Bats are widely distributed around the world, have adapted to many different environments and are highly sensitive to changes in their habitat, which makes them essential bioindicators of environmental changes. Passive acoustic monitoring over long durations, like months or years, accumulates large amounts of data, turning the manual identification process into a time-consuming task for human experts. Automated acoustic monitoring of bat activity is therefore an effective and necessary approach for bat conservation, especially in wind energy applications, where flying animals like bats and birds have high fatality rates. In this work, we provide a neural-network-based approach for bat echolocation pulse detection with subsequent genus classification and species classification under real-world conditions, including various types of noise. Our supervised model is supported by an unsupervised learning pipeline that uses autoencoders to compress linear spectrograms into latent feature vectors that are fed into a UMAP clustering algorithm. This pipeline offers additional insights into the data properties, aiding in model interpretation. We compare data collected from two locations over two consecutive years sampled at four heights (10 m, 35 m, 65 m and 95 m). With sufficient data for each labeled bat class, our model is able to comprehend the full echolocation soundscape of a species or genus while still being computationally efficient and simple by design. Measured classification F1 scores in a previously unknown test set range from 92.3% to 99.7% for species and from 94.6% to 99.4% for genera.
This paper reports a convolutional neural network (CNN)-based damage detection approach for radar-based structural health monitoring of wind turbine blades. Subsequent radar measurements are transformed into an image-type representation for use as CNN input. In contrast to conventional approaches that require compensation for temperature and loading effects, the proposed framework inherently learns all required information during the training phase. Its damage detection performance (i.e., detecting intact vs. damaged condition) is demonstrated using measurements from multiple embedded radar sensors during fatigue testing of a wind turbine blade with a length of 31 m. The achieved F1-score for correct damage classification is between 91% and 100% for both the unloaded and the loaded blade.
This paper evaluates a data-driven classification approach of operational wind turbine blades based on consecutive tower-radar measurements that are each compressed in a two-dimensional slow-time to range representation (radargram). Like many real-world machine learning systems, installed tower-radar systems face some key challenges: (i) transferability to new operational contexts, (ii) impediments due to evolving environmental and operational conditions (EOCs), and (iii) limited explainability of their deep neural decisions. These challenges are addressed here with a set of structured machine learning studies. The unique field data comes from a sensor box equipped with a frequency-modulated continuous wave (FMCW) radar (33.4–36 GHz frequency range). Relevant parts of the radargram that contribute to a decision of the used convolutional neural networks were identified by a class-sensitive visualization technique named GuidedGradCAM (Guided Gradient-weighted Class Activation Mapping). The following main contributions are provided to the field of tower-radar monitoring (TRM) in the context of wind energy applications: (i) every individual rotor blade holds a number of characteristic structural features revealed by the radar sensor, which can be used to discriminate rotor blades from the same turbine via neural networks; (ii) those unique features are not agnostic to changing EOCs; and (iii) pixel-level distortions reveal the necessity of low-level information for a precise rotor blade classification.
1 July 2024 in e-Journal of Nondestructive Testing
The authors have already presented a first analysis of a field study on radar- based structural health monitoring of rotor blades on two operational wind turbines. This analysis will now be extended with measurements from a third operational wind turbine used as a case study for structural monitoring of individual rotor blades over different time intervals and blade modifications. More precisely, a sensor box with a 35 GHz FMCW radar and a highspeed camera was positioned at 90m height on the turbine tower, collecting radar data for structural information and videos for automatic ground truth labelling. After two months of collecting data, each individual rotor blade of that turbine was differently modified and measured again. The radar-facing surface of one rotor blade was partially coated with a microwave absorber foil, while an equivalent foil was applied to the backside of the second rotor blade. The third rotor blade was intentionally left unchanged for the sake of comparability. This study investigates potential limitations like general dataset complexity in radar-based anomaly detection for operational wind turbines. Furthermore, the discriminative ability of a convolutional neural network for classifying moving rotor blades is discussed when encountering feature drift through changing environmental and operational conditions, i.e. metadata like nacelle orientation, rotor blade pitch and rotation speed.
Wind turbines are critical infrastructure whose economical deployment benefits from blade monitoring. Tower-radar remote sensing generates radargrams from a mast-bound active sensor for this and related purposes. Initial machine learning classifiers are publicly available, yet they have not been stress-tested. Suitable test imagery remains scarce. This paper addresses these gaps through interconnected investigations, supported by two data contributions: a synthetic surrogate benchmark (spanning eight image dimensions in a full-factorial design) and an enrichment of the empirical WiRoRa dataset augmented with human annotations and machine-generated ones where the latter can also serve as an on-the-fly labeling solution in the field. The studies report: multi-class anomaly filtering; a sensitivity analysis revealing that the end-to-end-trained (E2E) classifier is poorly calibrated, while its pretrained counterpart is substantially more stable; adversarial vulnerability evaluation showing that the E2E model is also more easily fooled; an analytical derivation of when/why bottleneck training on auxiliary imagery improves representations; a surrogate test confirming the bottleneck hypothesis; and a preliminary Mixture-of-Experts pilot for enhanced traceability as well as scalability that performs environmental/operational metaparameter regression as an archetypal example. Together, the results expose failure modes of existing classifiers and chart a path toward intrinsically interpretable systems for structural health monitoring and beyond.
Dendritic spines are key structural components of excitatory synapses in the brain. Given the size of dendritic spines provides a proxy for synaptic efficacy, their detection and tracking across time is important for studies of the neural basis of learning and memory. Despite their relevance, large-scale analyses of the structural dynamics of dendritic spines in 3D+time microscopy data remain challenging and labor-intense. Here, we present a modular machine learning-based pipeline designed to automate the detection, time-tracking, and feature extraction of dendritic spines in volumes chronically recorded with two-photon microscopy. Our approach tackles the challenges posed by biological data by combining a transformer-based detection module, a depth-tracking component that integrates spatial features, a time-tracking module to associate 3D spines across time by leveraging spatial consistency, and a feature extraction unit that quantifies biologically relevant spine properties. We validate our method on open-source labeled spine data, and on two complementary annotated datasets that we publish alongside this work: one for detection and depth-tracking, and one for time-tracking, which, to the best of our knowledge, is the first data of this kind. To encourage future research, we release our data, code, and pre-trained weights at https://github.com/pamelaosuna/SynapFlow, establishing a baseline for scalable, end-to-end analysis of dendritic spine dynamics.