Machine learning (ML) algorithms are remarkably good at approximating complex non-linear relationships. Most ML training processes, however, are designed to deliver ML tools with good average performance, but do not offer any guarantees about their worst-case estimation error. For safety-critical systems such as power systems, this places a major barrier for their adoption. So far, approaches could determine the worst-case violations of only trained ML algorithms. To the best of our knowledge, this is the first paper to introduce a neural network training procedure designed to achieve both a good average performance and minimum worst-case violations. Using the Optimal Power Flow (OPF) problem as a guiding application, our approach (i) introduces a framework that reduces the worst-case generation constraint violations during training, incorporating them as a differentiable optimization layer; and (ii) presents a neural network sequential learning architecture to significantly accelerate it. We demonstrate the proposed architecture on four different test systems ranging from 39 buses to 162 buses, for both AC-OPF and DC-OPF applications.
translated by 谷歌翻译
在排放限制下优化的气体网络规划优化优先考虑最少$ _2 $强度的天然气供应。由于此问题包括复杂的气流物理定律,因此标准优化求解器无法保证融合与可行解决方案。为了解决这个问题,我们开发了一个输入 - 控制神经网络(ICNN)辅助优化例程,该程序结合了一组训练有素的ICNN,以高精度近似于气流方程。比利时气体网络上的数值测试表明,ICNN辅助优化主导了非凸和基于弛豫的求解器,其最佳增长较大,与更严格的发射目标有关。此外,每当非凸线求解器失败时,ICNN ADED优化为网络计划提供了可行的解决方案。
translated by 谷歌翻译
能源部门的深度脱碳将需要大量的随机可再生能源渗透和大量的网格资产协调。对于面对这种变化而负责维持电网稳定性和安全性的电力系统运营商来说,这是一个具有挑战性的范式。凭借从复杂数据集中学习并提供有关快速时间尺度的预测解决方案的能力,机器学习(ML)得到了很好的选择,可以帮助克服这些挑战,因为在未来几十年中,电力系统转变。在这项工作中,我们概述了与构建可信赖的ML模型相关的五个关键挑战(数据集生成,数据预处理,模型培训,模型评估和模型嵌入),这些模型从基于物理的仿真数据中学习。然后,我们演示如何将单个模块连接在一起,每个模块都克服了各自的挑战,在机器学习管道中的顺序阶段,如何有助于提高训练过程的整体性能。特别是,我们实施了通过反馈连接学习管道的不同元素的方法,从而在模型培训,绩效评估和重新训练之间“关闭循环”。我们通过学习与拟议的北海风能中心系统的详细模型相关的N-1小信号稳定性边缘来证明该框架,其组成模块的有效性及其反馈连接。
translated by 谷歌翻译
我们探讨了使用物理知识的神经网络急剧加速管理动力系统动态的常用代数方程的解决方案。在暂时稳定性评估方面,传统应用的方法要么携带显着的计算负担,需要模型简化,或使用过于保守的代理模型。传统的神经网络可以规避这些限制,而是面临着高质量训练数据集的高需求,而他们忽略了潜在的控制方程。物理知识的神经网络是不同的:它们将电力系统差分代数方程直接纳入神经网络培训,并大大降低了对训练数据的需求。本文深入潜入物理知识神经网络的电力系统瞬态稳定性评估的性能。介绍一种新的神经网络培训程序,以促进彻底的比较,我们探讨了物理知识的神经网络如何与传统的差分代数求解器和经典神经网络在计算时间,数据要求和预测准确性方面比较。我们说明了昆医生的两国系统的调查结果,并评估了物理知识的神经网络的机会和挑战,用作瞬态稳定性分析工具,突出了进一步开发这种方法的可能途径。
translated by 谷歌翻译
深度学习的最新进展使神经网络(NNS)能够在许多应用中成功地取代传统的数控求解器,从而实现令人印象深刻的计算收益。一个这样的应用是时域模拟,这对于许多工程系统的设计,分析和操作是必不可少的。模拟基于牛顿的求解器的动态系统是一种计算繁忙的任务,因为它需要在每个时间步骤解决差分和代数方程的参数化系统的解决方案。已经显示了各种基于NN的方法,以成功地近似于数值溶剂计算的轨迹。但是,以前的一些工程已经使用NNS来模拟数值求解器本身。为了快速加速时域模拟速度的表达目的,本文提出并探索了两个互补的替代数字溶剂。首先,我们使用NN以模仿由逆雅加诺在单个牛顿步骤中提供的线性变换。使用此过程,我们评估并将基于物理的残余错误评估并将基于NN映射的确切,物理的残留错误项目进行评估并将其留下物理为“循环”中的“循环”。所得到的工具称为物理投影的神经 - 牛顿求解器(Prenn),能够在观察到的速度下实现极高的数值准确度,其比基于牛顿的求解器更快地高达31%。在第二种方法中,我们将牛顿求解器在隐式跳动-Kutta积分器的核心上模拟,作为一个契约地图,迭代地寻求时域轨迹的一个固定点。相关的复发性NN仿真工具被称为合同神经牛顿求解器(Conns),嵌入有训练约束(通过CVXPY层),该训练约束(通过CVXPY层),保证NN提供的映射满足BANACH定点定理。
translated by 谷歌翻译
本文介绍了一个框架,以捕获先前棘手的优化约束,并通过使用神经网络将其转换为混合构成线性程序。我们编码以可拖动和顽固的约束为特征的优化问题的可行空间,例如微分方程,转到神经网络。利用神经网络的精确混合重新印象,我们解决了混合企业线性程序,该程序将解决方案准确地近似于最初棘手的非线性优化问题。我们将方法应用于交流最佳功率流问题(AC-OPF),其中直接包含动态安全性约束可使AC-OPF棘手。我们提出的方法具有比传统方法更明显的可扩展性。我们展示了考虑N-1安全性和小信号稳定性的电力系统操作方法,展示了如何有效地获得成本优势的解决方案,同时满足静态和动态安全性约束。
translated by 谷歌翻译
Industry 4.0 aims to optimize the manufacturing environment by leveraging new technological advances, such as new sensing capabilities and artificial intelligence. The DRAEM technique has shown state-of-the-art performance for unsupervised classification. The ability to create anomaly maps highlighting areas where defects probably lie can be leveraged to provide cues to supervised classification models and enhance their performance. Our research shows that the best performance is achieved when training a defect detection model by providing an image and the corresponding anomaly map as input. Furthermore, such a setting provides consistent performance when framing the defect detection as a binary or multiclass classification problem and is not affected by class balancing policies. We performed the experiments on three datasets with real-world data provided by Philips Consumer Lifestyle BV.
translated by 谷歌翻译
Quality control is a crucial activity performed by manufacturing companies to ensure their products conform to the requirements and specifications. The introduction of artificial intelligence models enables to automate the visual quality inspection, speeding up the inspection process and ensuring all products are evaluated under the same criteria. In this research, we compare supervised and unsupervised defect detection techniques and explore data augmentation techniques to mitigate the data imbalance in the context of automated visual inspection. Furthermore, we use Generative Adversarial Networks for data augmentation to enhance the classifiers' discriminative performance. Our results show that state-of-the-art unsupervised defect detection does not match the performance of supervised models but can be used to reduce the labeling workload by more than 50%. Furthermore, the best classification performance was achieved considering GAN-based data generation with AUC ROC scores equal to or higher than 0,9898, even when increasing the dataset imbalance by leaving only 25\% of the images denoting defective products. We performed the research with real-world data provided by Philips Consumer Lifestyle BV.
translated by 谷歌翻译
Climate change is expected to aggravate wildfire activity through the exacerbation of fire weather. Improving our capabilities to anticipate wildfires on a global scale is of uttermost importance for mitigating their negative effects. In this work, we create a global fire dataset and demonstrate a prototype for predicting the presence of global burned areas on a sub-seasonal scale with the use of segmentation deep learning models. Particularly, we present an open-access global analysis-ready datacube, which contains a variety of variables related to the seasonal and sub-seasonal fire drivers (climate, vegetation, oceanic indices, human-related variables), as well as the historical burned areas and wildfire emissions for 2001-2021. We train a deep learning model, which treats global wildfire forecasting as an image segmentation task and skillfully predicts the presence of burned areas 8, 16, 32 and 64 days ahead of time. Our work motivates the use of deep learning for global burned area forecasting and paves the way towards improved anticipation of global wildfire patterns.
translated by 谷歌翻译
新兴的非挥发记忆设备的备忘录在神经形态硬件设计中显示出有希望的潜力,尤其是在尖峰神经网络(SNN)硬件实现方面。基于Memristor的SNN已成功应用于各种应用程序,包括图像分类和模式识别。但是,在文本分类中实施基于备忘录的SNN仍在探索中。主要原因之一是,培训基于备忘录的SNN用于文本分类是由于缺乏有效的学习规则和不理想性的不存在。为了解决这些问题,并加快了在文本分类应用程序中探索基于备忘录的尖峰神经网络的研究,我们使用经验的Memristor模型开发了使用虚拟备忘录阵列的仿真框架。我们使用此框架来演示IMDB电影评论数据集中的情感分析任务。我们采用两种方法,通过将预训练的人工神经网络(ANN)转换为基于Memristor的SNN或2),通过直接训练基于Memristor的SNN,以获取训练有素的尖峰神经网络:1)通过将预训练的人工神经网络(ANN)转换为基于Memristor的SNN。这两种方法可以在两种情况下应用:离线分类和在线培训。鉴于等效ANN的基线训练精度为86.02%,我们通过将预训练的ANN转换为基于Memristor的SNN的ANN通过将预培训的ANN转换为基于Memristor的SNN的85.88%的分类准确性为85.88%。我们得出的结论是,可以在从ANN到SNN以及从非同步突触到数据驱动的Memristive突触的模拟中实现类似的分类精度。我们还研究了诸如Spike火车长度,读取噪声和重量更新停止条件之类的全局参数如何影响两种方法的神经网络。
translated by 谷歌翻译