem which can be solved by numerical optimization algorithms such as sequential quadratic programming. Specifically, an implicit finite difference method is employed to solve the time fractional system, and the sensitivity method for gradient computation in integer order optimal control problems is adjusted to the fractional order case. Simulation results demonstrate the validity and accuracy of the proposed numerical approximation method. [ABSTRACT FROM AUTHOR]

This paper considers the numerical approximation for the time optimal control problem of a thermoelastic system with some control and state constraints. By the Galerkin finite element method (FEM), the original problem is projected into a semidiscrete optimal control problem governed by a system of ordinary differential equations. Then the optimal time and control parameterization method is applied to reduce the original system to an optimal parameter selection problem, in which both the optimal time and control are taken as decision variables to be optimized. This problem can be solved as a nonlinear optimization problem by a hybrid algorithm consisting of chaotic particle swarm optimization (CPSO) and sequential quadratic programming (SQP) algorithm. The numerical simulations demonstrate the effectiveness of the proposed numerical approximation method. [ABSTRACT FROM AUTHOR]

Grain transportation plays an important role in many relief and emergency supply chains. In this paper, we take the grain emergency vehicle scheduling model between multiware houses as the research object. Under the emergency environment, the aim of the problem is to maximize the utilization of vehicles and minimize the delay time. The randomness of the key parameters in grain emergency vehicle scheduling, such as time and demand, is determined through statistical analysis and the model is solved through robust optimization method. Besides, we apply the numerical examples for experimental analysis. We compare the robust optimization model with classic model to illustrate the differences and similarities between them. The results show that the uncertainty of both time and demand has great influence on the efficiency of grain emergency vehicle scheduling problem. [ABSTRACT FROM AUTHOR]

Abstract: Rough set theory (RS) has been a topic of general interest in the field of knowledge discovery and pattern recognition. Machine learning algorithms are known to degrade in performance when faced with many features (sometimes attributes) that are not necessary for rule discovery. Many methods for selecting a subset of features have been proposed. However, only one method cannot handle the complex system with many attributes or features, so a hybrid mechanism is proposed based on rough set integrating artificial neural network (Rough-ANN) for feature selection in pattern recognition. RS-based attributes reduction as the preprocessor can decrease the inputs of the NN and improve the speed of training. So the sensitivity of rough set to noise can be avoided and the system’s robustness is to be improved. A RS-based heuristic algorithm is proposed for feature selection. The approach can select an optimal subset of features quickly and effectively from a large database with a lot of features. Moreover, the validity of the proposed hybrid recognizer and solution is verified by the application of practical experiments and fault diagnosis in industrial process. [Copyright &y& Elsevier]

In order to recognize the coupling faults of complex industrial processes effectively, this paper proposed an AdaBoost ensemble (AdBE) model based on the reconstruction of local tangent space alignment (RLTSA). First, to obtain the low-dimensional manifold structure embedded in original data space, RLTSA algorithm is designed by constructing the tangent space in the neighborhood of each data point to represent the local geometry and then aligning them to obtain the embedding coordinates. Secondly, to solve the loss of global feature information, an affine matrix is used to inversely map the low-dimensional coordinates to restore the global structure information. Thirdly, based on the above reconstruction of local tangent space alignment, an AdaBoost ensemble (AdBE) classifier is constructed for multiple faults recognition in which the AdaBoost algorithm is used to improve the performance of Decision Tree (DT), and One vs. Rest (OvR) ensemble strategy is introduced to establish the RLTSA-AdBE model. Case studies are conducted using a three-dimensional S_curve data set and the Tennessee Eastman process (TEP) to respectively verify the performance of the RLTSA algorithm and the proposed RLTSA-AdBE model. The simulation results indicate that the proposed method guarantees high diagnosis accuracy and macro_F1 Score of coupling faults recognition. • AdaBoost Ensemble Based on Local Tangent Space Alignment is proposed. • An affine matrix is used to map low-dimensional coordinates to restore global structures. • AdaBoost ensemble (AdBE) classifier is constructed for multiple faults recognition. • Case studies of multi-faults using the Tennessee Eastman process are executed. • The effectiveness and feasibility of the proposed fault diagnosis method is conformed. [ABSTRACT FROM AUTHOR]

One of the key issues of the sustainable development in all countries is industrial productivity improvement, especially the production capacity improvement and energy-saving of complex chemical processes. Therefore, this paper proposes a production prediction and energy-saving model based on Extreme Learning Machine (ELM) integrated Interpretative Structural Modeling (ISM) and Analytic Hierarchy Process (AHP). The factors that affect the productivity are divided into different levers by the ISM. And then the attributes of each layer are fused by the AHP based on the entropy weight, which greatly reduces the complexity of the input attributes. Moreover, the production prediction and energy-saving model is established based on the ELM. Compared with the traditional ELM, the validity and the practicability of the proposed method are verified by University of California Irvine (UCI) datasets. Finally, the proposed method is applied in the production capacity prediction and energy-saving of ethylene production systems and Purified Terephthalic Acid (PTA) production systems. The experimental results show the proposed method could reduce the number of hidden layer nodes and improve the training time of the ELM. Furthermore, the prediction accuracy of the ethylene production and the PTA production reaches about 99% to improve the energy efficiency of complex chemical processes. [ABSTRACT FROM AUTHOR]

Most of existing modeling methods are based on point prediction. However, the accuracy of point prediction cannot meet the actual demand due to existence of high noise, volatility, complexity and irregularity inherent in the chemical process data. In order to solve this problem, a hybrid high-quality prediction intervals (PIs) method integrating complementary ensemble empirical mode decomposition (CEEMD), sample entropy (SE), and improved multi-kernel relevant vector machine (RVM) is proposed in the paper. The proposed PIs method mainly consists of three aspects: Firstly, CEEMD is adopted to decompose the original data into several independent intrinsic mode functions (IMFS), and then SE is used to analyze the complexity of the extracted IMFs to obtain recombinant components; Secondly, an improved multi-kernel RVM (MRVM) is presented to predict recombinant components independently, in which the linear kernel and the Gaussian kernel are combined; Thirdly, the predicted components are aggregated to obtain an ensemble result using another MRVM for constructing the high-quality PIs. To verify the performance of the proposed PIs method, a purified Terephthalic acid (PTA) solvent system is selected. Comparative simulation results demonstrate that the proposed PIs method greatly outperforms on coverage probability and sharpness in all the step predictions. [ABSTRACT FROM AUTHOR]

Recently, zebrafish has received more and more attention due to its wide range of applications such as regeneration promoting therapeutics and drug discovery. Therefore, vision‐based trackers are utilized to record the swimming trajectory of zebrafish. In this paper, a re‐association method is introduced in the 3D reconstruction process to generate missed targets caused by occlusion. Since the variation of the overall tracking targets has the property of continuity and stability, a topology association model (TAM) is proposed by point group similarity into the tracking framework. TAM describes the movement of zebrafish from the macroscopic level and utilizes the changes of the point group structure for tracking. Experimental results show that the tracking framework enhances the overall performance and promotes the trajectory integrity. On the latest 3D‐ZeF20 benchmark, state‐of‐the‐art results are achieved. In addition, TAM tracking framework is applied to 2D general tracking to prove that the method is useful and have great advantage in other scenarios with relatively stable amount of targets as well. [ABSTRACT FROM AUTHOR]

With the scale expansion of industrial processes, safety has become one of its important links and the requirements for safety monitoring are getting higher. How to realize timely and effective fault diagnosis, especially for incipient faults, has attracted more discussion and research. This paper proposes a novel pattern classification integrated global−local preserving projections (GLPP) and improved adaptive rank-order morphological filter (IAROMF) for fault diagnosis. First, in order to preserve the global manifold information and local manifold information of the data, GLPP is introduced to extract the features of the data to obtain the test signal and the template signal. Second, AROMF transformation is performed on the test signal and template signal to obtain the output trend feature. Third, as the pattern matching by Euclidean distance-based AROMF has the restriction of sequence timing and the feature points need to be strictly corresponding, the Weighted Dynamic Time Warping (WDTW) distance is used to calculate the total error of iteration between the template trend and the output trend. In order to prove the effectiveness of the method proposed in this paper, a case study was carried out on the Tennessee Eastman (TE) process. The experiment results illustrated that the novel pattern classification method proposed in this paper has higher diagnostic accuracy than other fault diagnosis methods, especially for incipient faults. [ABSTRACT FROM AUTHOR]

Multi-objective optimization problems are difficult to solve in that the optimized objectives are usually conflicting with each other. It is usually hard to find an optimal solution that satisfies all objectives from the mathematical point of view. Unlike analytical methods and classical numerical methods, which require strict mathematical calculation or defined initial search values, intelligent optimization algorithms are heuristic algorithms able to find global optimal solutions. In this paper, we make a brief introduction of multi-objective optimization problems and some state-of-the-art intelligent algorithms. In order to get the final optimal solution in the real-world multi-objective optimization problems, trade-off methods including a priori methods, interactive methods, Pareto-dominated methods and new dominance methods are utilized. Moreover, we give a review of multi-objective optimization methods application in the environmental protection fields, for optimization objectives of energy saving, emissions reduction and cost reduction, etc. At last, a whole summary about current difficulties existed in the multi-objective optimization problem is given out, serving as suggestions or guidance for future researches. [ABSTRACT FROM AUTHOR]

The objective of this article is to research and design a multi-objective operation optimization strategy and comprehensive evaluation method of solutions, to efficiently solve the multi-objective operation optimization problem of ethylene cracking furnace. An adaptive multi-objective particle swarm optimization (AMOPSO) algorithm is proposed and developed based on dynamic analytic hierarchy process (AHP). The algorithm adopts fuzzy consistent matrix to select the global best solution, which ensures the right direction of particle evolution. Furthermore, the evolution state is measured to adjust the weight and learning coefficients adaptively. The proposed method is applied to the operation optimization of ethylene cracking furnace. Two cases are studied including the fixed cracking cycle with four objectives and the non-fixed cracking cycle with five objectives. According to the preferences, decision makers can select the appropriate operation optimization conditions from alternative Pareto optimal solutions by the results of fuzzy evaluation. A feasible solution is provided for the multi-objective operation optimization of ethylene cracking furnace. [ABSTRACT FROM AUTHOR]

Multi‐object tracking is an important branch of computer vision, which is mostly used for behavior recognition and event analysis. At present, most of the research focuses on the accuracy of tracking. However, the real‐time performance is also urgently desired but there is lack of research. As a result, Deepsort, proposed 5 years ago, is still the most widely used tracker in real applications. In this paper, a Bilateral Association Tracking (BAT) framework is proposed. It uses tracklet as the basic node instead of discrete detection for tracking. Meanwhile, a Parzen density based Hierarchical Agglomerative Clustering (P‐HAC) algorithm is introduced to describe the density distribution of targets and generate tracklets with high confidence. In addition, Dual Appearance Features (DAF) is proposed which considers both spatial and temporal features of tracklets and promotes the accuracy of tracklet association. Experiments are conducted on popular benchmarks such as MOT2017, Visdrone and KITTI. BAT outperforms Deepsort on both association accuracy and trajectory integrity without obvious efficiency decline. Compared with other state‐of‐the‐art trackers, BAT shows significant advantage on computational cost while performing competitive tracking accuracy as well. It is hoped that the research can promote the applications on real‐time tracking in the near future. [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]

DEA (data envelopment analysis) has been widely used for the efficiency analysis of industrial production process. However, the conventional DEA model is difficult to analyze the pros and cons of the multi DMUs (decision-making units). The DEACM (DEA cross-model) can distinguish the pros and cons of the effective DMUs, but it is unable to take the effect of the uncertainty data into account. This paper proposes an efficiency analysis method based on FDEACM (fuzzy DEA cross-model) with Fuzzy Data. The proposed method has better objectivity and resolving power for the decision-making. First we obtain the minimum, the median and the maximum values of the multi-criteria ethylene energy consumption data by the data fuzzification. On the basis of the multi-criteria fuzzy data, the benchmark of the effective production situations and the improvement directions of the ineffective of the ethylene plants under different production data configurations are obtained by the FDEACM. The experimental result shows that the proposed method can improve the ethylene production conditions and guide the efficiency of energy utilization during ethylene production process. [ABSTRACT FROM AUTHOR]

Signed directed graph (SDG), as awidely applied fault diagnosisapproach, is unable to express complicated logic relations other thanlogic OR and usually results in spurious interpretations. To solvethe problem, a semiquantitative fault diagnosis approach based onthe model of multilogic probabilistic SDG (MPSDG) with Bayesian inferenceis proposed. The MPSDG model introduces the logic gates to describemultiple logic causalities between process variables, and the prioriprobabilistic parameters in MPSDG are decided by the historical malfunctionfrequencies and the deviation of variables. When a failure occurs,the backtracking algorithm using the consistent rule is conductedimmediately, and the posterior probabilities of each searched faultare computed and sorted by a set of Bayesian inference mechanisms.Thus, the real reason is further distinguished. This MPSDG based faultdiagnosis approach is applied to two examples: a continuous stirredtank heater (CSTH) process and a Tennessee Eastman (TE) process. Theexperimental results demonstrate that the proposed approach is superiorto the conventional SDG approach and can diagnose the production faultsmore accurately. [ABSTRACT FROM AUTHOR]

Anomaly detection plays a critical role in ensuring the quality and safety of industrial processes. Process mining, as an emerging technology, has proven effective in extracting knowledge and process rules inherent in process events. However, industrial time series data possess characteristics such as high noise, and data redundancy, posing challenges for accurately assessing system anomalies using traditional data-driven methods. To address these challenges, this paper proposes a Trend-Value Fusion Process Mining (TVPM) approach based on the representation of industrial process events to tackle anomaly detection in industrial processes. Firstly, TVPM introduces a fusion measure that combines data trends and mean-value to provide a comprehensive description of operating events in industrial processes. This fusion measure serves as a vital tool for capturing the complex details and features of industrial events. Additionally, a novel process discovery algorithm is developed to extract behavioral patterns and sequence information from events. Finally, a process abnormal state detection model is constructed by leveraging the comprehensive and in-depth information obtained from TVPM. The proposed method is applied to an industrial coal gasification process, yielding satisfactory results. • An approach to TVPM of industrial process operating events for abnormal detection was proposed. • This paper introduced a method for extracting process event constructs that blend value and trend information. • The final process abnormal detection framework was applied to an actual industrial process. [ABSTRACT FROM AUTHOR]

Abstract: Despite the fact that a stand-alone ideal heat-integrated distillation column (ideal HIDiC) can be thermodynamically efficient and operationally stable, the application of an ideal HIDiC system to separate a close-boiling multi-component mixture is still a challenging problem because of the possibility of strong interactions within/between the ideal HIDiCs involved. In this work, employment of two ideal HIDiCs to separate a close-boiling ternary mixture is studied in terms of static and dynamic performance. It is found that the ideal HIDiC system can be a competitive alternative with a substantial energy saving and comparable dynamic performance in comparison with its conventional counterpart. The direct sequence appears to be superior to the indirect sequence due to the relatively small vapor flow rates to the compressors. Controlling the bottom composition of the first ideal HIDiC with the pressure elevation from the stripping section to the rectifying section helps to suppress the disturbances from the feed to the second ideal HIDiC. Special caution should, however, be taken when the latent heat of the distillates is to be recovered within/between the ideal HIDiCs involved, because a positive feedback mechanism may be formed and give rise to additional difficulties in process operation. [Copyright &y& Elsevier]

With the rapid development of the internet technology, a large amount of internet text data can be obtained. The text classification (TC) technology plays a very important role in processing massive text data, but the accuracy of classification is directly affected by the performance of term weighting in TC. Due to the original design of information retrieval (IR), term frequency-inverse document frequency (TF-IDF) is not effective enough for TC, especially for processing text data with unbalanced distributions in internet media reports. Therefore, the variance between the DF value of a particular term and the average of all DFs DF ¯ , namely, the document frequency variance (ADF), is proposed to enhance the ability in processing text data with unbalanced distribution. Then, the normal TF-IDF is modified by the proposed ADF for processing unbalanced text collection in four different ways, namely, TF-IADF, TF-IADF+, TF-IADFnorm, and TF-IADF+norm. As a result, an effective model can be established for the TC task of internet media reports. A series of simulations have been carried out to evaluate the performance of the proposed methods. Compared with TF-IDF on state-of-the-art classification algorithms, the effectiveness and feasibility of the proposed methods are confirmed by simulation results. [ABSTRACT FROM AUTHOR]

• A novel membrane algorithm is proposed for multi-objective optimization problems. • Best objects are communicated and dominated ones are eliminated in competition. • The algorithm produces well-distributed and converged solutions. • The results reduce 2698 tons of feed oil and 8282 tons of carbon dioxide emission. As a relatively high energy-consuming in China, the chemical process is important and has potential to be optimized for energy saving, economic benefits and environmental protection. Multiple goals can be coordinated using multi-objective optimization algorithms. In order to improve the exploration and exploitation abilities in optimizing multiple objectives, a constrained competing evolutionary membrane algorithm is proposed. The proposed algorithm takes advantages of the distributed and parallel computing mode of the membrane computing. Populations are evolved independently in each membrane and share information between membranes based on competing communication rules. Meanwhile, the skin membrane archives global elitist solutions and serves as guidance for inner evolution processes. Finally, the optimization experiments on the ethylene cracking process, as an important production of complex chemical processes, prove that the proposed algorithm can provide enough selection for decision makers with well-distributed and converged candidate solutions. Furthermore, the solutions lead the ethylene cracking process to reach the coordinated optimum ethylene or propylene production, oil consumption reduction and carbon dioxide emission reduction. In average, the optimization solutions bring about reduction of 2697.58 tons of feed oil and 8281.57 tons of carbon dioxide emission. [ABSTRACT FROM AUTHOR]

Graphical abstract Highlights • A novel AP-DEACM method is proposed. • Performance evaluation and energy optimization model is obtained. • This proposed model is efficient in energy saving and carbon emission reduction. • The energy saving potential of ethylene and PTA production plants are 2.78% and 1.26%. • Carbon emission reduction potential is 3.62% in ethylene production plants. Abstract Data Envelopment Analysis (DEA) has been widely used in performance and energy efficiency evaluation. However, in the traditional DEA, the effective of each decision making unit (DMU) is evaluated through its own optimized perspective and regardless of other DMUs influence, which may result in too many effective DMUs. And the DEA cross-model (DEACM) can distinguish the effective DMUs better by constructing a cross-efficiency matrix, but the optimal weight of the DMU may not be unique, so the cross efficiency of the DEACM may be different. Therefore, this paper proposes a novel DEACM based on the affinity propagation (AP) clustering algorithm (AP-DEACM). Through the AP clustering algorithm, the high impact data affecting the performance capacity and energy saving are obtained. Then the better effective DMU is identified through the high discrimination of the AP–DEACM. Finally, the proposed AP-DEACM is used for performance evaluation and energy optimization modeling of the Pure Terephthalic Acid (PTA) production process and the ethylene industrial process in complex petrochemical industries. The experimental results show that the energy saving potential of PTA production plants and ethylene production plants are 2.78% and 1.26%, respectively, and the average value of carbon emission savings potential is 3.62% in ethylene production plants. [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]

Energy management and optimization play a key effect in the sustainable development. However, the uncertain data has a direct impact on the production prediction and energy optimization of complex petrochemical industries. Therefore, this paper proposes a novel energy management and optimization model based on the fuzzy extreme learning machine (FELM) method integrated the fuzzy set theory. The minimal, the median and the maximal values of the energy consumption data are obtained by data fuzzification to solve the problem of the fluctuation and uncertainty data. And the cross recombination of triangular fuzzy numbers (TFNs) is applied in the training of the FELM. Moreover, the upper and the lower limits of efficiency values are obtained on the basis of the network generalization to analyze the energy conservation and saving potentials. Furthermore, the FELM has better predictive performance and training speed than fuzzy error back propagation network (FBP) and fuzzy radical basis function network (FRBF) though University of California Irvine (UCI) standard datasets. Finally, the proposed method is applied to manage and optimize the energy status of China ethylene industry in complex petrochemical industries. The experimental results show that the proposed method is effective and applicable in the energy-saving potential, which is indicated up to about 15%. [ABSTRACT FROM AUTHOR]

Single layer feed-forward network (SLFN) is well applied to find mapping relationships between the input data and the output data. However, the SLFN has two obvious shortcomings of the indetermination structure and parameters. Therefore, this paper proposes a novel self-organizing cosine similarity learning network (SO-CSLN), which can obtain a stable structure and suitable parameters. The hidden layer nodes of the SO-CSLN are determined by the rank of the sample covariance matrix based on the central limit theorem. And then the weights are obtained by the entropy theory and the cosine similarity theory. Moreover, compared with the SLFN, the proposed algorithm can overcome the shortcomings of the SLFN and provide better performance with faster convergence and smaller generalization error through different UCI data sets. Finally, the proposed method is applied to building the production prediction model of the ethylene production system in petrochemical industries. The experiment results show that the effectiveness and the practicality of the proposed method. Meanwhile, it can guide ethylene production and improve the energy efficiency. [ABSTRACT FROM AUTHOR]

The complex chemical process is a high pollution and high energy consumption industrial process. Therefore, it is very important to analyze and evaluate the energy and environment efficiency of the complex chemical process. Data Envelopment Analysis (DEA) is used to evaluate the relative effectiveness of decision-making units (DMUs). However, the traditional DEA method usually cannot genuinely distinguish the effective and inefficient DMU due to its extreme or unreasonable weight distribution of input and output variables. Therefore, this paper proposes an energy and environment efficiency analysis method based on an improved environment DEA cross-model (DEACM) method. The inputs of the complex chemical process are divided into energy and non-energy inputs. Meanwhile, the outputs are divided into desirable and undesirable outputs. And then the energy and environment performance index (EEPI) based on the cross evaluation is used to represent the overall performance of each DMU. Moreover, the improvement direction of energy-saving and carbon emission reduction of each inefficiency DMU is quantitatively obtained based on the self-evaluation model of the improved environment DEACM. The results show that the improved environment DEACM method has a better effective discrimination than the original DEA method by analyzing the energy and environment efficiency of the ethylene production process in complex chemical processes, and it can obtain the potential of energy-saving and carbon emission reduction of ethylene plants, especially the improvement direction of inefficient DMUs to improve energy efficiency and reduce carbon emission. [ABSTRACT FROM AUTHOR]

Energy saving and management of complex chemical processes play a crucial role in the sustainable development procedure. In order to analyze the effect of the technology, management level, and production structure having on energy efficiency and energy saving potential, this paper proposed a novel integrated framework that combines index decomposition analysis (IDA) with energy saving potential method. The IDA method can obtain the level of energy activity, energy hierarchy and energy intensity effectively based on data-drive to reflect the impact of energy usage. The energy saving potential method can verify the correctness of the improvement direction proposed by the IDA method. Meanwhile, energy efficiency improvement, energy consumption reduction and energy savings can be visually discovered by the proposed framework. The demonstration analysis of ethylene production has verified the practicality of the proposed method. Moreover, we can obtain the corresponding improvement for the ethylene production based on the demonstration analysis. The energy efficiency index and the energy saving potential of these worst months can be increased by 6.7% and 7.4%, respectively. And the carbon emissions can be reduced by 7.4–8.2%. [ABSTRACT FROM AUTHOR]

Ethylene production shares the common characteristics of different techniques and scales, high dimension and multi-correlation. However, the existing methods do not take the influence of the technology, scale and materials into account. In order to analyze the energy efficiency of ethylene plants better, this paper proposes a linear optimization fusion model based on fuzzy C-means (FCM) clustering. The FCM clustering is used to obtain the corresponding classification and clustering centers of the large scale time series data of the ethylene production process. Then the mean squares of time-series variables are calculated by various clustering centers. The multidimensional energy efficiency benchmarking of ethylene plants can be extracted by the fusion weighting vectors in linear optimization fusion model. The experimental results indicate that the proposed method intuitively reveals the running state and the operating level of ethylene plants and accurately identify the reason of energy consumption for improving energy efficiency. [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]

Stepless capacity control technology for reciprocating compressors is a key contributor to energy saving for the petroleum and petrochemical industries. Devices called 'unloaders' are utilized to control the capacity of the compressor by forcibly holding the suction valves open during a variable portion of the compression stroke to control the compressor output. This approach can also lead to various faults of the suction valve. This paper describes the simulation and experimental studies of the transient motion of suction valves under stepless capacity control. Beginning with mathematical models for the normal cycle, improved models of a reciprocating compressor under stepless capacity control have been built. A simulation study of the working process of a double-acting reciprocating compressor has been completed. Theoretical formulas for the transient motion of the valve plate under complicated conditions and the dynamic pressure in the cylinder are compared with the experimental results. Based on the above simulations, a finite element analysis of the valve plate and valve seat has been completed. The experiment results showed that the vibration of the compressor cylinder under complicated conditions was consistent with numerical simulation results. Research presented in this paper is significant in providing tools for diagnosing faults in order to optimize the design of reciprocating compressors that utilize a stepless capacity control system. [ABSTRACT FROM AUTHOR]

This paper presents a data-based framework for distributed actuator fault identification and accommodation in networked process systems controlled over a resource-constrained communication medium. Initially, a quasi-decentralized networked control structure is designed to stabilize the plant in the absence of faults. The structure consists of a set of local model-based control systems that communicate with one another at discrete times. An explicit characterization of the networked closed-loop stability region is obtained in terms of the update period, the accuracy of the models, and the choice of controller design parameters. To address the actuator fault identification problem, a set of local fault diagnosis agents are designed and embedded within the various subsystems. Each agent uses a moving-horizon parameter estimation scheme to estimate on-line the size and location of the local faults using the locally sampled states and the model state estimates for the interconnected units. Potential discrepancies or ambiguities in the local fault diagnosis results, which may be caused by the strong dynamic coupling between the individual subsystems and the presence of plant-model mismatch, are reconciled by means of a fault estimation confidence interval which is obtained by analyzing the networked closed-loop dynamics at update times. Once the locations and magnitudes of the actuator faults are identified, the resulting estimates are transmitted to a higher-level supervisor to select and implement a suitable fault accommodation strategy. A number of stability-preserving fault accommodation strategies are devised, including updating the post-fault models, adjusting the controllers’ parameters, or a combination of both. The selection of the appropriate fault accommodation strategy is made on the basis of the estimated fault magnitude and the characterization of the networked closed-loop stability region. Finally, the developed methodology is illustrated using a reactor–separator process example subject to both sudden and incipient control actuator faults. [ABSTRACT FROM AUTHOR]

The petrochemical industry evaluation is affected by numerous factors. Many previous studies proposed a use of data envelopment analysis (DEA) as a methodology for energy efficiency analysis in the petrochemical industry. However, excessive decision-making units (DMUs) of DEA model result in difficulties in evaluation and comparison of the different DMUs. In this paper, a new energy analysis framework of petrochemical industrial processes based on DEA integrated interpretative structural model (ISM) is proposed. The ISM method is brought up based on the partial correlation coefficient method to find the main factors and basic reasons that affect the energy consumption of the ethylene production system, which serve as the inputs of the DEA. Meanwhile, ethylene, propylene and C4 productions of the ethylene production system sever as the outputs of the DEA. Then the fractional DEA model is solved by using the linear programming method. The proposed evaluation method can overcome the shortcomings of the DEA model mentioned above, and also is able to reflect the effectiveness of the DMUs and guide the improvement directions of the ineffective DMUs based on slack variables. Our approach is applied in the energy efficiency analysis of Chinese ethylene industry in the petrochemical field. The empirical results show that the proposed energy consumption analysis method is valid and efficient in improvements of energy efficiency in ethylene production systems. [ABSTRACT FROM AUTHOR]

This paper gives a survey of the inverse boosting algorithm which employs an inverse error vector to produce new sample distributions. The experimental result shows that the inverse boosting can outperform normal boosting in some cases. Further experiments on several benchmark real-world data sets available from the UCI repository are taken to get a better insight into the inverse boosting algorithm, and then we find that the performance of the ensemble is determined by the performance of its base classifiers. This distinctive feature of inverse boosting indicates that traditional ways to improve the performance of an ensemble through enhancing the diversity between the base classifier are invalid here. Therefore, this paper proposes a method with pertinence to improve the performance of inverse boosting. [ABSTRACT FROM PUBLISHER]

Abstract: A precise mechanistic model is fundamental in simulation, control and optimization of ethylene pyrolysis process. In the Kumar kinetics model proposed by Kumar and Kunzru, there are ten changeable selectivity coefficients and minor-changeable kinetics parameters in the primary reaction equation. They are mainly determined by oil properties, especially the oil composition. This paper proposes a new method of compromising adjustment solution based on target decomposition strategy and Error Correction Chaos Optimization (ECCO) algorithm to mainly acquire rational primary coefficients, and kinetics parameters when necessary. The core idea is to realize atoms balances of the carbon and hydrogen in the primary reaction, as well as minimum yield errors of products based on ECCO algorithm. It exceeds existing methods mentioned by other literatures in its preferable compromise between overall elemental balances and minimal yield errors. It also takes minor tuning of kinetics parameters into consideration. Moreover, this method has been proven effective and applicable to many naphthas with different properties. These data are from a real ethylene plant. The results are helpful in the design of optimal operational conditions and ultimately in controlling of ethylene cracking furnaces which will be discussed briefly. [Copyright &y& Elsevier]

Data fusion is an emerging technology to fuse data from multiple data or information of the environment through measurement and detection to make a more accurate and reliable estimation or decision. In this Article, energy consumption data are collected from ethylene plants with the high temperature steam cracking process technology. An integrated framework of the energy efficiency estimation is proposed on the basis of data fusion strategy. A Hierarchical Variable Variance Fusion (HVVF) algorithm and a Fuzzy Analytic Hierarchy Process (FAHP) method are proposed to estimate energy efficiencies of ethylene equipments. For different equipment scales with the same process technology, the HVVF algorithm is used to estimate energy efficiency ranks among different equipments. For different technologies based on HVVF results, the FAHP method based on the approximate fuzzy eigenvector is used to get energy efficiency indices (EEI) of total ethylene industries. The comparisons are used to assess energy utilization states of different equipments and technologies. It is helpful to decision-makers to identify quantitative energy consumptions and major influence factors to improve energy-saving chances. Furthermore, the proposed strategy can be used to evaluate energy efficiencies in other process units too. [ABSTRACT FROM AUTHOR]

Abstract: Two new types of hierarchy probability cost analysis (HPCA) model incorporating money allocated is money spent (MAIMS) principle based on definite work breakdown structure (WBS) level for EPC (engineering, procurement and construction) projects are presented. The proposed models have skillfully solved dilemma to appropriate cost elements and maximize the efficiency of information for cost risk analysis. Macroscopic and microscopic risk analysis of the project cost elements are introduced for meaningful model input. The illustration of an actual bidding EPC project substantiates that proposed integrating HPCA-hierarchy MAIMS models have demonstrated effective and viable for EPC projects. [Copyright &y& Elsevier]

Abstract: In the first three papers of this series, it has been shown that strengthening internal heat integration within a reactive distillation column involving reactions with high thermal effect is really effective for the reduction of utility consumption and capital investment besides the improvement in process dynamics and operation. One important issue that remains unstudied so far is the influences of reaction selectivity upon the reinforcement of internal heat integration, since the reaction operation is often accompanied by side-reactions and the maintenance of a high selectivity is extremely necessary in process synthesis and design. A reactive distillation column synthesizing high-purity ethylene glycol through the hydration of ethylene oxide is chosen and studied in this work. Because of the unfavorable physicochemical properties of the reacting mixture separated (e.g., the fairly large volatility between the reactants and the existence of a consecutive side-reaction), the process represents a challenging problem for the reinforcement of internal heat integration. Intensive comparison is conducted between the process designs with and without the consideration of further internal heat integration between the reaction operation and the separation operation involved, and it has been found that seeking further internal heat integration still leads to a substantial reduction of energy requirement, in addition to a further abatement in capital investment. Moreover, a favorable effect is again observed upon the process dynamics and operability. These striking outcomes manifest evidently that seeking further internal heat integration should be considered in process synthesis and design irrespective of what a reaction selectivity has been assigned. [Copyright &y& Elsevier]

Abstract: In this work, a novel temperature control scheme is derived for an ideal heat-integrated distillation column (ideal HIDiC), in which a temperature difference between two stages is designated as the controlled variable to circumvent the side-effect of continuous pressure variations in the rectifying section. For making an appropriate compensation to the changes in operating conditions, an inferential signal extracted from the feed stage, , is used to adjust the set-point of the temperature difference controller. Control of two ideal HIDiCs, separating, respectively, a binary mixture of benzene and toluene and an ideal ternary mixture of hypothetical components A–C is studied. It is demonstrated that the proposed temperature control scheme can retain a stable operation around the vicinity of the nominal steady state with improved dynamic performance and tolerable steady state discrepancies in comparison with the direct composition control scheme. Moreover, the proposed temperature control scheme is also found to be quite robust to the selection of temperature measurements. [Copyright &y& Elsevier]

Abstract: Process intensification calls for the combination of two or more conventional unit operations within one framework, thus giving rise to a challenging coordination problem in process synthesis and design. Seeking synergistic effect among all the conventional unit operations involved is found to be an important principle for process development. Three cases of process intensification are studied to evaluate the principle, including: (i) a hypothetical reactive distillation system; (ii) a reactive distillation column for the hydration of ethylene oxide; (iii) an ideal heat-integrated distillation column. It is demonstrated that simply combining two or more conventional unit operations together does not necessarily tap out the full potentials of capital investment reduction and energy saving. Only after the synergistic effect has been deliberately considered in process synthesis and design, can process intensification be carried out in the most effective manner. Furthermore, seeking synergistic effect appears frequently to yield improved process dynamics and provide additional redundancy to process operation because the underlying conflicts could be attenuated among all the conventional unit operations involved. [Copyright &y& Elsevier]

As the most effective indicator for energy saving and emission reduction, energy efficiency evaluation is widely used in complex petrochemical industries. It is nowadays common to combine traditional mechanism methods based on momentum transport, energy transport, quality transport (TT) and reaction engineering (RG) (TT-RG), with data-driven artificial intelligence methods. Using the combined method to achieve production optimization and energy saving by analyzing the evaluation indicator of energy efficiency has gradually become an important part in complex petrochemical industries. Therefore, this paper introduced the main methods and the latest research results of energy efficiency evaluation of complex petrochemical industries. These methods are mainly divided into three parts, including the mechanism methods based on TT-RG, the data-driven artificial intelligence methods, and the hybrid methods combining the mechanism and the data-driven. Then, different methods are compared and described in detail. Moreover, the best method for evaluating the energy efficiency can be found to provide theoretical guidance for energy saving and emission reduction of complex petrochemical industries. Finally, the future development direction for energy efficiency evaluation in complex petrochemical industries is given. Image 1 • Energy efficiency evaluation methods of petrochemical industries are reviewed and compared. • The latest research results of energy efficiency evaluation of petrochemical industries are analyzed. • The development direction of energy efficiency evaluation of petrochemical industries are given. [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]