Domain Generalization (DG) has been explored to achieve machine fault diagnosis under previously unseen operating conditions. However, most DG methods assume access to training data collected across multiple conditions, an assumption that rarely holds in industrial practice, where fault data are typically available from only a single operating condition. To address this critical constraint, we propose an attention-throughout latent diffusion model for single-source domain generalization (ATLD-SSDG). The proposed framework learns discriminative fault representations from a single-condition source domain and generalizes robustly to multiple unseen target conditions. First, to effectively capture complementary fault information, vibration signals from three views are fused and projected into a latent space via a collaborative attention fusion mechanism. Next, a dedicated one-dimensional (1D) U-Net is constructed to address information loss in existing approaches and facilitate more effective conditional diffusion. Unlike existing methods that directly adopt computer vision diffusion architectures, the proposed 1D U-Net is specifically designed for vibration signals, preserving localized fault-related details and preventing information loss caused by time–frequency transformations. Moreover, by explicitly regulating self-attention and cross-attention within the diffusion model, the framework preserves fault-relevant characteristics while selectively substituting operating-condition-related factors, thereby enabling controllable and effective domain generalization. Extensive experiments demonstrate superior generalization performance and diagnostic accuracy of the proposed method over state-of-the-art DG methods. These results indicate that latent diffusion, when properly structured for 1D condition-monitoring signals, provides an effective mechanism for single-source domain generalization, helping to close an important gap in DG research for predictive maintenance.

Physics-Informed Neural Networks (PINNs) have emerged as a powerful framework for solving partial differential equations (PDEs) by embedding physical laws directly into the loss function. However, as a fundamental optimization issue, internal covariate shift (ICS) hinders the stable and effective training of PINNs by disrupting feature distributions and limiting model expressiveness. Conventional remedies for ICS-such as Batch Normalization and Layer Normalization-aim to stabilize feature distributions through statistical regularization. However, PINNs require deterministic coordinate-to-solution mappings for enforcing physical constraints, making such strategies fundamentally misaligned with their formulation. To address this issue, we propose Mask-PINNs, which introduce a smooth, learnable mask to adaptively regulate internal features without altering the pointwise physics-based formulation. We provide a theoretical analysis showing that the mask suppresses the expansion of feature representations through a carefully designed modulation mechanism. Empirically, we validate the method on multiple PDE benchmarks across diverse activation functions. Our results show consistent improvements in prediction accuracy, convergence stability, and robustness. Furthermore, we demonstrate that Mask-PINNs enable the effective use of wider networks, overcoming a key limitation in existing PINN frameworks. The codes of the experiments can be found on https://github.com/flongjiang/Mask-PINNs.

Zero-shot fault diagnosis (ZSFD) faces significant challenges in aligning time-series signal features and contextual semantic information. Direct projection from feature space to semantic space may suffer from domain bias, while mutual projection approaches require complex tradeoffs among multiple objective functions. This article proposes a multiattribute cross-modal semantic alignment network (MCSANet) for ZSFD. An enhanced feature extractor incorporating a conditional fault severity encoding mechanism is employed to extract discriminative fault features across multiple attributes. The time-series features, and contextual semantic information are then aligned using a novel cross-modal embedding approach, eliminating the need for complex tradeoffs among multiple objective functions. The proposed method was validated on both self-designed and open-source bearing experiments. Experimental results demonstrate that MCSANet achieves robust diagnosis performance even under nonstationary operational conditions and limited distributional diversity in the training phase. Comparative experiments confirm that MCSANet outperforms current state-of-the-art approaches.

Predicting the Remaining Useful Life (RUL) is essential in Prognostic Health Management (PHM) for industrial systems. Although deep learning approaches have achieved considerable success in predicting RUL, challenges such as low prediction accuracy and interpretability pose significant challenges, hindering their practical implementation. In this work, we introduce a Spatio-temporal Attention-based Hidden Physics-informed Neural Network (STA-HPINN) for RUL prediction, which can utilize the associated physics of the system degradation . The spatio-temporal attention mechanism can extract important features from the input data. With the self-attention mechanism on both the sensor dimension and time step dimension, the proposed model can effectively extract degradation information. The hidden physics-informed neural network is utilized to capture the physics mechanisms that govern the evolution of RUL. With the constraint of physics, the model can achieve higher accuracy and reasonable predictions. The approach is validated on a benchmark dataset, demonstrating exceptional performance when compared to cutting-edge methods, especially in the case of complex conditions.

Fault type classification and fault severity identification are two critical and complementary tasks in fault diagnosis of industrial machines, providing essential information for the maintenance and safety of the machines. However, variable operating conditions in industrial settings make it hard to collect comprehensive fault data covering all possible types and severities, thereby limiting diagnostic efficiency. To overcome these challenges, a novel multi-task network approach is proposed to detect fault type and severity simultaneously even with zero novel samples. Discriminative features are extracted through a contrastive network with task-specific projection heads, enabling the capture of distinct representations for fault type and severity. Two zero-shot mapping spaces are constructed to diagnose fault types and severity by aligning feature representations with the semantic information of fault types and severity. A dynamic self-adaptation optimization mechanism is introduced considering the dependency of fault severity on fault types. It enhances the identification of fault severity. The proposed method was evaluated on two bearing datasets. It achieved up to 89.4 % accuracy for fault type and 83.42 % for fault severity under zero-shot settings, outperforming baselines and demonstrating strong real-world applicability.

Fault detection in mechatronic transmissions is particularly challenging due to the nonstationary nature of monitoring signals arising from complex operating conditions, coupled with the high-safety requirements that limit the availability of fault data. Sparse linear parameter varying autoregressive moving average (Spa LPV-ARMA) model is a powerful tool for dealing with nonstationary time series, and good fitting results can be achieved through the basis function expansion, where parameters of the model are associated with additional variables. However, current research on Spa LPV-ARMA model only considers single basis function, overlooking the potential complementarity of multiple basis functions. This article proposes a novel enhanced Spa LPV-ARMA model with ensemble basis for mechatronic transmission fault detection. The proposed model incorporates the concept of ensemble learning by combining models with different basis functions, and a stepwise approach is utilized to select the models to be combined. The rational choice of the combination scale allows the ensemble model to have fewer parameters with higher accuracy. Simulation and experimental studies in mechatronic transmission are conducted, verifying that the proposed ensemble basis Spa LPV-ARMA model exhibits higher modeling accuracy and fault detection performance.

In modern industrial processes, class imbalance occurs when there is a significant disparity in the number of instances between different classes. Current approaches for handling this problem cannot work effectively due to the invalid instance replenishment strategy for rare categories and even exacerbate class imbalance issues. Therefore, this work presents a novel semi-supervised fault diagnosis (FD) method to address imbalances in FD data by leveraging extensive unlabeled samples. Inspired by adversarial discriminative domain adaptation learning, the proposed approach includes a distribution alignment model for extracting domain-invariant fault features from unlabeled data. Additionally, a soft threshold selection strategy is introduced to strategically select unlabeled fault samples, ensuring an abundance of samples for rare categories and enriching their distribution. Extensive experiments on the two industrial process datasets, including a real-world hot rolling of steel process and a well-established public Tennessee Eastman process, demonstrate the effectiveness of the proposed method in alleviating imbalances and utilizing unlabeled samples, establishing its superiority over existing methods. The code is publicly available onhttps://github.com/Ticuby/SFDM.

Accurate fault diagnosis of trolley mechanisms in ship-to-shore cranes is essential for ensuring cargo transportation at ports. While deep neural networks (DNNs) have made some achievements in fault recognition, DNN’s inherent opacity often limits the ability to provide reliable explanations and interact with domain experts. In the field of neural-symbolic integration, researchers are increasingly focusing on methods to extract relational knowledge from DNNs to offer a semantic understanding of the DNN’s feature learning and reasoning processes, making their internal decision-making mechanisms more transparent and trustworthy for operators. This article introduces a Kolmogorov convolution network (KCN), which extracts relational knowledge that visualizes convolutional operations and simultaneously supports semantic reasoning similar to the IF-THEN form. For convolution visualization, based on the Kolmogorov representation theorem, we introduce a Kolmogorov convolution (KC) with trainable activation functions, which can represent the nonlinear relationships between input and feature maps based on several univariate functions. For the visualization of fully connected layers, a new rule format, classification rules, is designed to provide a semantic representation for fault diagnosis. Finally, experiments, conducted on a 1:4 STSC testbed, demonstrate that KCN achieves its outstanding diagnostic accuracy of 98.3% which outperforms conventional models, and demonstrates potential for optimizing prior knowledge use. The computational efficiency of KC increases by 37% using Levenberg–Marquardt optimization. The resemblance between relational knowledge from KCN and domain knowledge indicates that KCNs possess practical value in areas such as the optimization of prior diagnostic rules. These findings indicate that KCN is a promising approach for accurate and interpretable fault diagnosis in industrial scenarios.

Efficient fault diagnosis in ship-to-shore cranes (STSC) is vital for reliable cargo transport. However, deep neural networks (DNNs) lack transparency, hindering their explainability and interaction with experts during diagnostic decision-making. Currently, neural-symbolic systems increasingly focus on knowledge translation and embedding to enhance DNNs applicability for real-world fault diagnosis. Hence, this article introduces a deep knowledge-augmented belief network (DKABN), where knowledge translation and embedding are conducted to visualize the behavior of deep belief networks and integrate domain knowledge. Specifically, for stacked restricted Boltzmann machines (RBMs) layers, a novel activation-weighted logic RBM (AWL-RBM) is designed to fairly consider the contribution of each literal and reduce the inconsistencies between symbolic logic and RBMs. In the AWL-RBM, we formally prove that multiple literal groups can still be mapped into a violation rank function be capable of equalizing RBM energy minimization. Besides, translation and embedding of symbolic literals are conducted to interpret how RBMs work and fuse domain knowledge. For fully connected layers, a rule format like IF-THENs is translated and embedded to provide a semantic representation for diagnosis decision-making, and integrate domain knowledge. Finally, verified using an STSC testbed, DKABN demonstrates exceptional diagnostic performance and significant application potential.

The fault diagnosis of hoist mechanisms in ship-to-shore cranes (STSCs) is paramount for maintaining shipping schedules and ensuring personnel safety at ports. Although deep networks have achieved some success in diagnosing faults in hoist mechanisms, their opaque nature often precludes them from providing trustworthy explanations for their decisions. To address this problem, this article introduces a deep logic convolutional neural network (DLCNN), which incorporates two symbolic languages (confidence and classification rules) to visualize how convolutional neural networks (CNNs) work. Confidence rules are extracted from logic convolutions (LCs). In the LC, confidence rules are designed from three perspectives-information loss, the tradeoff between soundness and interpretability, and quantitative reasoning-to provide a comprehensive understanding of the feature learning and reasoning of stacked convolutions. Besides, classification rules are extracted from CNN's full-connected layers to elucidate implicit relationships between fault features and labels. Our experimental investigations on an STSC testbed demonstrate that DLCNNs have powerful performance in fault recognition, interpretability, and potential engineering value.

Data-driven feature extraction for machine health monitoring has garnered significant attention, yet two key limitations remain unaddressed: lack of interpretability and the need for extensive historical fault data. To overcome these problems, an online two-dimensional optimization framework is proposed that enables interpretable time-frequency feature extraction and health index (HI) construction without requiring faulty samples for model training. Our approach introduces a convex hull-based closest point optimization model for estimating time-frequency instances and learning interpretable time-frequency features. By leveraging a small set of baseline vibration samples and recent online data, rapid fault diagnosis can be achieved based on optimized interpretable time-frequency features. This method also facilitates long-term degradation tracking by constructing and updating an HI from collected time-frequency spectrograms. Once machine faults appear, updated time-frequency features can show apparent and interpretable fault signatures for prompt fault alarming. Moreover, the proposed framework allows continuous HI updates for incipient fault detection and degradation tracking. The proposed framework is validated by using two run-to-failure datasets and ablation experiments are conducted to demonstrate its superiority.

During the age of the Industrial Internet of Things (IIoT), extensive sensors are deployed on steel production lines to construct intelligent monitoring systems. A fan is a crucial piece of machinery in steel production lines, making its fault diagnosis imperative to prevent air pollution and casualties. DNN (Deep Neural Network) with powerful real-time IIoT data analysis has achieved outstanding performance in recognizing faults. Due to the black-box nature of DNNs, these models cannot provide reasonable explanations for their diagnostic decisions. It is still challenging for experts to make reliable and trustworthy conclusions. To address the issue, this paper introduces a new neural-symbolic model, termed Confidence and Classification DBN (CC-DBN), where confidence and classification rules are extracted from a Deep Belief Network (DBN) to provide an explainable representation of DBN feature learning and reasoning. In order to extract confidence rules, this paper develops a new clustering logic Restricted Boltzmann Machine (C-LRBM). Confidence rules can generate latent features of the raw vibration data of the fan and simultaneously explain the hierarchical reasoning of stacked RBM. Besides, to make trustworthy fan diagnosis decisions, classification rules are extracted to provide an explainable symbolic representation between input and output feature spaces. The experiment is performed on an industrial fan dataset from a leading steel production line in Shanghai. The results demonstrate that the proposed CC-DBN can effectively discover knowledge for fan diagnostic decisions and simultaneously achieve superior fault discrimination over typical classifiers and DBNs.

Lithium-ion batteries have been developed as the most widely used energy storage equipment and power batteries. State-of-charge (SOC) of the battery is a key index to evaluate the remaining range of electric vehicles. The existing SOC estimation methods perform unsatisfactorily on the multivariate long-time series data produced by battery operation. In this article, a graph deviation-based autoformer is proposed to realize accurate SOC estimation. The GD-based input module utilizes the graph structure with embedding vectors to extract spatial features and detect outliers. Encoder and decoder can acquire the temporal cycle dependencies in the data, using sequence decomposition block and auto-correlation mechanism instead of self-attention mechanism. Meanwhile, the online detection method can filter out noise and fluctuations to enhance the accuracy and robustness of the estimation results. The average values of normalized root mean square error, normalized mean absolute error, andR2achieved in the experiments are 0.0057, 0.0042, and 0.9995 respectively, which indicates superior performance on SOC estimation compared to other state-of-the-art methods. The method also has excellent generalization capability for new driving modes and new temperatures, which shows promising potential in practical applications.

Induction motors (IMs) are used extensively as driving actuators in electric vehicles. Motor rotors are prone to defects in the die casting procedure, which can significantly reduce the production quality. Benefitting from the development of Internet of Things (IoT) techniques and edge computing, this study designed an instrumentation system for the fast inspection of rotor defects to meet the objectives of efficient and high-quality rotor production. First, an electromagnetic sensing device is designed to acquire the induced voltage signal of the rotor under investigation. Second, a residual multiscale feature fusion convolutional neural network model is designed to extract the hierarchical features of the signal, to facilitate defect recognition. The developed algorithm is deployed into a cost-effective edge computing node that includes a signal acquisition circuit and a Raspberry Pi microcontroller. The conducted experimental studies show that this implementation can achieve an inference time of less than 200 ms and accuracy of more than 99%. It is shown that the designed system exhibits superior performance when compared with conventional methods. The developed, compact and flexible handheld solution with enhanced deep learning techniques shows outstanding potential for use in real-time rotor defect detection.

Convolutional neural networks (CNNs) have been widely applied to motor fault diagnosis. However, to obtain high recognition accuracy, massive training data are typically required and transmitted to the cloud/local server for training, which may suffer from security and privacy problems. In this article, a noise-boosted CNN (NBCNN) model is developed to achieve accelerated training and improved recognition accuracy with limited training samples. First, the NBCNN model with a noise-injection fully connected layer is established. Then, a strategy for noise selection and injection is proposed to obtain an optimal matching among the data, model, and noise. Finally, the optimal injected noise accelerates the convergence of model training and improves the accuracy of motor fault diagnosis. Compared with the conventional CNN without noise injection and the state-of-the-art models, the effectiveness and superiority of the proposed NBCNN model are validated by two benchmark datasets. In addition, the algorithm is deployed onto an edge device and the results show that the training speed of the developed NBCNN can reach nine times faster than the conventional CNN. The proposed method shows remarkable potential for distributed model training, federal learning, and real-time motor fault diagnosis.

Deep neural networks (DNNs) have been widely used for intelligent fault diagnosis under the closed-world assumption that any testing data are within classes of the training data. However, in reality, out-of-distribution (OOD) cases, such as new fault conditions, can happen after the original trained model is deployed. Most of the current DNNs are deterministic, which can misclassify with high confidence in the open-world scenario. This overconfident behavior would not guarantee the reliability and robustness of fault diagnosis results in practice. Therefore, trustworthy intelligent fault diagnosis with uncertainty estimation is crucial for real applications. In this article, we develop a novel convolutional neural network integrating evidence theory to achieve fault classifications with prediction uncertainty estimation. The estimated prediction uncertainty can identify potential OOD samples. This approach allows a minimal modification of the state-of-the-art DNN model by using a risk-calibrated evidential loss function and Dirichlet distribution that replaces the classification probabilities. The experimental results show that the proposed approach can not only achieve accurate classification of known classes but also detect unknown classes effectively. The proposed method shows significant potential in detecting OOD patterns and provides trustworthy fault diagnosis in open and nonstationary environments.

Intelligent transportation systems (ITS) with surveillance cameras capture traffic images or videos. However, images or videos in ITS often encounter blurs due to various reasons. Considering resource limitations, although recent technologies make progress in image-deblurring, there are still challenges in applying image-deblurring models in practical transportation systems: the model size and the running time. This work proposes an artful variant-depth network (VDN) to address the challenges. We design variant-depth sub-networks in a coarse-to-fine manner to improve the deblurring effect. We also adopt a new connection namely stack connection to connect all sub-networks to reduce the running time and model size while maintaining high deblurring quality. We evaluate the proposed VDN with the state-of-the-art (SOTA) methods on several typical datasets. Results on Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) show that the VDN outperforms SOTA image-deblurring methods. Furthermore, the VDN also has the shortest running time and the smallest model size.

Recently, various fault diagnosis methods based on domain adaptation (DA) have been explored to solve the problem of discrepancy between the source and target domains. However, given complex industrial scenarios, DA-based methods usually fail when the working conditions of machines are unseen, i.e., target data are unavailable during model training. In this article, a generic domain-regressive framework for fault diagnosis, namely, adversarial domain-invariant generalization (ADIG), is proposed. ADIG leverages multiple available domain data to exploit domain-invariant knowledge through adversarial learning between the feature extractor and the domain classifier. Simultaneously, the fault classifier generalizes the knowledge from the source-related domain to diagnose the unseen but related target domain signals. Moreover, customized strategies of feature normalization and adaptive weight are proposed to promote diagnosis performance. Comprehensive case studies show that ADIG achieves satisfactory diagnosis accuracy and robustness under unseen conditions, indicating that ADIG is a remarkably potential diagnosis tool for real-case industrial machines.

The die cast rotor bars in production squirrel cage induction motors (SCIMs) are easily subjected to porosity or other defects in production, which considerably affects the motors’ reliability and efficiency in operation. Planar flux sensing coils have been investigated for the defect detection of SCIM rotor. However, these types of sensors cannot accurately evaluate the severity of porosity or broken bar. This article develops a novel instrument to inspect and quantitatively analyze the rotor quality of SCIM. The sensor consists of the electromagnetic flux sensing coils directly from an SCIM stator. By injecting a dc voltage at phases A and B of the sensor, the induced voltage signal is generated from phase C. A quantitative fault indicator (QFI) is constructed on the basis of the instrument voltage output. The variation trend of the QFI with respect to fault severity is investigated by establishing a theoretical sensor model. Experimental results indicate that the proposed method can accurately detect the porosity and broken bar, and evaluate their severities for the die cast rotor. The developed solution can be easily implemented with low cost and computational complexity, which can achieve real-time inspection of SCIM rotor in theline.

The existing intelligent fault diagnosis methods of rotor-bearing system mainly focus on vibration analysis under steady operation, which has low adaptability to new scenes. In this article, a new framework for rotor-bearing system fault diagnosis under varying working conditions is proposed by using modified convolutional neural network (CNN) with transfer learning. First, infrared thermal images are collected and used to characterize the health condition of rotor-bearing system. Second, modified CNN is developed by introducing stochastic pooling and Leaky rectified linear unit to overcome the training problems in classical CNN. Finally, parameter transfer is used to enable the source modified CNN to adapt to the target domain, which solves the problem of limited available training data in the target domain. The proposed method is applied to analyze thermal images of rotor-bearing system collected under different working conditions. The results show that the proposed method outperforms other cutting edge methods in fault diagnosis of rotor-bearing system.

Predictions of renewable energy (RE) generation and electricity load are critical to smart grid operation. However, the prediction task remains challenging due to the intermittent and chaotic character of RE sources, and the diverse user behavior and power consumers. This article presents a novel method for the prediction of RE generation and electricity load using improved stacked gated recurrent unit-recurrent neural network (GRU-RNN) for both univariate and multivariate scenarios. First, multiple sensitive monitoring parameters or historical electricity consumption data are selected according to the correlation analysis to form the input data. Second, a stacked GRU-RNN using a simplified GRU is constructed with improved training algorithm based on AdaGrad and adjustable momentum. The modified GRU-RNN structure and improved training method enhance training efficiency and robustness. Third, the stacked GRU-RNN is used to establish an accurate mapping between the selected variables and RE generation or electricity load due to its self-feedback connections and improved training mechanism. The proposed method is verified by using two experiments: prediction of wind power generation using multiple weather parameters and prediction of electricity load with historical energy consumption data. The experimental results demonstrate that the proposed method outperforms state-of-the-art methods of machine learning or deep learning in achieving an accurate energy prediction for effective smart grid operation.

In the context of Industry 4.0, extensive deployment and application of advanced manufacturing equipment and various sensors is leading to a growing demand for data exchange between different devices. In smart factories, network transmission has multiprotocol features of wired/wireless communication, and different data flows have different real-time requirements. In this article, a heterogeneous network architecture based on software-defined network is proposed for realizing cross-network flexible forwarding of multisource manufacturing data and optimized utilization of network resources. Subsequently, the mechanism of cross-network fusion and scheduling (CNFS) is analyzed from the perspective of high dynamic characteristics and different delay requirements of data flows. Based on this analysis, a route-aware data flow dynamic reconstruction algorithm is proposed. The proposed algorithm improves the efficiency of manufacturing data cross-network fusion, especially for multivariety and small-batch intelligent manufacturing systems. Furthermore, for meeting the bandwidth requirements of different delay flows, a delay-sensitive network bandwidth scheduling algorithm is proposed. Finally, the effectiveness of the proposed CNFS mechanism is verified using a candy packaging intelligent production line prototype platform.

At present, smart manufacturing computing framework has faced many challenges such as the lack of an effective framework of fusing computing historical heritages and resource scheduling strategy to guarantee the low-latency requirement. In this paper, we propose a hybrid computing framework and design an intelligent resource scheduling strategy to fulfill the real-time requirement in smart manufacturing with edge computing support. First, a four-layer computing system in a smart manufacturing environment is provided to support the artificial intelligence task operation with the network perspective. Then, a two-phase algorithm for scheduling the computing resources in the edge layer is designed based on greedy and threshold strategies with latency constraints. Finally, a prototype platform was developed. We conducted experiments on the prototype to evaluate the performance of the proposed framework with a comparison of the traditionally-used methods. The proposed strategies have demonstrated the excellent real-time, satisfaction degree (SD), and energy consumption performance of computing services in smart manufacturing with edge computing.

The degradation of bearings plays a key role in the failures of industrial machinery. Prognosis of bearings is critical in adopting an optimal maintenance strategy to reduce the overall cost and to avoid unwanted downtime or even casualties by estimating the remaining useful life (RUL) of the bearings. Traditional data-driven approaches of RUL prediction rely heavily on manual feature extraction and selection using human expertise. This paper presents an innovative two-stage automated approach to estimate the RUL of bearings using deep neural networks (DNNs). A denoising autoencoder-based DNN is used to classify the acquired signals of the monitored bearings into different degradation stages. Representative features are extracted directly from the raw signal by training the DNN. Then, regression models based on shallow neural networks are constructed for each health stage. The final RUL result is obtained by smoothing the regression results from different models. The proposed approach has achieved satisfactory prediction performance for a real bearing degradation dataset with different working conditions.

Due to the development of modern information technology, the emergence of the fog computing enhances equipment computational power and provides new solutions for traditional industrial applications. Generally, it is impossible to establish a quantitative energy-aware model with a smart meter for load balancing and scheduling optimization in smart factory. With the focus on complex energy consumption problems of manufacturing clusters, this paper proposes an energy-aware load balancing and scheduling (ELBS) method based on fog computing. First, an energy consumption model related to the workload is established on the fog node, and an optimization function aiming at the load balancing of manufacturing cluster is formulated. Then, the improved particle swarm optimization algorithm is used to obtain an optimal solution, and the priority for achieving tasks is built toward the manufacturing cluster. Finally, a multiagent system is introduced to achieve the distributed scheduling of manufacturing cluster. The proposed ELBS method is verified by experiments with candy packing line, and experimental results showed that proposed method provides optimal scheduling and load balancing for the mixing work robots.

Unmanned Surface Vehicles (USV) with capabilities of mobile sensing, data processing, and wireless communication have been deployed to support remote aquatic environmental monitoring. This paper introduces a sampling planner for spatiotemporal survey of an aquatic environment using a USV-based sensing system. The sampling planner is proposed to distribute the Sampling Locations of Interest (SLoIs) over a geographical area and generate paths for the USVs to visit more SLoIs within their energy budgets. The sampling locations are chosen based on a cellular decomposition of uniform hexagonal cells. The SLoIs are visited and sensed by the USVs along a planned path ring, which is generated through a Spanning Tree-based Planning (STP) approach. To ensure that each SLoI measures within a certain time interval, multiple USVs are assigned to travel along the sub-paths that are divided from the generated path ring. In this paper, first an execution example presents the effectiveness of the proposed method. Then, the performance of the proposed sampling planner is demonstrated based on two application scenarios using USVs for aquatic environmental monitoring. The experimental results are presented in this paper.

This paper presents a novel approach for remaining useful life (RUL) prediction of rotating machinery using hierarchical deep neural networks (DNN). The different health stages are classified by a DNN-based health stage classifier trained by segmented degradation signal. This method builds several RUL predictors based on the health stages of the degradation process. Instead of modeling the entire degradation process (typically including various stages with dramatically different properties) with a single model, the proposed approach builds RUL model for each health stage where more accurate fitting can be obtained. A smoothing operator is applied to obtain the final RUL prediction. The experimental results show that the proposed method can achieve more accurate RUL prediction.