With more and more data being collected, data-driven modeling methods have been gaining in popularity in recent years. While physically sound, classical gray-box models are often cumbersome to identify and scale, and their accuracy might be hindered by their limited expressiveness. On the other hand, classical black-box methods, typically relying on Neural Networks (NNs) nowadays, often achieve impressive performance, even at scale, by deriving statistical patterns from data. However, they remain completely oblivious to the underlying physical laws, which may lead to potentially catastrophic failures if decisions for real-world physical systems are based on them. Physically Consistent Neural Networks (PCNNs) were recently developed to address these aforementioned issues, ensuring physical consistency while still leveraging NNs to attain state-of-the-art accuracy. In this work, we scale PCNNs to model building temperature dynamics and propose a thorough comparison with classical gray-box and black-box methods. More precisely, we design three distinct PCNN extensions, thereby exemplifying the modularity and flexibility of the architecture, and formally prove their physical consistency. In the presented case study, PCNNs are shown to achieve state-of-the-art accuracy, even outperforming classical NN-based models despite their constrained structure. Our investigations furthermore provide a clear illustration of NNs achieving seemingly good performance while remaining completely physics-agnostic, which can be misleading in practice. While this performance comes at the cost of computational complexity, PCNNs on the other hand show accuracy improvements of 17-35% compared to all other physically consistent methods, paving the way for scalable physically consistent models with state-of-the-art performance.

Reinforcement Learning (RL) generally suffers from poor sample complexity, mostly due to the need to exhaustively explore the state space to find good policies. On the other hand, we postulate that expert knowledge of the system to control often allows us to design simple rules we expect good policies to follow at all times. In this work, we hence propose a simple yet effective modification of continuous actor-critic RL frameworks to incorporate such prior knowledge in the learned policies and constrain them to regions of the state space that are deemed interesting, thereby significantly accelerating their convergence. Concretely, we saturate the actions chosen by the agent if they do not comply with our intuition and, critically, modify the gradient update step of the policy to ensure the learning process does not suffer from the saturation step. On a room temperature control simulation case study, these modifications allow agents to converge to well-performing policies up to one order of magnitude faster than classical RL agents while retaining good final performance.

In this paper, the CONFIG algorithm, a simple and provably efficient constrained global optimization algorithm, is applied to optimize the closed-loop control performance of an unknown system with unmodeled constraints. Existing Gaussian process based closed-loop optimization methods, either can only guarantee local convergence (e.g., SafeOPT), or have no known optimality guarantee (e.g., constrained expected improvement) at all, whereas the recently introduced CONFIG algorithm has been proven to enjoy a theoretical global optimality guarantee. In this study, we demonstrate the effectiveness of CONFIG algorithm in the applications. The algorithm is first applied to an artificial numerical benchmark problem to corroborate its effectiveness. It is then applied to a classical constrained steady-state optimization problem of a continuous stirred-tank reactor. Simulation results show that our CONFIG algorithm can achieve performance competitive with the popular CEI (Constrained Expected Improvement) algorithm, which has no known optimality guarantee. As such, the CONFIG algorithm offers a new tool, with both a provable global optimality guarantee and competitive empirical performance, to optimize the closed-loop control performance for a system with soft unmodeled constraints. Last, but not least, the open-source code is available as a python package to facilitate future applications.

Despite the immense success of neural networks in modeling system dynamics from data, they often remain physics-agnostic black boxes. In the particular case of physical systems, they might consequently make physically inconsistent predictions, which makes them unreliable in practice. In this paper, we leverage the framework of Irreversible port-Hamiltonian Systems (IPHS), which can describe most multi-physics systems, and rely on Neural Ordinary Differential Equations (NODEs) to learn their parameters from data. Since IPHS models are consistent with the first and second principles of thermodynamics by design, so are the proposed Physically Consistent NODEs (PC-NODEs). Furthermore, the NODE training procedure allows us to seamlessly incorporate prior knowledge of the system properties in the learned dynamics. We demonstrate the effectiveness of the proposed method by learning the thermodynamics of a building from the real-world measurements and the dynamics of a simulated gas-piston system. Thanks to the modularity and flexibility of the IPHS framework, PC-NODEs can be extended to learn physically consistent models of multi-physics distributed systems.

由于其高能量强度，建筑物在当前全球能源转型中发挥着重要作用。建筑模型是普遍无处不在的，因为在建筑物的每个阶段都需要它们，即设计，改装和控制操作。基于物理方程式的古典白盒式模型必然遵循物理规律，但其底层结构的具体设计可能会阻碍他们的表现力，从而阻碍他们的准确性。另一方面，黑匣子型号更适合捕获非线性建筑动态，因此通常可以实现更好的准确性，但它们需要大量的数据，并且可能不会遵循物理规律，这是神经网络特别常见的问题（NN）模型。为了抵消这种已知的概括问题，最近介绍了物理知识的NNS，研究人员在NNS的结构中介绍了以底层底层物理法律接地，并避免经典的NN概括问题。在这项工作中，我们介绍了一种新的物理信息的NN架构，被称为身体一致的NN（PCNN），其仅需要过去的运行数据并且没有工程开销，包括在并联运行到经典NN的线性模块中的先前知识。我们正式证明，这些网络是物理上一致的 - 通过设计甚至在看不见的数据 - 关于不同的控制输入和邻近区域的温度。我们在案例研究中展示了他们的表现，其中PCNN比3美元的古典物理型电阻电容模型更好地获得高达50美元的准确性。此外，尽管结构受到约束的结构，但PCNNS在验证数据上对古典NNS对古典NNS进行了类似的性能，使训练数据较少，并保留高表达性以解决泛化问题。