Accurate and physically interpretable wind power forecasting (WPF) is crucial for ensuring the reliable operation of power grid systems. Wind turbines have operational characteristics significantly influenced by complex environmental factors, such as wind speed fluctuations and intermittency, posing challenges for precise wind power modeling. Although deep learning models have become a promising data-driven solution in WPF, their common “closed-box” nature makes it difficult to balance forecast accuracy with the rationality of physical mechanisms. Therefore, based on the neural basis expansion analysis (NBEATSx) network architecture, this article proposes a multistep WPF method, named physics-informed adaptive-weight NBEATSx. This method realizes the deep integration of physical prior knowledge and data-driven models, providing a novel technical path for solving the joint optimization problem of accuracy and interpretability in WPF. The operational constraints of wind turbines, such as cut-in, rated, cut-out wind speeds, and rated power, are explicitly embedded into the network structure. A dynamic trainable weighting mechanism is leveraged for stack outputs, instead of the traditional aggregation strategy of direct summation. The experimental results based on a dataset of a 2-MW wind turbine show that the proposed method is significantly superior to the benchmark models and NBEATSx variants in terms of forecast accuracy and robustness.

Stochastic process-based methods have been widely used for predicting the remaining useful life (RUL) in engineering system health management. However, real-world degradation processes often exhibit non-Markovian dynamics, nonlinear evolution patterns, and varying operating conditions, which pose significant challenges for accurate RUL prediction. To address these challenges, this study proposes an adaptive RUL prediction framework tailored for nonlinear degradation with structural variability and memory effects. The degradation process is initially modeled using fractional Brownian motion (FBM) based on a segment of historical degradation data. During operation, the model adequacy is continuously assessed through a prediction error metric. If the error exceeds a predefined threshold, a prediction error model is activated to recalibrate the model structure. Subsequently, the drift coefficient is updated using an enhanced variational Bayesian Kalman filter (VBKF). The RUL is predicted based on the first hitting time (FHT) concept, from which an approximate analytical distribution is derived. Model parameters are identified through maximum likelihood estimation (MLE). Finally, the effectiveness and adaptability of the proposed approach are demonstrated through case studies involving a blast furnace and lithium-ion batteries.

The degradation starting time is an important variable affecting the accuracy of degradation path prediction, but little work has been considered in existing studies. This article investigates the problem of predicting the performance of rolling element bearings based on early degradation analysis. Based on an improved dual linear structural support vector machine with envelope spectrum algorithm and$\mu +4\sigma$criteria, a new health indicator is proposed to detect the degradation starting time. As well the detected time is sensitive to early anomalies. In addition, according to the degradation starting time, a convolutional neural network prediction model is established to predict the degradation path. Experiments show the effectiveness and superiority of the proposed method.

Some practical systems such as blast furnaces and turbofan engines have degradation processes with memory effects. The term of memory effects implies that the future states of the degradation processes depend on both the current state and the past states because of the interaction with environments. However, most works generally used a memoryless Markovian process to model the degradation processes. To characterize the memory effects in practical systems, we develop a new type of degradation model, in which the diffusion is represented as a fractional Brownian motion (FBM). FBM is actually a special non-Markovian process with long-term dependencies. Based on the monitored data, a Monte Carlo method is used to predict the remaining useful life (RUL). The unknown parameters in the proposed model can be estimated by the maximum likelihood algorithm, and then the distribution of the RUL is predicted. The effectiveness of the proposed model is fully verified by a numerical example and a practical case study.

A prerequisite for the existing remaining useful life prediction methods based on stochastic processes is the assumption of independent increments. However, this is in sharp contrast to some practical systems including batteries and blast furnace walls, in which the degradation processes have the property of long-range dependence. Based on the fractional Brownian motion, we adopt a degradation process with long-range dependence to predict the remaining useful life of the above systems. Because the degradation process with long-range dependence is neither a Markovian process nor a semimartingale, the exact analytical first passage time is difficult to derive directly. To address this problem, a weak convergence theorem is first adopted to approximately transform a fractional Brownian motion-based degradation process into a Brownian motion-based one with a time-varying coefficient. Then, with a space-time transformation, the first passage time of the degradation process with long-range dependence can be obtained in a closed form. Unknown parameters in the degradation model can be identified using discrete dyadic wavelet transform and maximum likelihood estimation. Numerical simulations and a practical example of a blast furnace wall are given to verify the effectiveness of the proposed method.

Object recognition and content-based image retrieval systems rely heavily on the accurate and efficient identification of 2-D shapes. Features such as color, texture, positioning etc., are insufficient to convey the information that could be obtained through shape analysis. A fundamental requirement in this analysis is that shape similarities are computed invariantly to basic geometric transformations, e.g., scaling, shifting, and most importantly, rotations. And while scale and shift invariance are easily achievable through a suitable shape representation, rotation invariance is much harder to deal with. In this work, we explore the metric properties of the rotation-invariant distance measures and propose an algorithm for fast similarity search in the shape space. The algorithm can be utilized in a number of important data mining tasks such as shape clustering and classification, or for discovering of motifs and discords in large image collections. The technique is demonstrated to introduce a dramatic speed-up over the current approaches, and is guaranteed to introduce no false dismissals.

The problem of efficiently finding images that are similar to a target image has attracted much attention in the image processing community and is rightly considered an information retrieval task. However, the problem of finding structure and regularities in large image datasets is an area in which data mining is beginning to make fundamental contributions. In this work, we consider the new problem of discovering shape motifs, which are approximately repeated shapes within (or between) image collections. As we shall show, shape motifs can have applications in tasks as diverse as anthropology, law enforcement, and historical manuscript mining. Brute force discovery of shape motifs could be untenably slow, especially as many domains may require an expensive rotation invariant distance measure. We introduce an algorithm that is two to three orders of magnitude faster than brute force search, and demonstrate the utility of our approach with several real world datasets from diverse domains.

Object recognition and content-based image retrieval systems rely heavily on the accurate and efficient identification of shapes. A fundamental requirement in the shape analysis process is that shape similarities should be computed invariantly to basic geometric transformations, e.g. scaling, shifting, and most importantly, rotations. And while scale and shift invariance are easily achievable through a suitable shape representation, rotation invariance is much harder to deal with. In this work we explore the metric properties of the rotation invariant distance measures and propose an algorithm for fast similarity search in the shape space. The algorithm can be utilized in a number of important data mining tasks such as shape clustering and classification, or for discovering of motifs and discords in image collections. The technique is demonstrated to introduce a dramatic speed-up over the current approaches, and is guaranteed to introduce no false dismissals.

The vast majority of visualization tools introduced so far are specialized pieces of software that run explicitly on a particular dataset at a particular time for a particular purpose. In this work we introduce a novel framework for allowing visualization to take place in the background of normal day-to-day operation of any GUI based operation system. Our system works by replacing the standard file icons with automatically created icons that reflect the contents of the files in a principled way. We call such icons Intelligent Icons. The utility of Intelligent Icons is further enhanced by arranging them in a way that reflects their similarity/differences. We demonstrate the utility of our approach on diverse applications.

For many real world problems we must perform classification under widely varying amounts of computational resources. For example, if asked to classify an instance taken from a bursty stream, we may have from milliseconds to minutes to return a class prediction. For such problems an anytime algorithm may be especially useful. In this work we show how we can convert the ubiquitous nearest neighbor classifier into an anytime algorithm that can produce an instant classification, or if given the luxury of additional time, can utilize the extra time to increase classification accuracy. We demonstrate the utility of our approach with a comprehensive set of experiments on data from diverse domains.

Over the past three decades, there has been a great deal of research on shape analysis, focusing mostly on shape indexing, clustering, and classification. In this work, we introduce the new problem of finding shape discords, the most unusual shapes in a collection. We motivate the problem by considering the utility of shape discords in diverse domains including zoology, anthropology, and medicine. While the brute force search algorithm has quadratic time complexity, we avoid this by using locality-sensitive hashing to estimate similarity between shapes which enables us to reorder the search more efficiently. An extensive experimental evaluation demonstrates that our approach can speed up computation by three to four orders of magnitude.

Many algorithms have been proposed for the problem of time series classification. However, it is clear that one-nearest-neighbor with Dynamic Time Warping (DTW) distance is exceptionally difficult to beat. This approach has one weakness, however; it is computationally too demanding for many realtime applications. One way to mitigate this problem is to speed up the DTW calculations. Nonetheless, there is a limit to how much this can help. In this work, we propose an additional technique, numerosity reduction, to speed up one-nearest-neighbor DTW. While the idea of numerosity reduction for nearest-neighbor classifiers has a long history, we show here that we can leverage off an original observation about the relationship between dataset size and DTW constraints to produce an extremely compact dataset with little or no loss in accuracy. We test our ideas with a comprehensive set of experiments, and show that it can efficiently produce extremely fast accurate classifiers.