Industrial robots are one of the most typical machines in smart manufacturing systems. Their joint bearing faults account for a significant portion of failures. Data-driven bearing fault diagnosis methods, especially deep learning methods, have become a research hotspot due to the development of the industrial Internet of Things and big data. However, the varying working conditions of industrial robots, such as the continuous changing of load and speed, challenge the existing data-driven methods. Although adversarial-based domain adaptive methods are promising for solving this problem, they still face an equilibrium issue in the model training process. Therefore, a novel deep perceptual adversarial domain adaptive (DPADA) method is proposed for fault diagnosis of industrial robot bearings under varying conditions in this article. Here, a novel perceptual loss is proposed to force the target domain and the source domain to have the same distribution, which helps to improve the stability of adversarial training. Correspondingly, a timestamp mapping-based vibration signal screening method is proposed to improve data preprocessing efficiency for fault diagnosis of industrial robots. Extensive experimental results show that the accuracy of DPADA is superior to convolutional neural network (CNN) and conditional domain-adversarial network (CDAN)-based methods. A comparison is further performed on transfer tasks in three classical transfer scenes of industrial robots.

Data-driven bearing-fault diagnosis methods have become a research hotspot recently. These methods have to meet two premises: (1) the distributions of the data to be tested and the training data are the same; (2) there are a large number of high-quality labeled data. However, machines usually work under different working conditions in practice, which challenges these prerequisites due to the fact that the data distributions under different working conditions are different. In this paper, the one-dimensional Multi-Scale Domain Adaptive Network (1D-MSDAN) is proposed to address this issue. The 1D-MSDAN is a kind of deep transfer model, which uses both feature adaptation and classifier adaptation to guide the multi-scale convolutional neural network to perform bearing-fault diagnosis under varying working conditions. Feature adaptation is performed by both multi-scale feature adaptation and multi-level feature adaptation, which helps in finding domain-invariant features by minimizing the distribution discrepancy between different working conditions by using the Multi-kernel Maximum Mean Discrepancy (MK-MMD). Furthermore, classifier adaptation is performed by entropy minimization in the target domain to bridge the source classifier and target classifier to further eliminate domain discrepancy. The Case Western Reserve University (CWRU) bearing database is used to validate the proposed 1D-MSDAN. The experimental results show that the diagnostic accuracy for the 12 transfer tasks performed by 1D-MSDAN was superior to that of the mainstream transfer learning models for bearing-fault diagnosis under variable working conditions. In addition, the transfer learning performance of 1D-MSDAN for multi-target domain adaptation and real industrial scenarios was also verified.

Deep neural networks has been widely used in industrial equipment fault diagnosis. The accuracy of deep neural network is usually proportional to the complexity, but the high inference delay and energy consumption caused by the complex model make it difficult to be applied in the industrial environment of real-time demand. At the same time, in the diagnosis of industrial equipment, different categories of samples have unbalanced characteristics in terms of number, difficulty of identification, and demand of identification. In order to solve this problem, this paper designs Multi-Branch Neural Network (MBNN), which is a new type neural network architecture that can use the unbalance of sample categories in industrial equipment fault diagnosis for fast inference. MBNN has multiple sub-networks with different complexity, and each branch is responsible for processing different categories of samples. Categories with large numbers, easy to process, and high demand of identification are processed through simple branches, such as normal samples. Categories with small numbers, difficult to identification, and low demand of identification are processed through complex branches, such as potential failure samples. The feasibility of MBNN has been verified on motor bearing fault diagnosis and gearbox fault diagnosis, and its performance has been evaluated on multiple computing platforms. The results show that MBNN can greatly improve the inference speed while ensuring the recognition accuracy, especially on resource-constrained platforms.

Demand response (DR) has been widely recognized as an effective solution to help mitigate the stresses imposed on power grids. As new concepts evolve, DR induces various interactions among multiple emerging entities, which further complicates the decision-making processes in grid operations. Recently, game theory (GT) has received great attention in DR management, due to its ability to handle complex decision-making problems. Numerous theoretical GT-based approaches have been proposed for addressing various DR issues, but the feasibility of these theoretical approaches in practical implementation remains in doubt. To bridge the gap between theoretical studies and practical implementations, we first provide specific guidelines regarding how to construct a DR-oriented facility, and then investigate the effectiveness of deploying a Stackelberg game theory-based DR algorithm to manage the energy consumption of the facility, wherein the energy management center (EMC) serves as the leader and multiple devices act as the followers. The experimental evaluation results show that the GT-based DR algorithm achieved great performance in practical DR management, including optimal load control in responding to real-time price (RTP), and peak load reduction with a peak-to-average ratio (PAR) of 1.59.

The degradation of key components of production equipment can have adverse effects on manufacturing, such as unexpected machine shutdown and product quality decline. Implementing self-aware component by prognostics and health management (PHM) based cyber-physical systems (CPS) are promising technologies that can address this problem. Considering that electromagnetic coils are fundamental energy conversion and transformation components of a variety of machines, like electric motors and solenoid valves, and their insulation failure can cause catastrophic effects, a precursor-based prognostics method is proposed in this paper to create self-aware low-voltage electromagnetic coils for incipient insulation degradation monitoring. Sensory data to insulation health information conversion and component-cyber interface development for integrating insulation health information to cyber space are described, which present opportunities for developing transparency and thus predictive maintenance of machines that incorporate electromagnetic coils.