We present and analyze a three-stage stochastic optimization model that integrates output from a geoscience-based flood model with a power flow model for transmission grid resilience planning against flooding. The pro...
详细信息
A joint location-inventory-maintenance model is proposed for a geographically distributed Service Parts Logistics problem. The model uses a reliability-based replacement strategy and is formulated as a quadratic Mixed...
详细信息
Industrial prognostics focuses on utilizing degradation signals to forecast and continually update the residual useful life of complex engineering systems. However, existing prognostic models for systems with multiple...
详细信息
Industrial prognostics focuses on utilizing degradation signals to forecast and continually update the residual useful life of complex engineering systems. However, existing prognostic models for systems with multiple failure modes face several challenges in real-world applications, including overlapping degradation signals from multiple components, the presence of unlabeled historical data, and the similarity of signals across different failure modes. To tackle these issues, this research introduces two prognostic models that integrate the mixture (log)-location-scale distribution with deep learning. This integration facilitates the modeling of overlapping degradation signals, eliminates the need for explicit failure mode identification, and utilizes deep learning to capture complex nonlinear relationships between degradation signals and residual useful lifetimes. Numerical studies validate the superior performance of these proposed models compared to existing methods.
Evaluating individual treatment effects (ITE) is challenging due to the lack of access to counterfactual outcomes, particularly when working with biased data. Recent efforts have focused on leveraging the generative c...
ISBN:
(纸本)9798331534202
Evaluating individual treatment effects (ITE) is challenging due to the lack of access to counterfactual outcomes, particularly when working with biased data. Recent efforts have focused on leveraging the generative capabilities of models like Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) for ITE estimation. However, few approaches effectively address the need for uncertainty quantification in these estimates. In this work, we introduce GANCQR, a GAN-based conformal prediction method that generates prediction intervals for ITE with reliable coverage. Numerical experiments on synthetic and semi-synthetic datasets demonstrate GANCQR's superiority in handling selection bias compared to state-of-the-art methods.
This paper reports on the second component of a three phase study undertaken for the Canada Post Corporation (CPC) to evaluate and select a commercial simulation package to be used for operational and long-term planni...
详细信息
This paper reports on the second component of a three phase study undertaken for the Canada Post Corporation (CPC) to evaluate and select a commercial simulation package to be used for operational and long-term planning. The formal evaluation process consisted of a hierarchical screening procedure to identify qualified candidates and the development of a comprehensive benchmark model to test each candidate. Of the 172 simulation packages listed in the Directory of Simulation, only three satisfied each of the CPC's highest priority requirements. Data, mail flows, and processing logic associated with operations at the Hamilton, Ontario plant were used to establish the benchmarks and validate the models. This project represents the first time full-scale models have been constructed in parallel to evaluate graphics-based simulation software. Although several economies of scale were realized, the differences in the three packages meant significant duplication. Nevertheless, the CPC felt that the parallel approach would return benefits in the long run and that it was necessary to arrive at a considered decision. A major aim of this paper is to highlight the methodology used in the analysis and to present the lessons learned from the project. (C) 1997 Elsevier Science Ltd.
A Dijkstra-like algorithm for solving the point-to-point connection problem on a finite directed network is presented. For this problem we find a subset of arcs with minimal total length connecting a fixed number of s...
详细信息
A Dijkstra-like algorithm for solving the point-to-point connection problem on a finite directed network is presented. For this problem we find a subset of arcs with minimal total length connecting a fixed number of source-destination pairs. The problem has many variations for different applications. We focus on a case where two source-destination pairs are prematched and show that the time complexity of the algorithm is O(n4).
In this paper, we develop a multi-stage decision model to quantify the economic value of near-Earth asteroid (NEA) detection systems. Specifically, we develop a two-stage decision-analytic model focusing on whether or...
详细信息
ISBN:
(纸本)9780983762447
In this paper, we develop a multi-stage decision model to quantify the economic value of near-Earth asteroid (NEA) detection systems. Specifically, we develop a two-stage decision-analytic model focusing on whether or not to invest in a detection system and if a NEA is detected whether and how to respond. Our model incorporates uncertainties related to detection rate, asteroid size, and damage potential. Further we model downstream decisions and associated uncertainties related to mitigation measures including evacuation and deflection or destruction of the NEA. This modeling framework allows us to quantify the value of the detection system (i.e., the value of information). We specify this value at the global level and also on a country-by-country basis. This analysis provides insights and recommendations to policy makers as they consider how much to spend on NEA detection and mitigation measures.
SUMMARYSUMMARYConsider a printed circuit board with N signal paths in which k (not known a priori) paths are subjected to electrical shorts. A straight forward technique to detect all shorts is to test each pair of si...
SUMMARYSUMMARYConsider a printed circuit board with N signal paths in which k (not known a priori) paths are subjected to electrical shorts. A straight forward technique to detect all shorts is to test each pair of signal paths separately. This method needs (N2— N)/2 tests. In order to reduce the testing effort, manufacturers introduced a device that could test a group of signal paths against another group of signal paths. With the help of this device, a method with N + ((k2—k)/) tests needed was patented in 1982. In this paper, we present a new method that requires only O(k[log2N]) tests to achieve the same resolution using the same device.
We describe a stochastic network interdiction model for deploying radiation detectors at border checkpoints to detect smugglers of nuclear material. The model is stochastic because the smuggler's origin-destinatio...
详细信息
We describe a stochastic network interdiction model for deploying radiation detectors at border checkpoints to detect smugglers of nuclear material. The model is stochastic because the smuggler's origin-destination pair is known only through a probability distribution when the detectors are installed. We formulate a mixed-integer program for the special case in which we can only install detectors at border checkpoints of either the origin or the destination country. While the problem is strongly NP-hard, we describe a family of instances which may be solved in polynomial time, and show that the solutions to this family are nested.
Determining whether a solution is of high quality (optimal or near optimal) is a fundamental question in optimization theory and algorithms. We develop a Monte Carlo sampling-based procedure for assessing solution qua...
详细信息
暂无评论