Data-driven Wasserstein distributionally robust chance-constrained optimization for crude oil scheduling under uncertainty

Crude oil scheduling optimization is an effective method to enhance the economic benefits of oil refining.But uncertainties,including uncertain demands of crude distillation units(CDUs),might make the production plans made by the traditional deterministic optimization models infeasible.A data-driven Wasserstein distributionally robust chance-constrained(WDRCC)optimization approach is proposed in this paper to deal with demand uncertainty in crude oil scheduling.First,a new deterministic crude oil scheduling optimization model is developed as the basis of this approach.The Wasserstein distance is then used to build ambiguity sets from historical data to describe the possible realizations of probability distributions of uncertain demands.A cross-validation method is advanced to choose suitable radii for these ambiguity sets.The deterministic model is reformulated as a WDRCC optimization model for crude oil scheduling to guarantee the demand constraints hold with a desired high probability even in the worst situation in ambiguity sets.The proposed WDRCC model is transferred into an equivalent conditional value-at-risk representation and further derived as a mixed-integer nonlinear programming counterpart.Industrial case studies from a real-world refinery are conducted to show the effectiveness of the proposed method.Out-of-sample tests demonstrate that the solution of the WDRCC model is more robust than those of the deterministic model and the chance-constrained model.

Multi-objective modeling and optimization for scheduling of cracking furnace systems

Cracking furnace is the core device for ethylene production. In practice, multiple ethylene furnaces are usually run in parallel. The scheduling of the entire cracking furnace system has great significance when multiple feeds are simultaneously processed in multiple cracking furnaces with the changing of operating cost and yield of product. In this paper, given the requirements of both profit and energy saving in actual production process, a multi-objective optimization model contains two objectives, maximizing the average benefits and minimizing the average coking amount was proposed. The model can be abstracted as a multi-objective mixed integer non- linear programming problem. Considering the mixed integer decision variables of this multi-objective problem, an improved hybrid encoding non-dominated sorting genetic algorithm with mixed discrete variables （MDNSGA-II） is used to solve the Pareto optimal front of this model, the algorithm adopted crossover and muta- tion strategy with multi-operators, which overcomes the deficiency that normal genetic algorithm cannot handle the optimization problem with mixed variables. Finally, using an ethylene plant with multiple cracking furnaces as an example to illustrate the effectiveness of the scheduling results by comparing the optimization results of multi-objective and single objective model.

A local space transfer learning-based parallel Bayesian optimization with its application

The optimization of process parameters in polyolefin production can bring significant economic benefits to the factory.However,due to small data sets,high costs associated with parameter verification cycles,and difficulty in establishing an optimization model,the optimization process is often restricted.To address this issue,we propose using a transfer learning Bayesian optimization strategy to improve the efficiency of parameter optimization while minimizing resource consumption.Specifically,we leverage Gaussian process(GP)regression models to establish an integrated model that incorporates both source and target grade production task data.We then measure the similarity weights of each model by comparing their predicted trends,and utilize these weights to accelerate the solution of optimal process parameters for producing target polyolefin grades.In order to enhance the accuracy of our approach,we acknowledge that measuring similarity in a global search space may not effectively capture local similarity characteristics.Therefore,we propose a novel method for transfer learning optimization that operates within a local space(LSTL-PBO).This method employs partial data acquired through random sampling from the target task data and utilizes Bayesian optimization techniques for model establishment.By focusing on a local search space,we aim to better discern and leverage the inherent similarities between source tasks and the target task.Additionally,we incorporate a parallel concept into our method to address multiple local search spaces simultaneously.By doing so,we can explore different regions of the parameter space in parallel,thereby increasing the chances of finding optimal process parameters.This localized approach allows us to improve the precision and effectiveness of our optimization process.The performance of our method is validated through experiments on benchmark problems,and we discuss the sensitivity of its hyperparameters.The results show that our proposed method can significantly improve the efficiency of process parameter optimization,reduce the dependence on source tasks,and enhance the method's robustness.This has great potential for optimizing processes in industrial environments.

Graph convolutional network for axial concentration profiles prediction in simulated moving bed

The simulated moving bed(SMB)chromatographic separation is a continuous compound separation process based on the differences in adsorption capacity exhibited by distinct constituents of a mixture on the fluid phase and stationary phase.The prediction of axial concentration profiles along the beds in a unit is crucial for the operating optimization of SMB.Though the correlation shared by operating variables of SMB has an enormous impact on the operational state of the device,these correlations have been long overlooked,especially by the data-driven models.This study proposes an operating variable-based graph convolutional network(OV-GCN)to enclose the underrepresented correlations and precisely predict axial concentration profiles prediction in SMB.The OV-GCN estimates operating variables with the Spearman correlation coefficient and incorporates them in the adjacency matrix of a graph convolutional network for information propagation and feature extraction.Compared with Random Forest,K-Nearest Neighbors,Support Vector Regression,and Backpropagation Neural Network,the values of the three performance evaluation metrics,namely MAE,RMSE,and R^(2),indicate that OV-GCN has better prediction accuracy in predicting five essential aromatic compounds'axial concentration profiles of an SMB for separating p-xylene(PX).In addition,the OV-GCN method demonstrates a remarkable ability to provide high-precision and fast predictions in three industrial case studies.With the goal of simultaneously maximizing PX purity and yield,we employ the non-dominated sorting genetic algorithm-II optimization method to perform multi-objective optimization of the PX purity and yield.The outcome suggests a promising approach to extracting and representing correlations among operating variables in data-driven process modeling.

Solving chemical dynamic optimization problems with ranking-based differential evolution algorithms

Dynamic optimization problems(DOPs) described by differential equations are often encountered in chemical engineering. Deterministic techniques based on mathematic programming become invalid when the models are non-differentiable or explicit mathematical descriptions do not exist. Recently, evolutionary algorithms are gaining popularity for DOPs as they can be used as robust alternatives when the deterministic techniques are invalid. In this article, a technology named ranking-based mutation operator(RMO) is presented to enhance the previous differential evolution(DE) algorithms to solve DOPs using control vector parameterization. In the RMO, better individuals have higher probabilities to produce offspring, which is helpful for the performance enhancement of DE algorithms. Three DE-RMO algorithms are designed by incorporating the RMO. The three DE-RMO algorithms and their three original DE algorithms are applied to solve four constrained DOPs from the literature. Our simulation results indicate that DE-RMO algorithms exhibit better performance than previous non-ranking DE algorithms and other four evolutionary algorithms.

Total plant performance evaluation based on big data: Visualization analysis of TE process

The performance evaluation of the process industry, which has been a popular topic nowadays, can not only find the weakness and verify the resilience and reliability of the process, but also provide some suggestions to improve the process benefits and efficiency. Nevertheless, the performance assessment principally concentrates upon some parts of the entire system at present, for example the controller assessment. Although some researches focus on the whole process, they aim at discovering the relationships between profit, society, policies and so forth, instead of relations between overall performance and some manipulated variables, that is, the total plant performance. According to the big data of different performance statuses, this paper proposes a hierarchical framework to select some structured logic rules from monitored variables to estimate the current state of the process. The variables related to safety and profits are regarded as key factors to performance evaluation. To better monitor the process state and observe the performance variation trend of the process, a classificationvisualization method based on kernel principal component analysis(KPCA) and self-organizing map(SOM) is established. The dimensions of big data produced by the process are first reduced by KPCA and then the processed data will be mapped into a two-dimensional grid chart by SOM to evaluate the performance status. The monitoring method is applied to the Tennessee Eastman process. Monitoring results indicate that off-line and on-line performance status can be well detected in a two-dimensional diagram.

Study on co-cracking performance of different hydrocarbon mixture in a steam pyrolysis furnace

Co-cracking is a process where the mixtures of different hydrocarbon feedstocks are cracked in a steam pyrolysis furnace, and widely adopted in chemical industries. In this work, the simulations of the co-cracking of ethane and propane, and LPG and naphtha mixtures have been conducted, and the software packages of COILSIM1 D and Sim CO are used to account for the cracking process in a tube reactor. The effects of the mixing ratio, coil outlet temperature, and pressure on cracking performance have been discussed in detail. The co-cracking of ethane and propane mixture leads to a lower profitability than the cracking of single ethane or single propane. For naphtha, cracking with LPG leads to a higher profitability than single cracking of naphtha, and more LPG can produce a higher profitability.

A stochastic reconstruction strategy based on a stratified library of structural descriptors and its application in the molecular reconstruction of naphtha

Molecular reconstruction is a rapid and reliable way to provide molecular detail of petroleum fractions,which is required in the kinetic modeling of petroleum conversation processes at the molecular level.In the typical stochastic reconstruction method,the estimation of properties of pseudo molecules that are generated by Monte Carlo sampling depends on the building of predefined molecular libraries,which is expensive and inaccessible for certain petroleum fractions.In this paper,a novel stochastic reconstruction strategy is proposed,which is based on a stratified library of structural descriptors.Properties of pseudo molecules generated in the novel strategy can be directly estimated by group contribution method in the condition of lacking predefined molecular libraries.In this strategy,the molecular building diagram comprises two steps.First,the ring structure is configured by determining the number of rings.Different from the length of chain adopted in the traditional stochastic reconstruction method,in the second step,number of structural descriptors(SDs)for binding site and chain were determined sequentially for the configuration of binding site and saturated acyclic hydrocarbon chain.These structural descriptors for binding site and chain were selected from group contribution methods.To count the number of partial overlapping sections between structural descriptors for chain,two supplementary structural descriptors were created.All possible saturated structures of hydrocarbon chains can be represented by structural descriptors at the scale of property estimation.This strategy separates the building of a predefined molecule library from the stochastic reconstruction process.The exact structures of pseudo molecules represented by structural descriptors in this work can be determined with sufficient chemical knowledge.Fifty naphtha samples are tested independently to demonstrate the performance of the proposed strategy and the results show that the estimated properties were close enough to the experimental values.This strategy will benefit the molecular management of petrochemical industries and therefore improve economic and environmental efficiencies.

Neural network-based source tracking of chemical leaks with obstacles

The leakage of hazardous gases poses a significant threat to public security and causes environmental damage.The effective and accurate source term estimation(STE)is necessary when a leakage accident occurs.However,most research generally assumes that no obstacles exist near the leak source,which is inappropriate in practical applications.To solve this problem,we propose two different frameworks to emphasize STE with obstacles based on artificial neural network(ANN)and convolutional neural network(CNN).Firstly,we build a CFD model to simulate the gas diffusion in obstacle scenarios and construct a benchmark dataset.Secondly,we define the structure of ANN by searching,then predict the concentration distribution of gas using the searched model,and optimize source term parameters by particle swarm optimization(PSO)with well-performed cost functions.Thirdly,we propose a one-step STE method based on CNN,which establishes a link between the concentration distribution and the location of obstacles.Finally,we propose a novel data processing method to process sensor data,which maps the concentration information into feature channels.The comprehensive experiments illustrate the performance and efficiency of the proposed methods.

Optimization of sensor deployment sequences for hazardous gas leakage monitoring and source term estimation

Nowadays, chemical safety has attracted considerable attention, and chemical gas leakage monitoring and source term estimation(STE) have become hot spots. However, few studies have focused on sensor layouts in scenarios with multiple potential leakage sources and wind conditions, and studies on the risk information(RI) detection and prioritization order of sensors have not been performed. In this work, the monitoring area of a chemical factory is divided into multiple rectangles with a uniform mesh. The RI value of each grid node is calculated on the basis of the occurrence probability and normalized concentrations of each leakage scenario. A high RI value indicates that a sensor at a grid node has a high chance of detecting gas concentrations in different leakage scenarios. This situation is beneficial for leakage monitoring and STE. The methods of similarity redundancy detection and the maximization of sensor RI detection are applied to determine the sequence of sensor locations. This study reveals that the RI detection of the optimal sensor layout with eight sensors exceeds that of the typical layout with 12 sensors. In addition, STE with the optimized placement sequence of the sensor layout is numerically simulated. The statistical results of each scenario with various numbers of sensors reveal that STE is affected by sensor number and scenarios(leakage locations and winds). In most scenarios, appropriate STE results can be retained under the optimal sensor layout even with four sensors. Eight or more sensors are advised to improve the performance of STE in all scenarios. Moreover, the reliability of the STE results in each scenario can be known in advance with a specific number of sensors. Such information thus provides a reference for emergency rescue.

A microporous surface containing Si3N4/Ta microparticles of PEKK exhibits both antibacterial and osteogenic activity for inducing cellular response and improving osseointegration

As an implantable biomaterial,polyetherketoneketone(PEKK)exhibits good mechanical strength but it is biologically inert while tantalum(Ta)possesses outstanding osteogenic bioactivity but has a high density and elastic modulus.Also,silicon nitride(SN)has osteogenic and antibacterial activity.In this study,a microporous surface containing both SN and Ta microparticles on PEKK(STP)exhibiting excellent osteogenic and antibacterial activity was created by sulfonation.Compared with sulfonated PEKK(SPK)without microparticles,the surface properties(roughness,surface energy,hydrophilicity and protein adsorption)of STP significantly increased due to the SN and Ta particles presence on the microporous surface.In addition,STP also exhibited outstanding antibacterial activity,which inhibited bacterial growth in vitro and prevented bacterial infection in vivo because of the presence of SN particles.Moreover,the microporous surface of STP containing both SN and Ta particles remarkably induced response(e.g.,proliferation and differentiation)of rat bone mesenchymal stem(rBMS)cells in vitro.Furthermore,STP significantly improved new bone regeneration and osseointegration in vivo.Regarding the induction of cellular response in vitro and improvement of osseointegration in vivo,the microporous surface containing Ta was better than the surface with SN particles.In conclusion,STP with optimized surface properties activated cellular responses in vitro,enhanced osseointegration and prevented infection in vivo.Therefore,STP possessed the dual biofunctions of excellent osteogenic and antibacterial activity,showing great potential as a bone substitute.

Development and challenges of planning and scheduling for petroleum and petrochemical production

Production planning and scheduling are becoming the core of production management,which support the decision of a petrochemical company.The optimization of production planning and scheduling is attempted by every refinery because it gains additional profit and stabilizes the daily production.The optimization problem considered in industry and academic research is of different levels of realism and complexity,thus increasing the gap.Operation research with mathematical programming is a conventional approach used to address the planning and scheduling problem.Additionally,modeling the processes,objectives,and constraints and developing the optimization algorithms are significant for industry and research.This paper introduces the perspective of production planning and scheduling from the development viewpoint.

Optimization of LiB electrode with bi-diameter active particles using a microstructure-resolved model

The microstructure of electrodes significantly affects the performance of lithium-ion batteries(LiBs),and using bi-diameter active particles is a simple but effective way to regulate the microstructure of commercial LiB electrodes.Herein,to optimize the LiB cathode of bi-diameter active particles,a microstructure-resolved model is developed and validated.The results indicate that randomly packing of bi-diameter active particles is optimal when the electrolyte diffusion limitation is mild,as it provides the highest volume fraction of active materials.Under strong electrolyte diffusion limitations,layered packing with small particles near the separator is preferred.This is because particles near the current collector have a low lithiation state.Besides,optimizing the random packing can further improve the energy density.For energy-oriented LiBs,a low volume fraction of small particles(0.2)is preferred due to the higher volume fraction of active materials.For power-oriented LiBs,a high volume fraction of small particles(0.8)is better because it reduces diffusion limitations.This work should serve to guide the optimal design of electrode microstructure for achieving high-performance LiBs.

基于深度学习的区域背光亮度提取方法

在分析现有算法的优缺点的基础上,尽可能考虑各种类型的图像,基于发光二极管-液晶显示器直下式图像视频显示原理样机,提出了一种可靠有效的基于区域背光亮度提取的数据测量方法,并提出了一种高效实用的基于深度学习的背光亮度提取方法。该方法基于采用多层下采样结构的神经网络,综合提取图像特征,获得最优的背光。实验结果表明,该方法可以提高图像显示质量和扩大图像的动态范围,而网络结构中有无旁路的对比实验结果验证了所提方法的优越性和有效性。

Modeling of oil near-infrared spectroscopy based on similarity and transfer learning algorithm

Near-infrared spectroscopy mainly reflects the frequency-doubled and total-frequency absorption information of hydrogen-containing groups (0 -H, C-H, N-H, S-H) in organic molecules for near-infrared lights with different wavelengths, so it is applicable to testing of most raw materials and products in the field of petrochemicals. However, the modeling process needs to collect a large number of laboratory analysis data. There are many oil sources in China, and oil properties change frequently. Modeling of each raw material is not only unfeasible but also will affect its engineering application efficiency. In order to achieve rapid modeling of near-infrared spectroscopy and based on historical data of different crude oils under different detection conditions, this paper discusses about the feasibility of the application of transfer learning algorithm and makes it possible that transfer learning can assist in rapid modeling using certain historical data under similar distributions under a small quantity of new data. In consideration of the requirement of transfer learning for certain similarity of different datasets, a transfer learning method based on local similarity feature selection is proposed. The simulation verification of spectral data of 13 crude oils measured by three different probe detection methods is performed. The effectiveness and application scope of the transfer modeling method under different similarity conditions are analyzed.

Performance monitoring of non-gaussian chemical processes with modes-switching using globality-locality preserving projection

In this paper, we propose a novel performance monitoring and fault detection method, which is based on modified structure analysis and globality and locality preserving （MSAGL） projection, for non-Gaussian processes with multiple operation conditions. By using locality preserving projection to analyze the embedding geometrical manifold and extracting the non-Gaussian features by independent component analysis, MSAGL preserves both the global and local structures of the data simultaneously. Furthermore, the tradeoff parameter of MSAGL is tuned adaptively in order to find the projection direction optimal for revealing the hidden structural information. The validity and effectiveness of this approach are illustrated by applying the proposed technique to the Tennessee Eastman process simulation under multiple operation conditions. The results demonstrate the advantages of the proposed method over conventional eigendecomposition-based monitoring methotis.

DE based economic control chart design and application for a typical petrochemical process

Petrochemical industry plays an important role in the development of the national economy. Purified terephthalic acid(PTA) is one of the most important intermediate raw materials in the petrochemical and chemical fiber industries. PTA production has two parts:p-xylene(PX) oxidation process and crude terephthalic acid(CTA) hydropurification process. The CTA hydropurification process is used to reduce impurities, such as 4-carboxybenzaldehyde, which is produced by a side reaction in the PX oxidation process and is harmful to the polyester industry. From the safety and economic viewpoints, monitoring this process is necessary. Four main faults of this process are analyzed in this study. The common process monitoring methods always use T^2 and SPE statistic as control limits. However, the traditional methods do not fully consider the economic viewpoint. In this study, a new economic control chart design method based on the differential evolution(DE) algorithm is developed. The DE algorithm transforms the economic control chart design problem to an optimization problem and is an excellent solution to such problem. Case studies of the main faults of the hydropurification process indicate that the proposed method can achieve minimum profit loss.This method is useful in economic control chart design and can provide guidance for the petrochemical industry.