Abstract The continuous steel rolling reheating furnace, as a key thermal device in the rolling process, is a major energy-consuming component in steel production. The design of its heating system directly determines the heating quality of billets and overall energy efficiency. Traditional methods, which rely on experience-driven system design or empirical model-based fuel optimization strategies, often face the issue of excessive energy consumption. To address this challenge, this study proposes a quantitative correlation model based on the Principle of Terminal Concentrated Heating (PCHT), linking sectional fuel inputs to the temperature fields within the furnace, thereby providing a theoretical basis for optimizing fuel distribution. Additionally, a parallel optimization strategy is introduced, significantly enhancing computational efficiency through multi-objective collaborative optimization. The developed parallel heating system optimization model aims to minimize total fuel consumption while maximizing computational speed. Validation results demonstrate a high consistency between model predictions and experimental data trends, with an average error of less than 26 °C. The computational speed improves by 98% compared to traditional methods. In four practical industrial scenarios, the optimized systems strictly adhere to the Principle of Terminal Concentrated Heating, achieving a 22.54% reduction in specific energy consumption compared to conventional designs and actual operations. This model not only provides an efficient framework for furnace design but also significantly enhances the energy-saving potential of continuous steel rolling reheating furnaces, offering practical technological support for industry emission reduction goals.
This paper introduces SENSE (Shared Embedding for N-lingual Speech and tExt), an open-source solution inspired by the SAMU-XLSR framework and conceptually similar to Meta AI's SONAR models. These approaches rely on a teacher-student framework to align a self-supervised speech encoder with the language-agnostic continuous representations of a text encoder at the utterance level. We describe how the original SAMU-XLSR method has been updated by selecting a stronger teacher text model and a better initial speech encoder. The source code for training and using SENSE models has been integrated into the SpeechBrain toolkit, and the first SENSE model we trained has been publicly released. We report experimental results on multilingual and multimodal semantic tasks, where our SENSE model achieves highly competitive performance. Finally, this study offers new insights into how semantics are captured in such semantically aligned speech encoders.
In this paper, we introduce TEDxTN, the first publicly available Tunisian Arabic to English speech translation dataset. This work is in line with the ongoing effort to mitigate the data scarcity obstacle for a number of Arabic dialects. We collected, segmented, transcribed and translated 108 TEDx talks following our internally developed annotations guidelines. The collected talks represent 25 hours of speech with code-switching that cover speakers with various accents from over 11 different regions of Tunisia. We make the annotation guidelines and corpus publicly available. This will enable the extension of TEDxTN to new talks as they become available. We also report results for strong baseline systems of Speech Recognition and Speech Translation using multiple pre-trained and fine-tuned end-to-end models. This corpus is the first open source and publicly available speech translation corpus of Code-Switching Tunisian dialect. We believe that this is a valuable resource that can motivate and facilitate further research on the natural language processing of Tunisian Dialect.
In this article we introduce a context-free grammar (CFG) for the Nawatl language. Nawatl (or Nahuatl) is an Amerindian language of the $π$-language type, i.e. a language with few digital resources, in which the corpora available for machine learning are virtually non-existent. The objective here is to generate a significant number of grammatically correct artificial sentences, in order to increase the corpora available for language model training. We want to show that a grammar enables us significantly to expand a corpus in Nawatl which we call $π$-\textsc{yalli}. The corpus, thus enriched, enables us to train algorithms such as FastText and to evaluate them on sentence-level semantic tasks. Preliminary results show that by using the grammar, comparative improvements are achieved over some LLMs. However, it is observed that to achieve more significant improvement, grammars that model the Nawatl language even more effectively are required.
This note is concerned with the problem of minimizing a separable, convex, composite (smooth and nonsmooth) function subject to linear constraints. We study a randomized block-coordinate interpretation of the Chambolle-Pock primal-dual algorithm, based on inexact proximal gradient steps. A specificity of the considered algorithm is its robustness, as it converges even in the absence of strong duality or when the linear program is inconsistent. Using matrix preconditiong, we derive tight sublinear convergence rates with and without duality assumptions and for both the convex and the strongly convex settings. Our developments are extensions and particularizations of original algorithms proposed by Malitsky (2019) and Luke and Malitsky (2018). Numerical experiments are provided for an optimal transport problem of service pricing.
