industrial maintenance teams

Abstract: Self-supervised pretraining has produced capable time-series foundation models, but its value for Prognostics and Health Management (PHM) has not been measured under leakage-controlled conditions. We measure it on a corpus of 47 public PHM datasets, harmonized to a single tensor contract and partitioned so that 11 datasets are withheld from pretraining in full. Transfer turns out to be task-dependent: a compact channel-independent Transformer encoder (801,808 parameters) pretrained with masked patch prediction raises fault-classification macro-F1 from 0.350 to 0.812 on CWRU and from 0.569 to 0.951 on HSG18, yet on CMAPSS remaining-useful-life estimation no pretrained checkpoint reliably improves upon a from-scratch baseline. We pretrain under two regimes---centralized, and simulated cross-silo federated with ten clients grouped by physical domain---holding architecture, objective, source data and optimization budget fixed. Two further findings are negative. At matched budget the centralized encoder leads by 15.5--20.2 macro-F1 points in four of four comparisons, although the comparison is confounded by a learning-rate schedule that favours the centralized arm and rests on a single pretraining run per regime; on RUL the two regimes are indistinguishable. And the intrinsic SSL loss is not a valid selection criterion: the centralized encoder more than halves the federated reconstruction loss without a corresponding gap on RUL, and a server-momentum sweep moves downstream validation macro-F1 by up to 0.29 while the SSL loss varies by 0.021. Transfer also hinges on the backbone learning rate: the same checkpoint yields 0.169 or 0.829 macro-F1 on CWRU depending on a single order of magnitude. We release the corpus pipeline, the protocol and the code.

Abstract: Conveyor belts are vital arteries in continuous bulk material handling, particularly in heavy process industries such as cement manufacturing. Undetected structural anomalies (longitudinal tears, holes, degraded patch repairs, and impact punctures) cause catastrophic belt snapping, costly downtime, and severe safety hazards. While deep learning offers high accuracy, existing models rely on power-hungry workstation GPUs, hindering practical deployment at remote industrial edge points. In this paper, we propose, implement, and validate an end-to-end, low-power edge AI vision system for real-time conveyor belt defect detection deployed on a Raspberry Pi 5 accelerated by a Google Coral Edge TPU coprocessor. The system leverages an optimized YOLOv11 nano (YOLOv11n) architecture trained on a multi-source industrial corpus exceeding 3,000 augmented samples from an operational cement plant in West Java, open-source datasets, and automated captures. The model undergoes post-training full integer quantization (INT8) compiled for systolic tensor execution. Experimental results demonstrate robust detection capability, achieving precision of 0.742, recall of 0.730, and mAP@0.5 of 0.764 across four defect classes. Deployed on-site in an IP-rated enclosure interfaced with an RTSP PoE industrial camera, the system achieves stable throughput of 30-40 FPS at 320x320 resolution with an end-to-end latency of 70-90 ms. Operational profiling under harsh clinker dust confirms thermal equilibrium at 55 +/- 5 deg C on the host CPU and ~65 deg C on the Edge TPU with zero frame loss. This demonstrates that edge AI bridges the gap between high-accuracy computer vision and cost-effective predictive maintenance in continuous manufacturing.

Abstract: Fault diagnosis during regulated motion requires informative signals even when feedback attenuates tracking deviations. This paper develops an energy-based diagnostic framework that constructs mechanical port-power residuals without a dedicated dynamic observer. Spectral Hamiltonian Algebraic Power Evaluation (SHAPE) combines port-Hamiltonian variables and differential flatness to generate nominal power references from planned motion for fully actuated mechanical systems with collocated actuation. Subtracting these references from commanded effort multiplied by measured flow yields residuals whose final evaluation requires neither recursive observer updates nor measured-state dynamics calculations. Continuous wavelet transform (CWT) scalograms and a shared-encoder convolutional neural network are used to distinguish nominal operation, actuator loss of effectiveness, anomalous friction, and vibration from complete trajectories. Evaluation uses a simulated six degree of freedom Kinova manipulator under model predictive control and fixed plant-model mismatch, with single faults at a specified joint. Across five training seeds and 3000 held-out test runs, SHAPE-CWT achieves a mean accuracy of 84.69 percent, versus 81.67 percent for torque residuals and 97.17 percent for the generalized momentum observer under common CWT processing. The respective sample standard deviations are 0.70, 0.70, and 0.37 percentage points. These results demonstrate useful fault-type discrimination from algebraic power residuals, while severity-excitation profiles and offline velocity perturbations reveal limits to their diagnostic capability.

Abstract: Unsupervised multivariate time series anomaly prediction (AP) aims to estimate future anomaly risks from current observations, providing early-warning signals for proactive intervention and maintenance in complex systems. Existing unsupervised AP methods follow a perturbation-based paradigm, where predefined or random perturbations are injected into historical windows to simulate abnormal future evolution. However, these methods share perturbations across different variables and contexts, and learn deterministic history-to-future evolution. In reality, anomaly evolution is variable- and context-dependent: the same perturbation may be amplified into abnormal future dynamics in one variable or context, while being absorbed as normal fluctuation in another. In addition, future evolution is not uniquely determined by a historical window, since similar histories may lead to multiple plausible trajectories, such as gradual degradation or abrupt changes. To address these problems, we propose EVOLVE, a unified framework that models unsupervised AP via variable- and context-conditioned perturbations and uncertainty-aware future reasoning. EVOLVE constructs context-specific anomaly perturbations through an adaptive anomaly prototype memory, which can dynamically update and retrieve relevant perturbations at the variable level. EVOLVE models uncertainty by sampling multiple latent historical states and decoding through complementary smooth and deviation-amplifying evolution hypotheses, and the disagreement among decoded future trajectories is used to estimate future anomaly risk. Extensive experiments on six real-world benchmark datasets demonstrate that EVOLVE consistently outperforms state-of-the-art anomaly prediction baselines.

Abstract: In standard acoustic anomaly detection (ASD), models are usually trained separately for each machine or domain using explicit metadata. However, in realistic deployments, machine identifiers are incomplete, unreliable, or simply unavailable. Thus, metadata-free machinery ASD asks a single model to monitor mixed machine populations without machine IDs. In this paper, we argue that the main failure mode is not a weak detector family, but representation entanglement. The heterogeneous normal modes overlap in frozen pre-trained feature spaces, making anomaly scoring and approximate retrieval unreliable. We study this problem directly and propose HARMONY (Hierarchical Anchor Retrieval on Manifold for Oblivious-source acoustic aNomalY detection), an anchor-guided geometric repartitioning framework that reorganizes mixed-source features into compact Voronoi regions and reuses this structure for hierarchical retrieval. On DCASE 2020, HARMONY improves mean AUC from 75.40% to 90.00% (14.60 percentage points) over the strongest unified baseline and from 83.90% to 90.00% over a strong foundation-feature baseline. On a single CPU, its hierarchical retrieval achieves a 7.8x speedup over exhaustive search with only a 0.20 percentage-point AUC drop. These results suggest that incorporating explicit geometric partitioning can improve both detection accuracy and retrieval efficiency for ASD. Code is available at https://github.com/Zzyh0208/HARMONY.

Abstract: Long-horizon node outages are harder than conventional missing-value imputation because complete sensor trajectories remain unobserved for extended periods, while the usefulness of spatial and temporal dependencies varies across outage locations and operating regimes. Existing graph, diffusion, and flow-based methods typically impose a fixed structural bias, which can oversmooth abrupt changes or propagate errors from unreliable neighbors. We introduce CTRL-FM, an observation-preserving flow-matching framework that treats structural guidance as an outage-conditioned inference-time decision. A missing-only flow-matching backbone learns a conditional velocity field while keeping observed measurements exactly fixed. For each realized outage, CTRL-FM constructs self-supervised proxy outages from surviving measurements and uses their known values to select among uncontrolled, graph-dominant, temporal-dominant, and balanced control policies. The selected policy is locally modulated by graph and temporal reliability estimated exclusively from surviving observations, while boundary-anchored trends provide structural guidance. Control is applied only to missing entries and is rejected when proxy evidence does not sufficiently improve over uncontrolled sampling. Across PeMS08, METR-LA, Air-36, and AQI, CTRL-FM achieves the strongest overall performance under 30% and 60% node outages. Stress tests with up to 75% sensor loss further show graceful degradation and consistent gains over training-time and fixed structural control. These results demonstrate that validating, selecting, and locally adapting structural guidance for each realized outage is more effective than imposing a single global structural prior.

Abstract: Industrial fluid transport systems are monitored through heterogeneous sensing streams, but robust fault diagnosis remains difficult because response signals vary with operating conditions and differ from physical variables in sampling rate, observation duration and data granularity. To address these challenges, we propose a physical-variable-informed deep learning framework (PhyNet) for robust fault diagnosis under real-world sampling heterogeneity. PhyNet treats physical variables as global operating constraints and response signals as local diagnostic evidence. Its physical-to-response cross-attention mechanism connects sequence-level physical-variable tokens with a learnable global response token, enabling interaction without strict temporal alignment. Across four benchmarks, including three real-world cavitation datasets and one public two-phase-flow dataset, PhyNet achieves the best performance across all evaluated metrics. Class-wise analyses, together with attention and masking analyses, show improved discrimination of ambiguous states and indicate that physical variables meaningfully constrain local response interpretation. These findings demonstrate a deployment-oriented approach to robust diagnosis in heterogeneous industrial environments.

Abstract: This paper proposes an integrated setup for a multi-scale asymmetric collaboration scenario in the context of a remote-expert use case, focusing on the expert side. In this system, the remote expert (with an exocentric view in Mixed Reality (MR)) uses a Tangible User Interface (TUI) to precisely position and rotate their avatar within a scaled tabletop World-in-Miniature (WIM). Inside the WIM, the expert's avatar and the operator share the same scale and egocentric view, while the expert retains a global tabletop overview of the plant to support collaboration. Interviews with industry experts during the participatory design phase revealed the need for an egocentric view inside the plant on the remote-expert side to enable full collaboration. We designed and studied three interaction-visualisation combinations to integrate and control the expert avatar's gaze: VR (fully immersive with direct head control), Head (floating screen with direct head control), and Touch (on-avatar screen with touchpad control). We evaluated these methods with 29 participants across two fault-detection tasks: Same Machine, where both collaborators inspect the same machine, and Twin Machine, where they inspect identical machines in separate locations. The VR condition, which combines immersion, direct head control, and a full-scale view, yielded the strongest overall performance and user experience, while the tabletop avatar setup was well received for collaboration. Our findings inform the design of gaze-control techniques for asymmetric MR-VR collaboration and reveal challenges and opportunities for future work.

Abstract: As physical AI increasingly relies on sensing to understand physical systems, reliable condition monitoring of industrial machinery has become more important. Motors are ubiquitous in industrial systems, and increasing system complexity raises the likelihood of simultaneous faults. Accordingly, compound fault diagnosis that identifies multiple fault components and their severities is increasingly required. Because different fault components jointly affect the same vibration signal, their severity classification can be formulated as related tasks, making multi-task learning (MTL) suitable for exploiting shared information. However, conventional shared-trunk architectures force tasks to share a common representation, potentially causing negative transfer because fault components are characterized by different time-frequency regions. To address this issue, this study proposes a Residual Neural Dimension Reductor with Time-Frequency Channel Attention (RNDR-TFCA), an attention-enhanced cross-talk architecture for multi-output compound fault diagnosis. RNDR-TFCA preserves task-specific feature extractors while selectively exchanging information across tasks. Time-frequency attention emphasizes informative intra-task regions, while channel attention enhances useful inter-task information after nonlinear feature fusion. Experiments on a rotor-bearing system with inner-race fault, outer-race fault, misalignment, and unbalance showed that RNDR-TFCA achieved a macro F1 score of 0.898, outperforming single-task, multi-class, shared-trunk, and cross-talk baselines. Ablation experiments confirmed the benefit of jointly applying both attention mechanisms. RNDR-TFCA required 713 K parameters and 170.42 MMACs, only slightly higher than RNDR. Channel-expanded baselines still underperformed RNDR-TFCA, indicating that the gain was not simply attributable to increased model capacity.

Abstract: Often, \emph{eg} in healthcare and predictive maintenance, what matters is which of several competing causes will strike first, and with what probability: survival analysis with competing risks. Corresponding deep learning methods are developed as bundles: a new architecture together with a new training loss, tested on one to five datasets against a handful of baselines. Thus, a state-of-the-art result cannot be attributed to the architecture, the loss, or the evaluation protocol. The coupling is not accidental: with one incidence curve per cause, a network's head is tied to the losses expressible on it. We vary the two axes independently, three losses, two of them strictly proper, on four backbones, across two modalities that tease the axes apart: 20 tabular and 3 pathology-image datasets. One loss wins in both: modelling cumulative incidence directly under censoring weighting. It brings twice as much as benefits a good choice of backbone on competing-risks data, and no more than it on single-event data: the loss is decisive for competing risks. The backbone matters too, and must match the modality: tabular networks lead on tables, pretrained vision encoders on images. The two choices compound rather than substitute. Proper scoring rules reveal these dynamics; the concordance index (C-index), which is not proper, does not separate models: neither axis moves it, not even tuning on the loss built to improve it. This is an avenue of progress: composed, the two give a model nobody has tried, RealMLP or TabM trained with the cumulative-incidence loss, which takes the best Brier score in our benchmark.

Abstract: In so-called "Industry 4.0," integrated sensors, analytics tools, and other digital technologies supplement industrial workflows, potentiating enhanced visibility and automation. Prognostics and health management (PHM) and natural language processing (NLP) practitioners alike have explored the application of large language models (LLMs) to industrial asset management, but many prior works' focus on exam-like benchmarks has limited their assessment of LLMs' ability to automate practical operations. Herein, we introduce CoffeeBench, a fault diagnostics task for LLM agents, using a simulated appliance. The LLMs we evaluate struggle to consistently identify faults from the sensor information alone, but the best-performing ones can iteratively refine the fault-option space to eventually obtain a successful diagnosis. Our subsequent analyses, therefore, focus on: differentiating models by diagnostic efficiency (RQ1); examining the lagging performance of the three worst models (RQ2); and identifying viable heuristics for selective prediction (RQ3), including that initial diagnostic uncertainty and LLM-judged soundness of reasoning are high-signal predictors of diagnostic success. In addition to our benchmark results (Section 3.1), we provide practical insights for improving the performance of the open-weight models on CoffeeBench, such as by explicitly tracking episode state on their behalf to reduce timeouts (Section 3.2) or applying a deliberation loop to refine diagnostic hypotheses (Section 3.3).

Abstract: Maintenance work orders are the largest written record of how industrial equipment fails, yet in most plants they are close to unusable for analysis. Short texts are abbreviated and misspelt, asset identity is buried in free text, work-type labels contradict the work described, and the fields that matter most for reliability (symptom, root cause, action taken) are usually empty. As a result, diagnostic knowledge stays with senior technicians and leaves when they do. We present Plant Memory, a system that applies technical language processing (TLP) to SAP Plant Maintenance (PM) exports and builds an ISO 14224-aligned maintenance ontology in which every extracted statement is a reified fact carrying a confidence score, the evidence it was read from, and a verification state. Extraction is rule-first, with an optional large language model (LLM) acting as a second reader whose disagreements raise a fact's review priority rather than overwrite it. Technicians verify facts through a review queue, answer targeted knowledge-gap questions where failures repeat without a recorded cause, and approve or reject ontology drift proposals when new terms appear. The resulting graph is served to people through a web application and to AI agents through a Model Context Protocol (MCP) server, so both query the same verified knowledge and every answer cites the work orders behind it. On a synthetic 12-month export of 400 work orders from a parboiled-rice plant, rule-based extraction reaches 96.2% component accuracy, 88.9% failure-mode accuracy and 100% root-cause precision at 62% coverage; on 28 diagnostic questions, ranked root causes from the ontology are correct at top-1 in 82.1% of cases against 53.6% for the raw SAP root-cause column.

Abstract: We study industrial fault diagnosis as a classification task that assigns sensor time-series windows to predefined health states or fault types. Scarce labels and changing operating conditions make repeated training of specialized classifiers costly. Yet structures such as periodicity, trends, and transients can remain diagnostically informative and be examined through reusable analytical tools. LLM agents can select and interpret these tools, but fixed rules or training-derived guidance may not resolve each signal's ambiguity, while unconstrained interpretation may overstate weak or conflicting results. We introduce Agentic4PDM, a framework that separates adaptive investigation from control over evidence use. LLM agents compare each signal with labeled references from every candidate class, identify unresolved distinctions, and propose follow-up measurements. A deterministic software controller, called the host, enforces contract-checked gated adjudication (CCGA): it checks requests, requires commitment to a complete tool batch before results are observed, and assigns evidence roles based on tool checks against labeled references. These roles distinguish corroborative support from advisory information. The Judge Agent proposes a diagnosis, while the controller checks protocol compliance and records the investigation. Agentic4PDM supports training-free diagnosis using pretrained representations and labeled references without task-specific diagnostic models, and a standard setting that additionally investigates trained-model predictions. Experiments on selected bearing and motor diagnosis challenges and an unfiltered industrial test set supplied by our customer show gains in aggregate macro F1 over the evaluated diagnostic and agentic baselines. Ablations further support the value of the governed workflow.

Abstract: Industrial IoT sensors produce continuous, high-volume data streams that predictive maintenance needs to analyse in real time. Cloud-centric architectures send all raw telemetry to central servers, which costs latency, bandwidth and resilience. This paper presents a hybrid cloud-edge architecture for manufacturing predictive maintenance built on AWS IoT Core and AWS IoT Greengrass v2, with local machine learning inference at the edge and selective cloud synchronization. We deploy two configurations on real AWS infrastructure and compare them: a cloud-only baseline (Configuration A) and the proposed hybrid edge architecture (Configuration B). We measure end-to-end inference latency, bandwidth consumption and inference accuracy. Configuration B cuts cloud-bound bandwidth by 86.8% (63.6 KB to 7.2 KB per 200-reading window) and decision latency by 256x (23.1 ms cloud round trip to 0.09 ms local inference). At the edge, with no cloud involvement, it keeps an anomaly-class F1 score of 0.84 and 91% recall. The evaluation also instruments system uptime and Stream Manager queuing under cloud disconnection; the quantitative disconnection experiment is left as planned work. Our review of the literature points to four gaps that this work addresses: the lack of empirically validated Greengrass v2 deployments for predictive maintenance, unquantified bandwidth savings from selective edge synchronization, unmeasured resilience under cloud disconnection, and the open MLOps feedback loop at the edge.

Abstract: Consumer rotating devices, including washing machines, air conditioners, electric fans, robotic vacuum cleaners, and home fitness equipment, increasingly rely on vibration sensing for intelligent condition monitoring and predictive maintenance. Ensuring reliable operation in these resource-constrained appliances requires efficient, lightweight artificial intelligence (AI) solutions capable of processing non-stationary signals under real-world operational interference. This paper proposes a lightweight AI-assisted vibration sensing framework that employs continuous wavelet transform (CWT) and Hilbert-Huang transform (HHT) to convert one-dimensional (1-D) vibration time-series signals into two-dimensional (2-D) time-frequency representations. These representations are subsequently analyzed using lightweight deep learning architectures, specifically MobileNetV3-Small, ConvNeXt-Tiny, and the You Only Look Once version 11 classification model (YOLOv11-cls). Public bearing benchmark datasets, including Case Western Reserve University (CWRU), Paderborn University (PU), and Intelligent Maintenance Systems (IMS), are utilized as representative rotating components to investigate model generalization. The proposed framework is designed with eventual embedded deployment in consumer electronics in mind. Experimental results demonstrate that CWT combined with YOLOv11-cls achieves high diagnostic accuracy, while MobileNetV3-Small provides an attractive low-latency alternative for computationally constrained edge platforms. Conventional random splitting is also compared with dataset-specific structured isolation. The results highlight the importance of avoiding data leakage and quantify tradeoffs in classification accuracy, parameter count, floating-point operations (FLOPs), model footprint, preprocessing cost, and central processing unit (CPU) inference latency.

Abstract: Maritime systems operate in highly dynamic environments where unexpected equipment failures can compromise safety, reliability, and operational efficiency. Recent advances in artificial intelligence (AI), machine learning, digital twins, and predictive maintenance enable proactive failure prediction and prevention. However, ensuring trustworthy and explainable decision-making remains a major challenge in safety-critical maritime applications. This chapter reviews key AI technologies required for explainable failure prediction and prevention in maritime systems and presents a conceptual architecture capable of supporting autonomous or human-in-the-loop corrective actions. This architecture integrates data acquisition, time-series forecasting, anomaly detection, risk assessment, decision-making, and explainable AI into a closed-loop framework. With reference to the architectural components, a review and discussion of relevant maritime studies is performed, outlining their methods, advantages, and limitations. Furthermore, it highlights current challenges, including uncertainty and robustness, model generalization, explainability, limited availability of maritime datasets, and operational deployment, and identifies future research directions toward trustworthy AI-assisted maritime decision-making.

Abstract: Predictive maintenance requires reliable remaining useful life (RUL) estimation. Existing methods mainly follow two paradigms: wear-based aging models that capture cumulative degradation and sensor-driven data models that reflect instantaneous health conditions, each providing only partial information. In this work, we propose a probabilistic fusion framework that integrates wear-based and sensor-based prognostic components through failure probability distributions. Based on explicit structural assumptions linking wear, latent health, sensor observations, and failure, we derive a principled combination rule that enables uncertainty-aware integration with adaptive weighting of the components. Experimentally, we assess this combination rule by learning the wear-based component using a parametric survival model and the sensor-based component using a 1D convolutional neural network (1D-CNN) with a post-hoc uncertainty model. Evaluation on multiple N-CMAPSS datasets demonstrates that the fused model improves point accuracy, preserves the C-index, and produces narrower yet well-calibrated prediction intervals compared to either component alone. The results highlight the complementary roles of wear-based survival model and sensor-based deep learning model, and show that their probabilistic integration provides a structured pathway toward more robust and consistent prognostics over the life-time.

Abstract: Large language models are increasingly used as integration layers above specialized tools, but a stronger component does not necessarily produce a stronger combined system. Across five diagnostic datasets (bearing vibration, process monitoring, semiconductor equipment), we study whether an LLM can reliably use external diagnostic information; paired repeat calls separate advice effects from output instability. In all five, conflicting external information overturned initially correct LLM judgments. Among the four datasets with direct integration comparisons, none showed a consistent advantage for implicit LLM integration over the stronger standalone source. On a Tennessee Eastman confirmation set whose protocol was fixed before evaluation, unaided accuracy was 64.67%, implicit LLM-specialist integration 77.43%, and the specialist alone 83.33%. Specialist information improved the LLM by 12.8 points (95% interval 9.7 to 15.9), yet the integrated output stayed 5.9 points below the specialist (95% interval -12.0 to -0.7). A two-source selector oracle reached 92.76%, indicating complementarity that the integrated output did not fully realize. The integrated output missed 140 of 295 specialist corrections (47.5%) but lost 15 of 99 initially correct LLM judgments (15.2%). The deficit remained under prompt and specialist sensitivity analyses. Among CWRU cases solved under both evidence presentations, task-aligned physical evidence yielded lower estimates of susceptibility to incorrect advice in six of seven models (five intervals excluding zero); higher reasoning effort gave no reliable reduction in five models, and a separate four-model TEP analysis gave no clear evidence that it resolves the integration problem. Source quality and integration quality should be evaluated separately: an integration layer should be compared with its stronger standalone component, not only with the unaided LLM.

Abstract: Large Language Model (LLM) agents are increasingly deployed in high-stakes settings such as industrial maintenance and equipment fault troubleshooting, where workers occupy a variety of roles. A capable agent must therefore act in a way that is calibrated to user's role: taking actions and providing information that respect the role's knowledge and capability boundaries. Unlike coding, where mistakes are usually recoverable, agent responses in these settings are enacted on physical equipment, and can therefore cause irreversible equipment damage, production loss, or personnel harm. Existing benchmarks, however, largely overlook the need for agents to infer what a role intends and acting only through tools that role may legitimately use, a capability which we term Perspective Awareness. To this end, we introduce ReFract, a benchmark of 150 expert-validated entries in which an agent must act differently in response to the same query depending on user's role. Entries of ReFract are grounded in anonymized queries from domain support conversations, against which we construct Text World Models that simulate the agent's operating environments and assemble perspective-aware action trajectories. State-of-the-art LLMs solve at most 69% of the tasks with more than 50% of their trajectories contain attempts of taking perspective-violating actions. ReFract exposes perspective awareness as a distinct, largely unsolved axis of agent evaluation and motivates agents that calibrate not just how to act, but for whom.

Abstract: Explainable Artificial Intelligence (AI) enables humans to understand and interpret decisions of AI models. Instead of having a black box, explainability supports humans in understanding AI models' behavior. Existing explainable AI approaches often present explanations on 2D displays using pre-recorded data, requiring users to relate the displayed information back to the physical objects and real world locations involved in a model's decision. Users are forced to decouple data exploration and capture from AI model interpretation. For AI systems that work within physical environments, this separation can make explanations difficult to interpret in context. We propose using Augmented Reality (AR) to enhance the understanding of AI models by enabling spatial explainability information directly in a user's workspace, in real time, as they explore the world. We show how known explainability methods can be applied in AR and provide insights into user experiences with such an application.

Abstract: This study provides a data-driven analysis of a novel dataset of single-cell Anion Exchange Membrane water electrolyzers (AEMWE), operated under constant current load across multiple heterogeneous experimental campaigns. We train and evaluate a range of machine learning models with different complexity, including linear baselines, LSTMs and CNNs, to perform medium-term forecasting of the cell voltage degradation curve. The models are assessed within a rigorous training and evaluation framework specifically designed for heterogeneous industrial data.

Abstract: Defect detection systems for industrial condition monitoring can only be relied upon if they are validated, yet defective samples are rare and, for a specific asset, often nonexistent. We present a framework that synthesizes severity-graded defects on real non-defective images without any defect references for the target asset, that can be used for model selection and validation. A defect taxonomy for common failure modes is distilled from literature into prescriptive prompts at varying defect severities. Regions of interest are cropped from in defect-free images and edited with a pre-trained image generation model ("FLUX.2 [klein]"). Color-matching and blending are employed to improve structural coherence with the original image. Generations are filtered out by a scorer and by estimated detection difficulty. Model selection experiments on MVTecAD show image AUROC choice regret over model selection can be nearly halved compared to the best fixed model chosen with access to test data. Experiments show the need for severity-graded anomaly synthesis. A case study investigates the proposed method for in-situ monitoring of Pelton turbine runners in hydropower, where real defect images are rare and expensive to collect. A PatchCorebased anomaly detection model is fit on Pelton turbine images and selected and validated using synthetic images, showing strong detection performance (94 % correct detection at optimal threshold and AUROC 0.97). The model reliably detects moderate and advanced defects, while early-stage defects remain challenging, indicating the synthetic data meaningfully stresses detector sensitivity.

Abstract: We consider fair resource allocation in sequential decision-making environments modeled as major-minor weakly coupled Markov decision processes (M2WCMDP). In this framework, resource constraints couple the action spaces of a major sub-Markov decision process (sub-MDP) and a population of minor sub-MDPs that would otherwise operate independently. Instead of using the traditional utilitarian (total-sum) objective, we optimize a general class of monotone, concave, permutation-invariant, normalized fairness functions. With homogeneous minor sub-MDPs, we prove that the problem under symmetry reduces to optimizing the platform-plus-mean-participant utilitarian objective over the class of \textit{permutation-invariant} policies, which allows us to exploit efficient algorithms that optimize the utilitarian-based objective to solve this fairness-aware problem. For more general settings, we introduce a count-proportion-based deep reinforcement learning approach with a priority-based sampler that generates feasible count actions. The generality of our framework means that the proposed algorithms and theoretical guarantees transfer to any domain with a symmetric M2WCMDP structure. We consider two applications: the machine replacement problem and the joint control of pricing and taxi relocation problem on a New York City-calibrated dataset. We validate our theoretical findings with comprehensive experiments, confirming the effectiveness of our proposed method in achieving strong fairness-aware performance while remaining scalable.

Abstract: Several businesses apply maintenance, repair, and overhaul (MRO) principles to the life-cycle of their existing products. In cases like casted gas turbine component Product Lifecycle Management (PLM), repairing components in frequent intervals can extend the lifetime expectation of the product, provide higher cost efficiency compared to newly produced components, and even improve the part design during the repair cycle. Another aspect of repair concerns sustainability, as products often contain rare materials. The emissions produced by the repair process are usually smaller than mining materials and casting new components. To optimize the repair process further, we propose the Smart Expert System (SES), which assists engineering experts with machine learning-based decision support throughout the repair process. We elaborate on its IT architecture and present machine learning models employed for representative MRO use cases. The SES is evaluated using actual industry data from a leading gas turbine company and demonstrably fulfills formulated requirements concerning the suitability of the overall decision support and the stability of the enclosing IT architecture.

Abstract: Time-series diagnostic systems rarely rely on retrieving relevant historical cases, and when they do, retrieval is evaluated only indirectly through downstream prediction. We introduce READ-Bench, a benchmark for historical-case retrieval across 12 diagnostic datasets, centered on multivariate time series, that defines relevance by shared fault or event type rather than signal shape, so visually different traces of the same fault count as relevant while similar-looking traces of different faults do not. Treating retrieval as a base retriever followed by a reranker, we evaluate classical distances, symbolic retrievers, self-supervised and foundation-model embedders, and their fusion, plus label-aware and language-model rerankers, under one protocol that varies supervision, pollution, and corpus scale with significance testing. Under a common channel-independent interface, pretrained representations offer no statistically detectable advantage over strong classical and symbolic baselines for search alone. The decisive factor is a small amount of resolved-case supervision at reranking, namely a Gaussian-process reranker that propagates a few neighbor labels in embedding space, which helps far more than more sophisticated representations or language-model reasoning and holds under pollution and at full corpus scale. Guided by these findings, we fuse a normal-residual-scored embedder with a dynamic time warping leg via reciprocal-rank fusion, then rerank with the Gaussian-process reranker, improving NDCG@10 over its own search stage on all 12 datasets, by +0.11 from reranking and +0.16 over the strongest single base retriever.

Abstract: Convolutional neural networks (CNN) are widely used to predict the remaining useful life (RUL) of rolling bearings from time-frequency representations (TFRs) of vibration signals. However, during degradation, characteristic structures in TFRs align predominantly along the frequency or time axis, making it challenging for conventional CNN isotropic kernels to capture directional structure. Furthermore, global average pooling (GAP) averages across axes, potentially obscuring the locations and concentrations of salient activations. This study introduces a factorized-axis convolutional gated recurrent unit (GRU) that employs multiscale anisotropic convolution and dual-axis convolution block attention module to enhance directional features and highlight salient time-frequency regions. Dynamic adaptive pooling (DAP) adaptively aggregates the time-frequency-axis information from the extracted feature maps, whereas a GRU captures temporal dynamics in the latent representations and Monte Carlo dropout enables predictive uncertainty estimation. Experiments on two public bearing datasets demonstrate that the proposed model outperforms existing RUL prediction methods across operating conditions. Ablation experiments demonstrate that the factorized axis-wise design achieves lower mean errors than convolutional isotropic kernels. DAP yields clear improvements on one dataset while matching GAP on the other, highlighting the importance of anisotropic feature extraction and adaptive feature aggregation for TFR-based RUL prediction.

Abstract: Anomalous sound detection (ASD) has long been dominated by k-nearest-neighbor (KNN) based detectors, which essentially perform implicit likelihood estimation over normal samples. In this work, we investigate whether generative models can better serve this role. We propose Relative Mismatch, a generative ASD backend powered by flow matching, which learns a velocity field that transports Gaussian noise to a representative feature space of normality. During inference, it measures the mismatch between the oracle and predicted path velocities and aggregates them through a two-level design. To mitigate the inherent mismatch offsets incurred by domain shift, each query is further calibrated with the mismatch of its local normal reference, thereby exposing only its deviation beyond normality. Extensive experiments on DCASE 2020--2025 demonstrate that Relative Mismatch outperforms state-of-the-art backends with the highest score of 71.01, along with strong robustness and training stability. Furthermore, we show that curating a compact and discriminative feature space is the key to unleash the power of generative models for ASD.

Abstract: Mobile robots require robust, real-time fault detection capable of continuous adaptation on constrained edge hardware. While deep time-series models excel at unsupervised anomaly detection, their computational cost prohibits high-frequency onboard execution. This paper bridges this gap via a Teacher-Student distillation framework. An offline foundation model (TSPulse) generates pseudo-labels from unlabeled time series augmented with fault injections. A lightweight MiniRocket Student, adapted with a Recursive Least Squares estimator, approximates this complex decision boundary to execute real-time inference onboard. Evaluations on the TSB-AD benchmark and a physical mobile robot demonstrate the Student achieves a 4.30 ms CPU inference latency. During real-world domain shifts, online adaptation enables the Student to recover from unseen mechanical degradation, improving VUS-PR scores from 0.26 to 0.75 without catastrophic forgetting. Crucially, an uncertainty-guided active learning strategy minimizes operator cognitive load, requesting sparse interventions only when encountering novel fault distributions. These results validate the deployment of state-of-the-art anomaly detection on resource-constrained robotics through offline-to-online distillation.

Abstract: The integration of model-based and data-driven paradigms provides a powerful framework for fault diagnosis by combining the interpretability of analytical redundancy relations, i.e., input-output relations that are used as diagnosis indicators in model-based diagnosis, with the adaptability of learning techniques. DT4X is a recent diagnosis algorithm that uses symbolic regression to generate multivariate relations leveraging some properties of analytical redundancy relations and uses them as split functions in a decision tree. However, its symbolic regression procedure optimizes only the separation between two selected classes at each node, often fragmenting the remaining classes and degrading both interpretability and diagnosis performance. This paper introduces DT4X+, an enhanced version of DT4X that modifies the construction of training sets and the symbolic-regression loss so that expressions separate the target classes while preserving the coherence of non-target classes. The resulting relations become fully consistent with ARR properties and lead to more informative splits, improved robustness, and better performance on dynamic-system datasets. Experiments conducted on several benchmark systems demonstrate the benefits of this enhanced formulation.

Abstract: Maintenance work orders must often be processed offline on embedded hardware, yet downstream software requires predictable structured output. We present ARID (Aviation-inspired Routing for Industrial Deployment), which extracts component, failure mode, symptom, and maintenance action into fixed-schema JSON on an 8 GB NVIDIA Jetson Orin NX. ARID combines conservative dual-teacher filtering, targeted noise-aware synthesis, one routing decision per work order, 4-bit inference, and grammar-constrained decoding. From 2,326 unlabeled OMIn records, it retains 716 training pairs and adds 99 topology-constrained records targeting action extraction. On 300 human-labeled records, ARID reaches 84.8% token-F1 on the reference stack and 82.9% on the deployed Jetson. Resident serving achieves 5,310/5,656 ms P50/P99 at 12.5 W. On zero-shot MaintNet transfer, semantic F1 falls to 46.4% while parser success remains at least 99.8%, showing that output validity transfers but field semantics do not.

Abstract: Digital Twins (DTs) are widely adopted across a variety of application domains. In industrial sectors, particularly in mechanical engineering, they accelerate product development, reduce risks, enable early issue prediction, and lower sustainment costs . In practice, DTs increasingly integrate physics-based (deductive) and data-driven (inductive) models into hybrid models combining the complementary strengths of both modeling paradigms. In this paper, we refer to this integration paradigm as hybridization. Despite this trend, the engineering of hybrid DTs that is, remains insufficiently documented. Hybridization is often introduced in an ad hoc manner, and its implementation is only partially made explicit, which limits reproducibility and transferability. This paper reports on the development of an existing fluidic loop digital twin at Centre Technique des Industries M{é}canique (CETIM). The DT is described using the characterization framework of Gil et al., providing a structured view across its lifecycle dimensions. To make hybridization explicit, the case is further analyzed through a complementary characterization structured along two dimensions: motivation and realization. The resulting description provides a traceable account of hybridization decisions and supports the documentation and transfer of hybrid DT engineering practices.

Abstract: Reinforcement learning (RL) agents deployed in real-world environments are often vulnerable to adversarial perturbations in state observations, creating risks in safety-critical applications. Certification methods can improve robustness against adversarial perturbations by providing lower bounds on expected cumulative rewards. Existing certification methods, however, mainly focus on risk-neutral objectives. In this paper, we extend certification methods to risk-sensitive objectives by establishing lower bounds on the exponential utility of cumulative rewards under $l_{p}$-norm-bounded state adversarial perturbations ($1\leq p <\infty$). By introducing a $φ$-divergence relaxation of the perturbation set, we formulate the risk-sensitive certification problem as a convex optimization and derive its dual to obtain a tractable approximation of the certified lower bound. We further propose an empirical method that improves certified lower bounds by selecting the training risk-aversion parameter $β$ independently of the risk level used during evaluation. Experiments on both OpenAI Gym environments and a machine replacement problem show that, compared to risk-neutral training, risk-averse training generally yields policies with higher certified lower bounds, particularly under larger perturbation budgets. Moreover, under both risk-neutral and risk-averse evaluation settings, increasing risk aversion during training leads to non-monotonic certification performance, where certified lower bounds initially improve but eventually decrease due to overly conservative policies.

Abstract: This article introduces PeriodicCALM, an effective real-time anomaly detection framework designed for cyclostationary data streams. While classical cyclostationary processes feature periodically time-varying statistical properties, real-world signals often contain recurring impulsive components that conceal abnormal behavior. Existing real-time methods for struggle with these dynamics, frequently misinterpreting phase-dependent variability as non-cyclic anomalies and causing excessive false alarms. To address this, PeriodicCALM incorporates cycle-dependent variability to systematically ignore regular cyclic impulses while accurately isolating genuine anomalies. Operating in real time with continuous retraining capabilities, the method adapts dynamically to evolving signal characteristics. Comparative evaluations against the baseline CALM framework using simulated data demonstrate significant improvements in detection accuracy and training efficiency, alongside a reduction in prediction latency. Furthermore, the practical utility of PeriodicCALM is validated on real-world vibration signals collected from a compressor monitoring system.

Abstract: In data-driven predictive maintenance (PdM), feature extraction is usually treated as fixed preprocessing: a descriptor set is chosen once and reused while the downstream model or forecasting horizon changes. This paper isolates the representation-learning stage and presents a quantile-led feature-extraction framework based on a dual-stage MLP-QRNN hierarchy. QRNN1 learns a broad ten-quantile conditional distribution for each sensor channel, while skip-connected QRNN2 refines a retained mid-tail quantile set into compact, channel-resolved, distribution-aware features. A fixed thirteen-pipeline ablation spans 1-hour, 70-hour, and 30-day regimes across 72 machines in 9 industrial facilities, with the downstream temporal classifier held fixed within each regime. Increasing the retained mid-tail set from two to four quantiles improves 30- and 60-minute F1-score, reaching 75.92% and 72.44% with attention enabled. The results also show that representations do not transfer reliably beyond their design horizon unless feature capacity, temporal embedding, activation strategy, and sensor breadth are scaled with the forecasting task. The unmodified short-horizon extractor falls to 42.90% F1 at 70 hours, whereas horizon-conditioned extractors reach 60.38% at 70 hours and 79.97% at 30 days. The framework therefore supports treating PdM feature extraction as a horizon-dependent representational stage rather than fixed preprocessing.