Search

This paper considers optimizing the performance of high-temperature combustion chamber of an aero-engine based on a concentric and hierarchical model. First, sample data for the design variables are obtained based on Latin hypercube sampling method, and a one-dimensional program is used to obtain the true values of combustion efficiency and total pressure loss corresponding to each group of variables. The obtained data are then pre-processed to establish a dataset. Second, a multi-layer artificial neural network (ANN) architecture is designed and a surrogate model of the combustion-related performance of the combustor is established using a data-driven method. The results of global sensitivity analysis based on variance show that ratio of fuel flow to air flow (fuel–air ratio) and the total inlet pressure are the most important factors influencing the two objective functions. Finally, we optimize the multi-objective combustion-related performance of the surrogate model by applying the particle swarm optimization algorithm to it. The results of experiments show that the ANN-based model could accurately predict the efficiency of combustion and total pressure loss of the chamber, yielding root mean-squared errors of 0.0107 and 0.3032%, respectively. It also had better generalization ability than the cubic polynomial surrogate model. Compared with the cubic polynomial model, it generated an optimal Pareto solution set as prediction that had higher values in both objective functions. The proposed model might require better data that can be obtained using intelligent sampling methods so that deeper neural networks can be designed to reduce error and improve its optimization design. [ABSTRACT FROM AUTHOR]

Sustainable supply chain management plays an important role in company's sustainability success. As the frequently emerging disruptions may harm supply chain's sustainable performance, managers need to design an effective sustainable supply chain (SSC) resilience solution to mitigate different risks. In addition, it is critical to integrate customer requirements (CRs) in SSC resilience solution design as SSC's performance is highly determined by customer satisfaction (CS) in the customer-oriented market. This article proposes an integrative approach to achieve an effective design of SSC resilience solution, taking both CRs and risk factors (RFs) into consideration. In this study, the Kano model, decision-making and trial evaluation laboratory (DEMATEL) are integrated with quality function deployment (QFD) through nonlinear programming to guide companies' design. Kano model is employed to analyse CRs qualitatively and quantitatively to determine each CR's priority and CS. DEMATEL is adopted to determine the RFs' interrelationships. The results obtained with the Kano model and DEMATEL are incorporated into QFD to transform CRs into RFs, and then into resilience measures. Furthermore, a nonlinear optimisation model is formulated to achieve the optimal resilience solution with maximised CS and risk mitigation under minimum cost investment. Finally, a case study is conducted to verify the methodology. [ABSTRACT FROM AUTHOR]

Promptly development of new products can be achieved through quality function deployment (QFD) process, which is critical to companies' survival. Since the multi-criteria decision-making problem involved in QFD, a novel method integrating cloud model and grey relational analysis is put forward in this paper. Taking into account the subjectivity and ambiguity in linguistic evaluations, some scholars utilise fuzzy theory, rough theory, interval-valued fuzzy-rough sets and MCDM methods to improve traditional QFD. However, much priori information requirements, inability to handle subjectivity and randomness, and lack of mechanism to overcome small sample size problem are some inevitable drawbacks in these methods. To solve these deficiencies, a hybrid methodology is proposed in this paper, integrating the fortes of cloud model in processing ambiguity and randomness, and the merits of grey relational analysis in overcoming small sample size error as well as revealing the inner correlations. The comparative analysis of different approaches as well as the sensitivity analysis of criteria weights is implemented to prove the stability of the novel method. The results obtained in this paper shows that the proposed method can be a practical tool for improving the efficiency and accuracy of traditional QFD in reality management. [ABSTRACT FROM AUTHOR]