Various works have been published around the optimization of Neural Networks that emphasize the significance of the learning rate. In this study we analyze the need for a different treatment for each layer and how this affects training. We propose a novel optimization technique, called AdaLip, that utilizes an estimation of the Lipschitz constant of the gradients in order to construct an adaptive learning rate per layer that can work on top of already existing optimizers, like SGD or Adam. A detailed experimental framework was used to prove the usefulness of the optimizer on three benchmark datasets. It showed that AdaLip improves the training performance and the convergence speed, but also made the training process more robust to the selection of the initial global learning rate.

The safe operation of nuclear power plants is highly dependent on the ability of quickly and accurately identifying possible anomalies and perturbations in the reactor. Operational defects are primarily diagnosed by detectors that capture changes in the neutron flux, placed at various points inside and outside of the core. Neutron flux signals are subsequently analyzed with signal processing techniques in an effort to be better described (have their higher-order characteristics uncovered, locate transient events, etc). To this end, the application of intelligent techniques may be extremely beneficial, as it may assist and extend the current level of analysis. Besides, the combination of signal processing methodologies and machine learning techniques in the framework of nuclear power plant data is an emerging topic that has yet to show its full potential. In this context, the current contribution attempts at introducing intelligent approaches and more specifically, deep learning techniques, in neutron flux signal analysis for the identification of perturbations and other anomalies in the reactor core that may affect its operational capabilities. The obtained results of an initial stage of analysis on neutron flux signals captured at pressurized water reactors are encouraging, underlying the robustness and the potential of the proposed approach.

This paper develops a two-stage method for the justification of investment in modern material handling systems. The underlying approach places heavy emphasis on the use of cost avoidance data quantified by activity-based costing systems. The first stage collects the life-cycle costs and benefits resulting from the reconfiguration of material handling systems in manufacturing facilities. A recently developed software package for process modelling and management is employed to capture the characteristics of material handling activities and to derive accurate applied cost rates for each activity and material handling system combination. These activity-related cost data as well as various opportunity costs are incorporated in a case-specific, investment decision model that constitutes the second stage of the method. The model performs an Economic Value Analysis for each material handling alternative. In doing so, it offers a sound basis for economic comparison of different systems. A case study illustrates the merit of our two-stage method in decision making by placing an accurate and reliable economic value on the transition from manual to automated material handling in a manufacturing facility. The use of activity-based costs reverses the decision of sustaining the 'status quo' supported by a traditional investment justification approach restricted to solely labour cost reductions

This paper considers the problem of minimizing the fixed cost of acquiring material handling transporter:; and the operational cost of material transfer in a manufacturing system. This decision problem, which arises during manufacturing facility design, is modeled using an integer programming formulation. Since the problem is NP-complete, two efficient heuristics are developed to solve it. Computational complexity, worst-case performance analysis, and extensive computational tests are provided for both heuristics. The results indicate that the proposed methods are well suited for large-scale manufacturing applications.

This work outlines an approach for localizing anomalies in nuclear reactor cores during their steady state operation, employing deep, one-dimensional, convolutional neural networks. Anomalies are characterized by the application of perturbation diagnostic techniques, based on the analysis of the so-called “neutron-noise” signals: that is, fluctuations of the neutron flux around the mean value observed in a steady-state power level. The proposed methodology is comprised of three steps: initially, certain reactor core perturbations scenarios are simulated in software, creating the respective perturbation datasets, which are specific to a given reactor geometry; then, the said datasets are used to train deep learning models that learn to identify and locate the given perturbations within the nuclear reactor core; lastly, the models are tested on actual plant measurements. The overall methodology is validated on hexagonal, pre-Konvoi, pressurized water, and VVER-1000 type nuclear reactors. The simulated data are generated by the FEMFFUSION code, which is extended in order to deal with the hexagonal geometry in the time and frequency domains. The examined perturbations are absorbers of variable strength, and the trained models are tested on actual plant data acquired by the in-core detectors of the Temelín VVER-1000 Power Plant in the Czech Republic. The whole approach is realized in the framework of Euratom’s CORTEX project.

Importance sampling, a variant of online sampling, is often used in neural network training to improve the learning process, and, in particular, the convergence speed of the model. We study, here, the performance of a set of batch selection algorithms, namely, online sampling algorithms that process small parts of the dataset at each iteration. Convergence is accelerated through the creation of a bias towards the learning of hard samples. We first consider the baseline algorithm and investigate its performance in terms of convergence speed and generalization efficiency. The latter, however, is limited in case of poor balancing of data sets. To alleviate this shortcoming, we propose two variations of the algorithm that achieve better generalization and also manage to not undermine the convergence speed boost offered by the original algorithm. Various data transformation techniques were tested in conjunction with the proposed scheme to develop an overall training method of the model and to ensure robustness in different training environments. An experimental framework was constructed using three naturally imbalanced datasets and one artificially imbalanced one. The results assess the advantage in convergence of the extended algorithm over the vanilla one, but, mostly, show better generalization performance in imbalanced data environments.