A novel distributionally robust chance‐constrained optimization (DRCCP) method is proposed in this work based on the Sinkhorn ambiguity set. The Sinkhorn ambiguity set is constructed based on the ...Sinkhorn distance, which is a variant of the Wasserstein distance with the entropic regularization. The proposed method can hedge against more general families of uncertainty distributions than the Wasserstein ambiguity set‐based methods. The presented approach is formulated as a tractable conic model based on the Conditional value‐at‐risk (CVaR) approximation and the discretized kernel distribution relaxation. This model is compatible with more general constraints that are subject to uncertainty than the Wasserstein‐based methods. Accordingly, the presented Sinkhorn DRCCP is a more practical approach that overcomes the limitations of the traditional Wasserstein DRCCP approaches. A numerical example and a nonlinear chemical process optimization case are studied to demonstrate the efficacy of the Sinkhorn DRCCP and its advantages over the Wasserstein DRCCP.
Two data-driven approaches based on the Fourier-transform infrared spectroscopy (FTIR) data are presented in this work to predict crude oil properties. The first approach is the combination of the ...principal component analysis (PCA) and the support vector regression (SVR), namely PCA-SVR. In the PCA-SVR, the PCA is employed to extract the high-dimension FTIR data to obtain lower-dimensional data. The lower-dimensional data is utilized as the inputs of the SVR to predict crude oil properties. The second approach is a hybrid model composed of the autoencoder and the SVR, namely Auto-SVR. In the Auto-SVR, the autoencoder is exploited to learn new representations for the dimensionality reduction of the FTIR data. The learned lower-dimensional representations are input into the SVR to predict crude oil properties. The presented data-driven approaches are used to predict fractions of light virgin naphtha (LVN), heavy virgin naphtha (HVN), kerosene (Kero), distillate, vacuum gas oil (VGO), and residual in crude oil. According to the obtained results, the presented methods can achieve accurate predictions with satisfactory prediction accuracy.
Objectives
This study aims to reveal immunophenotypes associated with immunotherapy response in bladder cancer, identify the signature genes of immune subtypes, and provide new molecular targets for ...improving immunotherapy response.
Methods
Bladder cancer immunophenotypes were characterized in the bulk RNA sequencing dataset GSE32894 and Imvigor210, and gene expression signatures were established to identify the immunophenotypes. Expression of gene signatures were validated in single‐cell RNA sequencing dataset GSE145140 and human proteins expression data source. Investigation of Immunotherapy Response was performed in IMvigor210 dataset. Prognosis of tumor immunophenotypes was further analyzed.
Results
Inflamed and immune‐excluded immunophenotypes were characterized based on the tumor immune cell scores. Risk score models that were established rely on RNA sequencing profiles and overall survival of bladder cancer cohorts. The inflamed tumors had lower risk scores, and the low‐risk tumors were more likely to respond to atezolizumab, receiving complete response/partial response (CR/PR). Patients who responded to atezolizumab had higher SRRM4 and lower NPHS1 and TMEM72 expression than the non‐responders. SRRM4 expression was a protective factor for bladder cancer prognosis, while the NPHS1 and TMEM72 showed the opposite pattern.
Conclusion
This study provided a novel classification method for tumor immunophenotypes. Bladder cancer immunophenotypes can predict the response to immune checkpoint blockade. The immunophenotypes can be identified by the expression of signature genes.
Conventional chance-constrained programming methods suffer from the inexactness of the estimated probability distribution of the underlying uncertainty from data. To this end, a distributionally ...robust approach to the problem allows for a level of ambiguity considered around a reference distribution. In this work, we propose a novel formulation for the distributionally robust chance-constrained programming problem using an ambiguity set constructed from a variant of optimal transport distance that was developed for Gaussian Mixture Models. We show that for multimodal process uncertainty, our proposed method provides an effective way to incorporate statistical moment information into the ambiguity set construction step, thus leading to improved optimal solutions. We illustrate the performance of our method on a numerical example as well as a chemical process case study. We show that our proposed methodology leverages the multimodal characteristics from the uncertainty data to give superior performance over the traditional Wasserstein distance-based method.
•Ambiguity set constructed from optimal transport between Gaussian Mixture Models.•Hedging against the right family of candidate distributions to avoid unnecessary conservatism.•A tractable distributionally robust chance constrained optimization formulation.•Applicability to more generate type of uncertain constraints.•Better objective-constraint satisfaction trade-off performance than classical Wasserstein DRCCP model.
Data-driven distributionally robust chance-constrained optimization (DRCCP) is a powerful technique to handle optimization problems involving uncertainty in constraint functions. However, the ...outliers and extreme samples in the data set may deteriorate the decision quality of DRCCP. Although there are numerous outlier detection techniques, they are either unable to pinpoint the samples causing overly conservative solutions, or incompatible with DRCCP models. This work proposes a novel and widely compatible algorithm that generates a representative subset of the original data set and removes samples causing overly conservative solutions for the DRCCP problem. With the proposed approach, the DRCCP solution quality can be enhanced while simultaneously ensuring the solution feasibility. To illustrate its effectiveness, we examine two numerical examples and a nonlinear process optimization problem in our study.
•Novel algorithm for distributionally robust chance constrained problem (DRCCP).•Refine solution quality via representative subset and removal of detrimental data.•Performance is shown through Wasserstein ambiguity set based DRCCP model.•Algorithm is applicable for general data-driven DRCCP problems.
The artificial neural network (ANN) can be effectively used as a data-driven surrogate model in process optimization. However, there is a problem that the change of training set leads to prediction ...uncertainty. A novel framework is proposed in this paper to address this issue. In the proposed approach, an ensemble of ReLU ANNs is first trained with different training sets to simulate the prediction uncertainty caused by the training set variation. Then, a mixture density network (MDN) is used to approximate the ReLU ANN ensemble and it is further embedded into a mixed-integer linear optimization problem. The original optimization problem is reformulated into a chance-constrained form with the mean-variance-type objective function to address both constraint and objective uncertainties. The proposed approach is applied to a numerical example and two case studies to show its capability of solving complex process optimization problems under the neural network model prediction uncertainty.
The hydroprocessing technique is used to refine crude oil and produce lighter, valuable products. Developing models of these units is crucial for predicting the process dynamics and facilitating ...optimization and control. In this research, we develop attention-based encoder–decoder recurrent neural network (A-ED-RNN) models, employing various RNN cells such as bioinspired neural circuit policies (NCPs), gated recurrent unit (GRU), and long short-term memory (LSTM), to predict diesel and jet production rates within an industrial hydroprocessing unit. A key innovation is integrating the NCP into the A-ED-RNN models, harnessing its advanced computational power to attain enhanced performance with a smaller model size compared to that of GRU and LSTM cells. The developed RNN models effectively capture the dynamics of diesel and jet production, surpassing the traditional data-driven models. Notably, the NCP-based A-ED-RNN model demonstrates superior memory efficiency and predictive ability, standing out among all of the developed RNN models, underscoring its potential for modeling complex processes.
A recurrent neural network (RNN)-based approach is proposed in this paper to handle joint chance-constrained stochastic optimal control problems (SOCP) and stochastic model predictive control (SMPC) ...implementations. In the proposed approach, the joint chance constraint (JCC) in a SOCP is first reformulated as a quantile-based inequality. Then, the sample average approximation (SAA) method is used to build the RNN-based surrogate model for the quantile function. Afterwards, the RNN-based model is embedded into the probabilistic constraint of the SOCP. Subsequently, the SOCP involving the RNN-based model can be solved using a deterministic nonlinear optimization solver. Moreover, while applying the proposed approach to the SMPC, the SOCP involving the RNN-based model is solved repeatedly at different sampling instants, based on different initial system states. The proposed approach is applied to a numerical illustrating example and a chemical process case study to demonstrate its capability of handling the SOCP and the SMPC implementation.
•Quantile reformulation of joint chance constraints and sample based empirical approximation.•Approximation of quantile function through recurrent neural network based surrogate model.•Stochastic optimal control problem is deterministically solvable though embedded RNN model.•Easy extension and implementation of the proposed approach to stochastic model predictive control problem.
The heterogeneously catalytic esterification of glycolic acid (GA) and methanol (MeOH) is superior to other approaches for the mass production of methyl glycolate (MG) due to several advantages. ...However, there is no research on the chemical process for the industrial synthesis of MG via esterification so far. Therefore, the rigorous design and optimization of a reactive distillation-based process for the MG production via the esterification of GA and MeOH are first proposed and investigated in this work. The overall process consists of a reactive distillation column (RDC) to convert GA and MeOH into MG and a separation section to purify the crude MG into the final product. In the study, a realistic GA feed stream including significant amounts of other impurities such as water, diglycolic acid, and methoxyacetic acid is assumed. The systematic optimization of minimizing the total annual cost (TAC) through sequential iterations is performed to find the optimal sets of design variables for RDC and the downstream separation section. From the optimization of RDC, the authors found that the molar feed ratio of MeOH to GA is the most influential variable, and its optimal value is 1.88. For the separation section, from the comparison of the optimized direct sequence, indirect sequence, and prefractionator sequence (PFS) processes, the PFS arrangement is the most economical design configuration. Furthermore, the two-column PFS process is integrated into the middle dividing-wall column that significantly saves 23.21% operating cost and 15.94% TAC.