Robust Design of Coupled Engineered Systems

Coupled Engineered Systems can be characterized by the inherent interactions among design decisions. These interactions define the influence that one design decision exerts over another and require appropriate method to model such interactions. Robust design enables designers to design a product or process that is relatively insensitive to uncertainties. Hence, robust design of coupled engineered systems enables designers to, (i) design engineered systems while accounting for interaction among design decisions and (ii) identifying design decisions that are relatively insensitive to uncertainties. In this paper, an appropriate method to model interactions and identify robust solution is presented. The interacting decisions are categorized into concurrent and hierarchical decisions and are respectively modeled with horizontal and vertical coupling. Based on the strength of interaction between these decisions, two types of interactions are defined, weak and strong interactions. To enable robust decisions in a coupled engineered systems, robustness metrics are defined and included as goals/constraints. The metrics considered in this work are to explore the solution space and manage uncertainty by considering the design of robust systems. The method has been tested on three design examples, that are, (i) design of a fender, (ii) design of a gearbox and (iii) design of a composite structure.

A Robust Data-Driven Approach for the Newsvendor Problem with Nonparametric Information

Problem definition: For the standard newsvendor problem with an unknown demand distribution, we develop an approach that uses data input to construct a distribution ambiguity set with the nonparametric characteristics of the true distribution, and we use it to make robust decisions. Academic/practical relevance: Empirical approach relies on historical data to estimate the true distribution. Although the estimated distribution converges to the true distribution, its performance with limited data is not guaranteed. Our approach generates robust decisions from a distribution ambiguity set that is constructed by data-driven estimators for nonparametric characteristics and includes the true distribution with the desired probability. It fits situations where data size is small. Methodology: We apply a robust optimization approach with nonparametric information. Results: Under a fixed method to partition the support of the demand, we construct a distribution ambiguity set, build a protection curve as a proxy for the worst-case distribution in the set, and use it to obtain a robust stocking quantity in closed form. Implementation-wise, we develop an adaptive method to continuously feed data to update partitions with a prespecified confidence level in their unbiasedness and adjust the protection curve to obtain robust decisions. We theoretically and experimentally compare the proposed approach with existing approaches. Managerial implications: Our nonparametric approach under adaptive partitioning guarantees that the realized average profit exceeds the worst-case expected profit with a high probability. Using real data sets from Kaggle.com, it can outperform existing approaches in yielding profit rate and stabilizing the generated profits, and the advantages are more prominent as the service ratio decreases. Nonparametric information is more valuable than parametric information in profit generation provided that the service requirement is not too high. Moreover, our proposed approach provides a means of combining nonparametric and parametric information in a robust optimization framework.

Calculating and communicating ensemble-based volcanic ash concentration risk for aviation

<p>During volcanic eruptions Volcanic Ash Advisory Centers (VAAC) produce forecasts of ash location and concentration. However, these forecasts are deterministic and do not take into account the inherent uncertainty in the forecasts due to incomplete knowledge of the volcano’s eruption characteristics and imperfect representation of atmospheric processes in numerical models. This means flight operators have incomplete information regarding the risk of flying following an eruption, which could result in overly conservative decisions being made. There is a need for a new generation of volcanic ash hazard charts allowing end users to make fast and robust decisions using risk estimates based on  state-of-the-art probabilistic forecast methods .</p><p> </p><p>In this presentation, a method for visualizing ash concentration matrix using a risk-matrix approach will be applied to two volcanic eruptions, Grimsvotn (2011) and Raikoke (2019). These risk-matrix graphics reduce the ensemble information into an easy-to-use decision-making tool. In this work the risk level is determined by combining the concentration of volcanic ash and the likelihood of that concentration occurring.</p><p> </p><p>When applying this technique to the Grimsvotn eruption, the airspace containing volcanic ash concentrations deemed to be associated with the highest risk (high likelihood of exceeding a high concentration threshold) to aviation are reduced by over 85% compared to using an ensemble that gives an ash distribution similar to the VAAC issued deterministic forecast. The reduction during the Raikoke eruption can be as much as 40% at a forecast lead time of 48 hours. This has the potential to reduce the disruption to airline operations.  This tool could be extended to include other aviation hazards, such as desert dust, aircraft icing and clear air turbulence.</p><p> </p>

A method for robust design in a coupled decision environment

The design of a connected engineered system requires numerous design decisions that influence one another. In a connected system that comprises numerous interacting decisions involving concurrency and hierarchy, accounting for interactions while also managing uncertainties, it is imperative to make robust decisions. In this article, we present a method for robust design using coupled decisions to identify design decisions that are relatively insensitive to uncertainties. To account for the influence among decisions, design decisions are modelled as coupled decisions. They are defined using three criteria: the types of decisions, the strength of interactions and the decision levels. In order to make robust decisions, robust design methods are classified based on sources of uncertainty, namely, Type I (noise factors), Type II (design variables) and Type III (function relationship between design variables and responses). The design of a one-stage reduction gearbox is used as a demonstration example. To illustrate the proposed method for robust design using coupled decisions, we present the simultaneous selection of gear material and gearbox geometry in a coupled decision environment while managing the uncertainties involved in designing gearboxes.

Optimal generation dispatch with wind and solar curtailment

To solve the actual task of finding optimal generation mix and dispatch of thermal and nuclear power units, and hydro units of hydro pumped storages of Ukraine to cover day load power profile according to one of possible wind and solar generation curtailment mode the modification of mathematical MIP model is proposed. There are three modes of wind and solar generation curtailment revised in the article: 1) absolute maximum generation curtailment, 2) single for whole day decreased load factor, and 3) one per one hour decreased load factor. The possibility to allocate an exogenously determined level of frequency containment reserves (secondary reserves) on thermal power units is realized in the MIP model. The calculation’s results analysis shows that among revised wind and solar generation curtailment methods the method 2) is most appropriate in the short term because only administrative measures implementation is required, which could be put into force with appropriate legislation and does not require essential investments or implementation of complicated technical measures. The additional possible positive effect caused by the implementation of method 2) is it makes background for participation wind and solar generation in the ancillary services market and intraday balancing. In the middle term, the gradual implementation of method 3) is the most appropriate decision because a more stable power system balancing mode (minimum import/export amounts) could be provided. Moreover, extra nuclear power units and fewer coal thermal power units could be dispatched that is decreases hazard pollutions and carbon emission. The MIP model is written using MathProg language, a freeware version of AMPL. As a solver, the GNU GLPK program is used. The overall time for one calculation with standard table PC is about 30 seconds. MIP model could be used both for short-term power system optimal dispatch and for long-term national generation mix development studies under the growth rates of renewable installed capacities. Keywords: power system, daily load profile, robust decisions, mixed linear-integer problem, frequency containment reserve

Investigation of Combining Logitboost(M5P) under Active Learning Classification Tasks

Active learning is the category of partially supervised algorithms that is differentiated by its strategy to combine both the predictive ability of a base learner and the human knowledge so as to exploit adequately the existence of unlabeled data. Its ambition is to compose powerful learning algorithms which otherwise would be based only on insufficient labelled samples. Since the latter kind of information could raise important monetization costs and time obstacles, the human contribution should be seriously restricted compared with the former. For this reason, we investigate the use of the Logitboost wrapper classifier, a popular variant of ensemble algorithms which adopts the technique of boosting along with a regression base learner based on Model trees into 3 different active learning query strategies. We study its efficiency against 10 separate learners under a well-described active learning framework over 91 datasets which have been split to binary and multi-class problems. We also included one typical Logitboost variant with a separate internal regressor for discriminating the benefits of adopting a more accurate regression tree than one-node trees, while we examined the efficacy of one hyperparameter of the proposed algorithm. Since the application of the boosting technique may provide overall less biased predictions, we assume that the proposed algorithm, named as Logitboost(M5P), could provide both accurate and robust decisions under active learning scenarios that would be beneficial on real-life weakly supervised classification tasks. Its smoother weighting stage over the misclassified cases during training as well as the accurate behavior of M5P are the main factors that lead towards this performance. Proper statistical comparisons over the metric of classification accuracy verify our assumptions, while adoption of M5P instead of weak decision trees was proven to be more competitive for the majority of the examined problems. We present our results through appropriate summarization approaches and explanatory visualizations, commenting our results per case.

Implementing an integrated maintenance management system for monitoring production lines: a case study for biscuit industry

PurposeThis study provides a unique integrated diagnosis system to investigate the causes of low productivity, profitability, machinery health conditions and wear severity of medium-size biscuit industry assets in Taiz, Yemen.Design/methodology/approachThe evaluation is based on an integrating of the overall equipment effectiveness (OEE) and oil-based maintenance (OBM) approaches. The data are collected using the company's operational records, interviews and observations, while the used lubricating oil samples are also collected from production lines' machineries. Scanning electron microscope (SEM) is used to study the wear debris particle features and wear mechanism. Different other analysis tools such as fishbone, 5 whys and Pareto charts are also used to investigate the root causes and plausible recovery solutions of machinery failures.FindingsThis study demonstrated that a large proportion of machinery failures and production loss are of management concerns. Also, this study inferred that the analysis of wear debris is unique and informative for determining machinery wear severity and useful life. Finally, the current conditions of production lines are clarified and suggestions to use a mixed preventive/predictive maintenance management approach are also elucidated.Originality/valueThis work implemented an integrated OEE/OBM diagnostic maintenance system to investigate the root causes of low productivity and machine failures in real production lines and suggested robust decisions on the maintenance duties.