A model to determine the optimal critical level and the monitoring intervals in condition-based maintenance

In condition-based maintenance, a common practice is to record a condition reading at a regular interval, and once the reading is higher than a pre-set critical level, the item monitored is declared faulty and repair or replacement may be initiated. However, surprisingly both in practice and theory, little attention has been paid to whether or not the critical level and the monitoring interval are set in a cost effective way. This paper reports on the development of a model that can be used to determine the optimal critical level and interval in condition-based maintenance in terms of a criterion of interest. The model is established on the basis of the random coefficient growth model where the coefficients of the regression growth model are assumed to follow known distribution functions. A simple example is given in the paper to illustrate the modelling ideas.     

Kriging metamodel management in the design optimization of a CNG injection system

This paper deals with the use of Kriging metamodels in multi-objective engineering design optimization. The metamodel management issue to find the tradeoff between accuracy and efficiency is addressed. A comparative analysis of different strategies is conducted for a case study devoted to the design of a component of the injection system for Compressed Natural Gas (CNG) engines. The computational results are reported and analyzed for a performance assessment conducted with a data envelopment analysis approach.     

Self-organizing maps for pattern recognition in design of alloys

A combined experimental–computational methodology for accelerated design of AlNiCo-type permanent magnetic alloys is presented with the objective of simultaneously extremizing several magnetic properties. Chemical concentrations of eight alloying elements were initially generated using a quasi-random number generator so as to achieve a uniform distribution in the design variable space. It was followed by manufacture and experimental evaluation of these alloys using an identical thermo-magnetic protocol. These experimental data were used to develop meta-models capable of directly relating the chemical composition with desired macroscopic properties of the alloys. These properties were simultaneously optimized to predict chemical compositions that result in improvement of properties. These data were further utilized to discover various correlations within the experimental dataset by using several concepts of artificial intelligence. In this work, an unsupervised neural network known as self-organizing maps was used to discover various patterns reported in the literature. These maps were also used to screen the composition of the next set of alloys to be manufactured and tested in the next iterative cycle. Several of these Pareto-optimized predictions out-performed the initial batch of alloys. This approach helps significantly reducing the time and the number of alloys needed in the alloy development process.     

行星齿轮减速器稳健优化设计

在优化设计中主要存在设计变量的初值选取,设计变量的随机波动和外来干扰造成的可靠性和稳健性问题。为了解决此问题提出了6σ稳健设计和序列二次规划法相结合的方法,并以行星齿轮减速器为例进行了优化研究,通过与确定性优化的对比,验证了所提出的优化方法具有良好的优化效果。     

探索性分析方法及其关键技术

探索性分析方法是Rand公司在战略分析中总结得出的一种系统分析方法，它以层次化分析建模、模型抽象与聚合、主动元模型、仿真结果数据可视化等关键技术为支撑。探索性分析方法从系统所包含的不确定性因素出发，通过模型抽象和聚合建立系统层次化变分辨率低分辨率动态模型，调整不同的不确定性因素，通过对结果数据进行可视化交互式分析来观察和比较系统的行为变化，从而全面认识不确定性因素对结果的影响。探索性分析方法在深入研究特定的系统内部细节之前，通过对想定空间的快速大范围探索，能给出对问题的鲁棒、自适应和灵活的解，从而获得对系统的全面认识。     

Robust ensemble of metamodels based on the hybrid error measure

Frontiers of Mechanical Engineering - Metamodels have been widely used as an alternative for expensive physical experiments or complex, time-consuming computational simulations to provide a fast...     

Adaptive accuracy trust region: using cross-validation in the optimization process

This article presents an adaptive accuracy trust region (AATR) optimization strategy where cross-validation is used by the trust region to reduce the number of sample points needed to construct metamodels for each step of the optimization process. Lower accuracy metamodels are initially used for the larger trust regions, and higher accuracy metamodels are used for the smaller trust regions towards the end of optimization. Various metamodelling strategies are used in the AATR algorithm: optimal and inherited Latin hypercube sampling to generate experimental designs; quasi-Newton, kriging and polynomial regression metamodels to approximate the objective function; and the leave-k-out method for validation. The algorithm is tested with two-dimensional single-discipline problems. Results show that the AATR algorithm is a promising method when compared to a traditional trust region method. Polynomial regression in conjunction with a new hybrid inherited-optimal Latin hypercube sampling performed the best.     

Monotonic Metamodels for Deterministic Computer Experiments

In deterministic computer experiments, it is often known that the output is a monotonic function of some of the inputs. In these cases, a monotonic metamodel will tend to give more accurate and interpretable predictions with less prediction uncertainty than a nonmonotonic metamodel. The widely used Gaussian process (GP) models are not monotonic. A recent article in Biometrika offers a modification that projects GP sample paths onto the cone of monotonic functions. However, their approach does not account for the fact that the GP model is more informative about the true function at locations near design points than at locations far away. Moreover, a grid-based method is used, which is memory intensive and gives predictions only at grid points. This article proposes the weighted projection approach that more effectively uses information in the GP model together with two computational implementations. The first is isotonic regression on a grid while the second is projection onto a cone of monotone splines, which alleviates problems faced by a grid-based approach. Simulations show that the monotone B-spline metamodel gives particularly good results. Supplementary materials for this article are available online.     

Effects of flexibility and scheduling decisions on the performance of an FMS: simulation modelling and analysis

This paper focuses on a simulation-based experimental study of the effects of routing flexibility, sequencing flexibility, and part sequencing rules on the performance of a typical FMS. Three routing flexibility levels, five sequencing flexibility levels, and four scheduling rules for part sequencing decision are considered for detailed investigation. The system work load characterised by the mean interarrival time of parts has been set at different levels. The performance of the FMS is evaluated using various measures related to flow time and tardiness of parts. The simulation results are subjected to statistical analysis. Multiple regression-based metamodels have been developed using the simulation results. The analyses of results reveal that deterioration in system performance can be minimised substantially by incorporating either routing flexibility or sequencing flexibility or both. However, the benefits of either of these flexibilities diminish at higher flexibility levels. When flexibility exists, part sequencing rules such as the earliest due date and earliest operation due date provide a better performance for all the measures.     

MCS-based response surface metamodels and optimal design of experiments for gravity dams

Deterministic seismic analysis of dam-foundation-water does not usually reflect the true behavior of the system due to presence of different epistemic uncertainties. On the other hand, the crude Monte Carlo simulation (CMCS) of such a system is computationally expensive and often practically impossible. This paper investigates the potential application of so-called design of experiments (DOE) in order to develop appropriate metamodels and present an explicit expression of dam response. More than ten DOE techniques are compared and contrasted. Accuracy of metamodels is evaluated using about 120,000 finite element simulations from CMCS. Furthermore, the application of several sampling reduction techniques (i.e. Latin Hypercube, Sobol, and Halton) is evaluated. Next, the impact of polynomial degree is studied for an actual gravity dam with five random variables. Results are generalised for 12 different dam classes where the displacements, stresses and failure modes are quantified. Last but not least, a metamodel is proposed for seismic uncertainty of gravity dam in which the dam response is estimated using different features of the input ground motions.