Although Transformer-based methods have achieved remarkable performance in the field of long-term series forecasting, they can be computationally expensive and lack the ability to specifically model local features as CNNs. CNN-based methods, such as temporal convolutional network (TCN), utilize convolutional filters to capture local temporal features. However, the intermediate layers of TCN suffer from a limited effective receptive field, which can result in the loss of temporal relations during global feature extraction.To solve the above problems, we propose to combine local features and global correlations to capture the overall view of time series (e.g. fluctuations, trends). To fully exploit the underlying information in the time series, a multi-scale branch structure is adopted to model different potential patterns separately. Each pattern is extracted using a combination of interactive learning convolution and causal frequency enhancement to capture both local features and global correlations. Furthermore, our proposed method,multi-scale local-global feature learning network (MLGN), achieves a time and memory complexity of O(L) and consistently achieve state-of-the-art results on six benchmark datasets. In comparision with previous best method Fedformer, MLGN yields 12.98% and 11.38% relative improvements for multivariate and univariate time series, respectively. Our code and data are available on Github at https://github.com/Zero-coder/MLGN.
The Agile Robotics for Industrial Automation Competition (ARIAC) was established to advance flexible manufacturing, aiming to increase the agility of robotic assembly systems in unstructured and dynamic industrial environments. ARIAC 2023 introduced eight agility challenges involving faulty parts, flipped parts, faulty grippers, robot malfunctions, sensor blackouts, high-priority orders, insufficient parts, and human safety. Given the unpredictability of these scenarios, it is impractical to develop a specific strategy for each possible situation. To address these issues, this paper presents a hierarchical framework for autonomous robotic task generation and execution in dynamic scenarios. The framework is divided into a task level and an execution level. Initially, an immediate task management strategy is adopted at the task level, which reasonably decomposes dynamic tasks and allocates short-term tasks to the floor robot and ceiling robot. Later, at the execution level, each robot is designed with an agent architecture that combines PDDL planning with the quick response of behavior trees. Finally, the effectiveness and practicality of the proposed framework were thoroughly validated in ARIAC 2023.
Pressure transmitters are widely used in the process industry for pressure measurement. The sensing line, a core component of the pressure sensor in the pressure transmitter, significantly impacts the accuracy of the pressure transmitter’s output. The reliability of pressure transmitters is critical in the nuclear power industry. Blockage is recognized as a common failure in pressure sensing lines; therefore, a novel detection method based on Trend Features in Time–Frequency domain characteristics (TFTF) is proposed in this paper. The dataset of pressure transmitters comprises both fault and normal data. This method innovatively integrates multi-scale time series decomposition algorithms with time-domain and frequency-domain feature extraction techniques. Initially, this dataset is decomposed into multi-scale time series to mitigate periodic component interference in diagnosis. Subsequently, via the sliding window algorithm, both the time-domain features and frequency-domain features of the trend components are extracted, and finally, the XGBoost algorithm is used to detect faults. The experimental results demonstrate that the proposed TFTF algorithm achieves superior fault detection accuracy for diagnosing sensing line blockage faults compared with traditional machine learning classification algorithms.