Reliability-Based Multi-Objective Optimization Applied to Chemical Engineering Design

Abstract

Chemical engineering optimization represents a significant challenge due to the complexity of the mathematical models that are frequently required in this area. These models are normally associated with nonlinear equations that represent mass, energy, and momentum balances, which are submitted to physical, constitutive, environmental, and design limitations. The design of chemical systems is generally carried out by considering the model, the vector of design variables, and system parameters as deterministic values, i.e., small variations in these quantities do not affect the objective function. In this contribution, a new methodology based on a double loop iteration process to evaluate the influence of uncertainties on chemical engineering design is proposed. The inner optimization loop is used to find the solution associated with the highest probability value by using the so-called Inverse Reliability Analysis and the outer loop is the regular optimization loop used to determine the vector of design variables. For this aim, the Multi-Objective Optimization Water Cycle Algorithm is improved, adopting a mechanism of neighborhood exploration. For illustration purposes, the proposed methodology is applied to mathematical functions and to chemical engineering design. The obtained results demonstrate that the proposed strategy represents an interesting alternative to reliability design in chemical engineering.

A Novel Reliability-Based Robust Design Multiobjective Optimization Formulation Applied in Chemical Engineering

“…When the terms of the temperatures of the hot fluid entering the heat exchangers, t 11 , t 21 , and t 31 , are rewritten in terms of T 1 and T 2 , and the resultant expressions in the constraints defined by eq are replaced, the problem now has five decision variables, namely, the area of the heat exchangers, A 1 , A 2 , and A 3 , and temperatures T 1 and T 2 . Thus, the new constraints of the problem are as follows: For reliability-based optimization, Lobato et al suggest that model uncertainties are associated with the constant terms in the inequalities, so that they are treated as independent normal random variables X = ( X 1 , ..., X 8 ), with the mean equal to the constants in eqs 23 and the standard deviation as in Table . In this case, the equivalent inequalities of the deterministic problem, given by eqs 23, can be transformed into probabilistic constraints.…”

Grid Feature-Based Weighted Simulation Method for Multi-Objective Reliability-Based Design Optimization

“…Integrating MCS into MOPSO, Xie et al [31] proposed a MORBDO approach for the design optimization of a cooling system. Using multi-objective optimization water cycle algorithm (MOWCA) and PMA, Lobatoet al [32] presented the MORBDO of chemical engineering problems. Duan et al [33] developed a MORBDO framework for a new front longitudinal beam under front-impact collision.…”

Illustration Design Model with Clustering Optimization Genetic Algorithm

“…However, the k-means algorithm is easy to converge to the local optimal solution, and the clustering results are very dependent on the random initialization process of the algorithm; that is, multiple k-means clustering on the same data set may produce different clustering results [20,21]. Self-organizing mapping is a kind of neural network, which can map data in high-dimensional space to lowdimensional space, and it is also applied to clustering analysis of gene expression data [22]. SOM's shortcoming is that unbalanced clustering results are often produced, and it is difficult to find clear classification boundaries from the clustering results.…”