This article aims to solve the Moore-Penrose inverse of time-varying full-rank matrices in the presence of various noises in real time. For this purpose, two varying-parameter zeroing neural networks (VPZNNs) are proposed. Specifically, VPZNN-R and VPZNN-L models, which are based on a new design formula, are designed to solve the right and left Moore-Penrose inversion problems of time-varying full-rank matrices, respectively. The two VPZNN models are activated by two novel varying-parameter nonlinear activation functions. Detailed theoretical derivations are presented to show the desired finite-time convergence and outstanding robustness of the proposed VPZNN models under various kinds of noises. In addition, existing neural models, such as the original ZNN (OZNN) and the integration-enhanced ZNN (IEZNN), are compared with the VPZNN models. Simulation observations verify the advantages of the VPZNN models over the OZNN and IEZNN models in terms of convergence and robustness. The potential of the VPZNN models for robotic applications is then illustrated by an example of robot path tracking.

The emergence of fog computing has improved the performance and efficiency of intelligent manufacturing. In a fog computing platform, fog nodes can provide distributed and proximity resources for tasks related to intelligent manufacturing. Due to the heterogeneous characteristics of fog nodes and the space-time characteristics of intelligent manufacturing, the effective deployment of fog nodes is a precondition for fog computing implementation, it is also a key to providing high-performance services with the fog computing platform. However, traditional deployment strategies cannot satisfy the performance requirements of intelligent manufacturing systems. In this paper, the problem of fog nodes deployment is studied, a fog nodes deployment strategy based on the space-time characteristics (TSBP) is proposed. A fog nodes deployment system model is set up in this paper, the objective function of fog nodes deployment is built up, which the optimization goal is to minimize the computing response time and realize the load balancing of the fog nodes. In addition, the discrete differential evolution algorithm is applied to search the optimal fog nodes deployment solution. Finally, the effectiveness of the proposed TSBP strategy is verified using a candy packaging intelligent production line prototype platform.

Industrial process monitoring is a significant task and has started to get better solved by deep learning. However, ensuring that the learned deep features from process data are effective and interpretable for the monitoring task remains a challenge. In this article, a slow feature analysis-aided autoencoder (SFA-AE) is proposed for interpretable process monitoring. The SFA-AE, which combines the advantages of SFA and an autoencoder (AE), enables the learning of deep slow variation patterns from the high-level features extracted by the AE. Particularly, the AE additionally incorporates in convolutional long short-term memories for representing the spatiotemporal relationships of multivariate time-series process data. These slow patterns that are able to heavily highlight abnormal states are used to construct monitoring statistics and then improve the reliability of fault detection. Most importantly, variable relative attention and its control limit based on self-attention mechanisms are developed for fault diagnosis. The proposed self-attention emphasizes the different contributions of process variables to fault detection, making it possible to interpret fault variables in an end-to-end way. In the experiments on the Tennessee Eastman process, the proposed process monitoring method obtains superior fault detection and diagnosis performance than state-of-the-art ones.

Recently, deep convolutional neural networks (CNNs) have emerged as powerful tools for the correspondence problem in stereo matching task. However, the existence of multiscale objects and inevitable ill-conditioned regions, such as textureless regions, in real-world scene images continue to challenge current CNN architectures. In this article, we present a robust scale-aware stereo matching network, which aims to predict multiscale disparity maps and fuse them to achieve a more accurate disparity map. To this end, powerful feature representations are extracted from stereo images and are concatenated into a 4-D feature volume. The feature volume is then fed into a series of connected encoder–decoder cost aggregation structures for the construction of multiscale cost volumes. Following this, we regress multiscale disparity maps from the multiscale cost volumes and feed them into a fusion module to predict final disparity map. However, uncertainty estimations at each scale and complex disparity relationships among neighboring pixels pose a challenge on the disparity fusion. To overcome this challenge, we design a robust learning-based scale-aware disparity map fusion model, which seeks to map multiscale disparity maps onto the ground truth disparity map by leveraging their complementary strengths. Experimental results show that the proposed network is more robust and outperforms recent methods on standard stereo evaluation benchmarks.

Automation equipment with different functions from different manufacturers is common in lithium ion battery manufacturing workshops, which is manifested as heterogeneous data distributed at different network levels at the information level. The interconnection between a workshop system and equipment is the basis for realizing manufacturing informatization and intelligence, and is a core problem of intelligent manufacturing workshop integration. The key to solve this problem is to establish a standardized and consistent information model. Aiming at the problem of information interconnection, this paper established an information model of the intelligent manufacturing workshop of lithium ion batteries based on the analysis of the architecture, functional categories, and information interaction of the intelligent manufacturing workshop. Then, by clarifying the attribute set, component set, and the information objects contained in each information model, the hierarchical architecture of the information model was constructed. Then, the rules that map the information model in to the OLE for Process Control Unified Architecture (OPC UA) address space is established. The approach for implementing data storage and interaction of the information model based on the OPC UA server/client are also discussed. Finally, taking the soft-pack battery manufacturing workshop as an example, the information model is applied to realize the interconnection and interoperability of production management data, material management data, equipment management data, and quality management data among various levels of the workshop, which verifies the feasibility of the proposed information model.