Leandro Von Krannichfeldt

Raffael Theiler, Lev Telyatnikov, Leandro Von Krannichfeldt et al.

Data-driven Prognostics and Health Management (PHM) uses time-varying condition-monitoring data to diagnose system states and estimate remaining useful life in engineered assets. These tasks are central to maintenance planning, but industrial PHM data are often fragmented, partially observed, and poorly labeled, which hinders supervised learning. Foundation models offer a route toward reusable predictive systems, yet most time-series foundation models are designed for forecasting and assume long, coherent, regularly sampled sequences. To address this gap, we propose a framework for applying Tabular Foundation Models to industrial time series using in-context learning, and we evaluate them on a variety of PHM tasks. By converting raw unit-level signals into tabular rows, we show that these models perform well across multiple tasks - including prognostics, and diagnostics - and are highly data efficient. We compare them directly with sequence models, transformer baselines, and gradient-boosted trees under a common evaluation protocol. The results indicate that tabular foundation models achieve the best average ranks across prognostic and diagnostic tasks. Our findings further show that PFN-based models are competitive in low-data regimes, that temporal context can be preserved in the tabular representation, and that performance depends on representative context construction under subsampling. These results demonstrate that tabular foundation models provide a practical and general interface for heterogeneous PHM problems.

Lev Telyatnikov, Raffael Theiler, Leandro Von Krannichfeldt et al.

Progress in Prognostics and Health Management (PHM) is hindered by the lack of standardized and reusable evaluation practices across tasks, datasets, and application domains. Reported results are often difficult to reproduce and compare, as key protocol choices, such as data splits, preprocessing, label alignment, temporal windowing, and metrics, are often implicit or implemented ad hoc. We introduce \picid, a modular evaluation infrastructure that formalizes the PHM evaluation pipeline as an explicit, executable, and reproducible protocol. Through well-defined abstractions, \picid enforces deterministic, leakage-safe dataset construction while remaining flexible across diverse PHM settings. The framework supports fault detection, diagnostics, and prognostics through a unified interface and can be extended to new datasets and model classes without violating protocol invariants. By standardizing data contracts and evaluation boundaries, \picid also enables fair cross-task comparisons across diagnostics (classification) and prognostics (regression), allowing identical model families to be evaluated consistently across heterogeneous settings. We demonstrate \picid through an empirical evaluation of thirteen models on twelve datasets spanning batteries, bearings, turbofan engines, hydraulics, filtration systems, and buildings. This work establishes a reusable foundation for standardized, fair and reproducible evaluation in PHM.

Raffael Theiler, Ludovico Comito, David Leko et al.

Industrial Prognostics and Health Management (PHM) provides a representative case study for a broader challenge in applied machine learning: translating published papers into executable, benchmark-ready implementations. Reproducing under-specified methods in PHM is particularly difficult due to restricted access to industrial datasets, incomplete reporting of preprocessing and evaluation protocols, and implicit design choices (e.g., windowing, target construction, data splits) that critically affect performance. Existing paper-to-code systems generate implementations for individual papers, but these artifacts are often not directly comparable due to inconsistencies in assumptions and evaluation settings. We introduce \emph{agentic, framework-based PHM paper reproduction}, where an agent translates a paper into a shared PHM benchmark framework via a \emph{slot-binding interface}. This interface maps equations and protocol descriptions into structured components (task definitions, dataset adapters, windowing, targets, models, and evaluators), while explicitly recording unresolved assumptions. The resulting implementations are validated against standardized task contracts and evaluation hooks, enabling consistent and comparable benchmarking. We evaluate this approach on 16 PHM papers, comparing framework-enhanced, skill-based and prompt-based agentic reproduction against a recent framework-free paper-reproduction agent. We assess reproduction success, model-based code evaluation, framework binding of paper assumptions, and cross-paper benchmark comparability under standardized protocols. Our results show that coupling agentic generation with a shared framework transforms paper reproduction from isolated code synthesis into executable, assumption-aware, and systematically comparable benchmark implementations.

Zhixian Wang, Qingsong Wen, Chaoli Zhang et al.

Energy (load, wind, photovoltaic) forecasting is significant in the power industry as it can provide a reference for subsequent tasks such as power grid dispatch, thus bringing huge economic benefits. However, there are many differences between energy forecasting and traditional time series forecasting. On the one hand, traditional time series mainly focus on capturing characteristics like trends and cycles. In contrast, the energy series is largely influenced by many external factors, such as meteorological and calendar variables. On the other hand, energy forecasting aims to minimize the cost of subsequent tasks such as power grid dispatch, rather than simply pursuing prediction accuracy. In addition, the scale of energy data can also significantly impact the predicted results. In this paper, we collected large-scale load datasets and released a new renewable energy dataset that contains both station-level and region-level renewable generation data with meteorological data. For load data, we also included load domain-specific feature engineering and provided a method to customize the loss function and link the forecasting error to requirements related to subsequent tasks (such as power grid dispatching costs), integrating it into our forecasting framework. Based on such a situation, we conducted extensive experiments with 21 forecasting methods in these energy datasets at different levels under 11 evaluation metrics, providing a comprehensive reference for researchers to compare different energy forecasting models.

Raffael Theiler, Leandro Von Krannichfeldt, Giovanni Sansavini et al.

Accurate and reliable energy forecasting is essential for power grid operators who strive to minimize extreme forecasting errors that pose significant operational challenges and incur high intra-day trading costs. Incorporating planning information -- such as anticipated user behavior, scheduled events or timetables -- provides substantial contextual information to enhance forecast accuracy and reduce the occurrence of large forecasting errors. Existing approaches, however, lack the flexibility to effectively integrate both dynamic, forward-looking contextual inputs and historical data. In this work, we conceptualize forecasting as a combined forecasting-regression task, formulated as a sequence-to-sequence prediction problem, and introduce contextually-enhanced transformer models designed to leverage all contextual information effectively. We demonstrate the effectiveness of our approach through a primary case study on nationwide railway energy consumption forecasting, where integrating contextual information into transformer models, particularly timetable data, resulted in a significant average mean absolute error reduction of 26.6%. An auxiliary case study on building energy forecasting, leveraging planned office occupancy data, further illustrates the generalizability of our method, showing an average reduction of 56.3% in mean absolute error. Compared to other state-of-the-art methods, our approach consistently outperforms existing models, underscoring the value of context-aware deep learning techniques in energy forecasting applications.

Leandro Von Krannichfeldt, Kristina Orehounig, Olga Fink

Building energy modeling plays a vital role in optimizing the operation of building energy systems by providing accurate predictions of the building's real-world conditions. In this context, various techniques have been explored, ranging from traditional physics-based models to data-driven models. Recently, researchers are combining physics-based and data-driven models into hybrid approaches. This includes using the physics-based model output as additional data-driven input, learning the residual between physics-based model and real data, learning a surrogate of the physics-based model, or fine-tuning a surrogate model with real data. However, a comprehensive comparison of the inherent advantages of these hybrid approaches is still missing. The primary objective of this work is to evaluate four predominant hybrid approaches in building energy modeling through a real-world case study, with focus on indoor thermodynamics. To achieve this, we devise three scenarios reflecting common levels of building documentation and sensor availability, assess their performance, and analyze their explainability using hierarchical Shapley values. The real-world study reveals three notable findings. First, greater building documentation and sensor availability lead to higher prediction accuracy for hybrid approaches. Second, the performance of hybrid approaches depends on the type of building room, but the residual approach using a Feedforward Neural Network as data-driven sub-model performs best on average across all rooms. This hybrid approach also demonstrates a superior ability to leverage the simulation from the physics-based sub-model. Third, hierarchical Shapley values prove to be an effective tool for explaining and improving hybrid models while accounting for input correlations.

Hanmin Cai, Federica Bellizio, Yi Guo et al.

Harnessing the demand-side flexibility in building and mobility sectors can help to better integrate renewable energy into power systems and reduce global CO2 emissions. Enabling this sector coupling can be achieved with advances in energy management, business models, control technologies, and power grids. The study of demand-side flexibility extends beyond engineering, spanning social science, economics, and power and control systems, which present both challenges and opportunities to researchers and engineers in these fields. This Review outlines recent trends and studies in social, economic, and technological advancements in power systems that leverage demand-side flexibility. We first provide a concept of a socio-techno-economic system with an abstraction of end-users, building and mobility sectors, control systems, electricity markets, and power grids. We discuss the interconnections between these elements, highlighting the importance of bidirectional flows of information and coordinated decision-making. We then emphasize that fully realizing demand-side flexibility necessitates deep integration across stakeholders and systems, moving beyond siloed approaches. Finally, we discuss the future directions in renewable-based power systems and control engineering to address key challenges from both research and practitioners' perspectives. A holistic approach for identifying, measuring, and utilizing demand-side flexibility is key to successfully maximizing its multi-stakeholder benefits but requires further transdisciplinary collaboration and commercially viable solutions for broader implementation.

Olga Fink, Ismail Nejjar, Vinay Sharma et al.

Prognostics and Health Management ensures the reliability, safety, and efficiency of complex engineered systems by enabling fault detection, anticipating equipment failures, and optimizing maintenance activities throughout an asset lifecycle. However, real-world PHM presents persistent challenges: sensor data is often noisy or incomplete, available labels are limited, and degradation behaviors and system interdependencies can be highly complex and nonlinear. Physics-informed machine learning has emerged as a promising approach to address these limitations by embedding physical knowledge into data-driven models. This review examines how incorporating learning and observational biases through physics-informed modeling and data strategies can guide models toward physically consistent and reliable predictions. Learning biases embed physical constraints into model training through physics-informed loss functions and governing equations, or by incorporating properties like monotonicity. Observational biases influence data selection and synthesis to ensure models capture realistic system behavior through virtual sensing for estimating unmeasured states, physics-based simulation for data augmentation, and multi-sensor fusion strategies. The review then examines how these approaches enable the transition from passive prediction to active decision-making through reinforcement learning, which allows agents to learn maintenance policies that respect physical constraints while optimizing operational objectives. This closes the loop between model-based predictions, simulation, and actual system operation, empowering adaptive decision-making. Finally, the review addresses the critical challenge of scaling PHM solutions from individual assets to fleet-wide deployment. Fast adaptation methods including meta-learning and few-shot learning are reviewed alongside domain generalization techniques ...

Leandro Von Krannichfeldt, Kristina Orehounig, Olga Fink

Building energy modeling is a key tool for optimizing the performance of building energy systems. Historically, a wide spectrum of methods has been explored -- ranging from conventional physics-based models to purely data-driven techniques. Recently, hybrid approaches that combine the strengths of both paradigms have gained attention. These include strategies such as learning surrogates for physics-based models, modeling residuals between simulated and observed data, fine-tuning surrogates with real-world measurements, using physics-based outputs as additional inputs for data-driven models, and integrating the physics-based output into the loss function the data-driven model. Despite this progress, two significant research gaps remain. First, most hybrid methods focus on deterministic modeling, often neglecting the inherent uncertainties caused by factors like weather fluctuations and occupant behavior. Second, there has been little systematic comparison within a probabilistic modeling framework. This study addresses these gaps by evaluating five representative hybrid approaches for probabilistic building energy modeling, focusing on quantile predictions of building thermodynamics in a real-world case study. Our results highlight two main findings. First, the performance of hybrid approaches varies across different building room types, but residual learning with a Feedforward Neural Network performs best on average. Notably, the residual approach is the only model that produces physically intuitive predictions when applied to out-of-distribution test data. Second, Quantile Conformal Prediction is an effective procedure for calibrating quantile predictions in case of indoor temperature modeling.