GEMTELLIGENCE: Accelerating gemstone classification with deep learning.

The value of luxury goods, particularly investment-grade gemstones, is influenced by their origin and authenticity, often resulting in differences worth millions of dollars. Traditional methods for determining gemstone origin and detecting treatments involve subjective visual inspections and a range of advanced analytical techniques. However, these approaches can be time-consuming, prone to inconsistencies, and lack automation. Here, we propose GEMTELLIGENCE, a novel deep learning approach enabling streamlined and consistent origin determination of gemstone origin and detection of treatments. GEMTELLIGENCE leverages convolutional and attention-based neural networks that combine the multi-modal heterogeneous data collected from multiple instruments. The algorithm attains predictive performance comparable to expensive laser-ablation inductively-coupled-plasma mass-spectrometry analysis and expert visual examination, while using input data from relatively inexpensive analytical methods. Our methodology represents an advancement in gemstone analysis, greatly enhancing automation and robustness throughout the analytical process pipeline.

Collective relational inference for learning heterogeneous interactions.

Interacting systems are ubiquitous in nature and engineering, ranging from particle dynamics in physics to functionally connected brain regions. Revealing interaction laws is of fundamental importance but also particularly challenging due to underlying configurational complexities. These challenges become exacerbated for heterogeneous systems that are prevalent in reality, where multiple interaction types coexist simultaneously and relational inference is required. Here, we propose a probabilistic method for relational inference, which possesses two distinctive characteristics compared to existing methods. First, it infers the interaction types of different edges collectively by explicitly encoding the correlation among incoming interactions with a joint distribution, and second, it allows handling systems with variable topological structure over time. We evaluate the proposed methodology across several benchmark datasets and demonstrate that it outperforms existing methods in accurately inferring interaction types. The developed methodology constitutes a key element for understanding interacting systems and may find application in graph structure learning.

Filter-Informed Spectral Graph Wavelet Networks for Multiscale Feature Extraction and Intelligent Fault Diagnosis.

Intelligent fault diagnosis has been increasingly improved with the evolution of deep learning (DL) approaches. Recently, the emerging graph neural networks (GNNs) have also been introduced in the field of fault diagnosis with the goal to make better use of the inductive bias of the interdependencies between the different sensor measurements. However, there are some limitations with these GNN-based fault diagnosis methods. First, they lack the ability to realize multiscale feature extraction due to the fixed receptive field of GNNs. Second, they eventually encounter the over-smoothing problem with increase of model depth. Finally, the extracted features of these GNNs are hard to understand due to the black-box nature of GNNs. To address these issues, a filter-informed spectral graph wavelet network (SGWN) is proposed in this article. In SGWN, the spectral graph wavelet convolutional (SGWConv) layer is established upon the spectral graph wavelet transform, which can decompose a graph signal into scaling function coefficients and spectral graph wavelet coefficients. With the help of SGWConv, SGWN is able to prevent the over-smoothing problem caused by long-range low-pass filtering, by simultaneously extracting low-pass and band-pass features. Furthermore, to speed up the computation of SGWN, the scaling kernel function and graph wavelet kernel function in SGWConv are approximated by the Chebyshev polynomials. The effectiveness of the proposed SGWN is evaluated on the collected solenoid valve dataset and aero-engine intershaft bearing dataset. The experimental results show that SGWN can outperform the comparative methods in both diagnostic accuracy and the ability to prevent over-smoothing. Moreover, its extracted features are also interpretable with domain knowledge.

Fully learnable deep wavelet transform for unsupervised monitoring of high-frequency time series.

High-frequency (HF) signals are ubiquitous in the industrial world and are of great use for monitoring of industrial assets. Most deep-learning tools are designed for inputs of fixed and/or very limited size and many successful applications of deep learning to the industrial context use as inputs extracted features, which are a manually and often arduously obtained compact representation of the original signal. In this paper, we propose a fully unsupervised deep-learning framework that is able to extract a meaningful and sparse representation of raw HF signals. We embed in our architecture important properties of the fast discrete wavelet transform (FDWT) such as 1) the cascade algorithm; 2) the conjugate quadrature filter property that links together the wavelet, the scaling, and transposed filter functions; and 3) the coefficient denoising. Using deep learning, we make this architecture fully learnable: Both the wavelet bases and the wavelet coefficient denoising become learnable. To achieve this objective, we propose an activation function that performs a learnable hard thresholding of the wavelet coefficients. With our framework, the denoising FDWT becomes a fully learnable unsupervised tool that does not require any type of pre- or postprocessing or any prior knowledge on wavelet transform. We demonstrate the benefits of embedding all these properties on three machine-learning tasks performed on open-source sound datasets. We perform an ablation study of the impact of each property on the performance of the architecture, achieve results well above baseline, and outperform other state-of-the-art methods.

Learning physics-consistent particle interactions.

Interacting particle systems play a key role in science and engineering. Access to the governing particle interaction law is fundamental for a complete understanding of such systems. However, the inherent system complexity keeps the particle interaction hidden in many cases. Machine learning methods have the potential to learn the behavior of interacting particle systems by combining experiments with data analysis methods. However, most existing algorithms focus on learning the kinetics at the particle level. Learning pairwise interaction, e.g., pairwise force or pairwise potential energy, remains an open challenge. Here, we propose an algorithm that adapts the Graph Networks framework, which contains an edge part to learn the pairwise interaction and a node part to model the dynamics at particle level. Different from existing approaches that use neural networks in both parts, we design a deterministic operator in the node part that allows to precisely infer the pairwise interactions that are consistent with underlying physical laws by only being trained to predict the particle acceleration. We test the proposed methodology on multiple datasets and demonstrate that it achieves superior performance in inferring correctly the pairwise interactions while also being consistent with the underlying physics on all the datasets. While the previously proposed approaches are able to be applied as simulators, they fail to infer physically consistent particle interactions that satisfy Newton's laws. Moreover, the proposed physics-induced graph network for particle interaction also outperforms the other baseline models in terms of generalization ability to larger systems and robustness to significant levels of noise. The developed methodology can support a better understanding and discovery of the underlying particle interaction laws, and hence, guide the design of materials with targeted properties.

Contrastive Learning for Fault Detection and Diagnostics in the Context of Changing Operating Conditions and Novel Fault Types.

Reliable fault detection and diagnostics are crucial in order to ensure efficient operations in industrial assets. Data-driven solutions have shown great potential in various fields but pose many challenges in Prognostics and Health Management (PHM) applications: Changing external in-service factors and operating conditions cause variations in the condition monitoring (CM) data resulting in false alarms. Furthermore, novel types of faults can also cause variations in CM data. Since faults occur rarely in complex safety critical systems, a training dataset typically does not cover all possible fault types. To enable the detection of novel fault types, the models need to be sensitive to novel variations. Simultaneously, to decrease the false alarm rate, invariance to variations in CM data caused by changing operating conditions is required. We propose contrastive learning for the task of fault detection and diagnostics in the context of changing operating conditions and novel fault types. In particular, we evaluate how a feature representation trained by the triplet loss is suited to fault detection and diagnostics under the aforementioned conditions. We showcase that classification and clustering based on the learned feature representations are (1) invariant to changing operating conditions while also being (2) suited to the detection of novel fault types. Our evaluation is conducted on the bearing benchmark dataset provided by the Case Western Reserve University (CWRU).

Interpretable Detection of Partial Discharge in Power Lines with Deep Learning.

Partial discharge (PD) is a common indication of faults in power systems, such as generators and cables. These PDs can eventually result in costly repairs and substantial power outages. PD detection traditionally relies on hand-crafted features and domain expertise to identify very specific pulses in the electrical current, and the performance declines in the presence of noise or of superposed pulses. In this paper, we propose a novel end-to-end framework based on convolutional neural networks. The framework has two contributions: First, it does not require any feature extraction and enables robust PD detection. Second, we devise the pulse activation map. It provides interpretability of the results for the domain experts with the identification of the pulses that led to the detection of the PDs. The performance is evaluated on a public dataset for the detection of damaged power lines. An ablation study demonstrates the benefits of each part of the proposed framework.

Two Machine Learning Approaches for Short-Term Wind Speed Time-Series Prediction.

The increasing liberalization of European electricity markets, the growing proportion of intermittent renewable energy being fed into the energy grids, and also new challenges in the patterns of energy consumption (such as electric mobility) require flexible and intelligent power grids capable of providing efficient, reliable, economical, and sustainable energy production and distribution. From the supplier side, particularly, the integration of renewable energy sources (e.g., wind and solar) into the grid imposes an engineering and economic challenge because of the limited ability to control and dispatch these energy sources due to their intermittent characteristics. Time-series prediction of wind speed for wind power production is a particularly important and challenging task, wherein prediction intervals (PIs) are preferable results of the prediction, rather than point estimates, because they provide information on the confidence in the prediction. In this paper, two different machine learning approaches to assess PIs of time-series predictions are considered and compared: 1) multilayer perceptron neural networks trained with a multiobjective genetic algorithm and 2) extreme learning machines combined with the nearest neighbors approach. The proposed approaches are applied for short-term wind speed prediction from a real data set of hourly wind speed measurements for the region of Regina in Saskatchewan, Canada. Both approaches demonstrate good prediction precision and provide complementary advantages with respect to different evaluation criteria.