Category: IEEE Transactions on Industrial Informatics

Decentralized optimizations have been extensively applied in large-scale industrial cyber-physical systems to achieve control scalability. However, state-of-the-art methods heavily depend on explicit communications between participants, exposing the entire control framework to data confidentiality risks. To overcome this challenge, in this article, a privacy-preserving decentralized multi-agent cooperative optimization paradigm was developed via integrating cryptography into decentralized optimization. The proposed approach can effectively protect participants’ privacy against external eavesdroppers, honest-but-curious agents, and the system operator. Theoretical security and correctness analyses are provided. Simulations of numerical examples and experiments on a real-world platform are given to demonstrate the security, accuracy, and applicability of the proposed method.

The use of aerial base stations, AI cloud, and satellite storage can help manage location, traffic, and specific application-based services for vehicular social networks. However, sharing of such data makes the vehicular network vulnerable to data and privacy leakage. In this regard, this article proposes an efficient and secure data sharing scheme using community segmentation and a blockchain-based framework for vehicular social networks. The proposed work considers similarity matrices that employ the dynamics of structural similarity, modularity matrix, and data compatibility. These similarity matrices are then passed through stacked autoencoders that are trained to extract encoded embedding. A density-based clustering approach is then employed to find the community segments from the information distances between the encoded embeddings. A blockchain network based on the Hyperledger Fabric platform is also adopted to ensure data sharing security. Extensive experiments have been carried out to evaluate the proposed data-sharing framework in terms of the sum of squared error, sharing degree, time cost, computational complexity, throughput, and CPU utilization for proving its efficacy and applicability. The results show that the CSB framework achieves a higher degree of SD, lower computational complexity, and higher throughput.

With the development of the industrial internet technology, the medical data exchange in IoT systems has become more prosperous. Specially, more and more medical images produced by industrial and intelligent devices are outsourced to the cloud for convenient use. However, IoT systems deployment poses several medical data security challenges. To address this issue, in this article, a robust medical data hiding scheme based on secure hybrid optimization for industrial scenario image is presented. Specifically, the marked image is obtained through non-subsampled shearlet transform-multiresolution singular value decomposition. In order to generate the dual marks, we employ the Fisher–Yates permutation to produce the scrambled system watermark address for embedding into the mark image. Afterward, the generated mark image is embedded in the chosen coefficients of the cover in an invisible way. After the watermarking, a hybrid optimization-based encryption scheme is utilized to secure the marked image. Extensive experiments demonstrate the invisibility, security, and robustness of our scheme. Further, the superiority of the scheme is elaborated through making the comparison with the other similar algorithms. The solution not only performs the robust exchange of medical data but also protects the privacy of patients.

Inferential modeling has been of significance for modern manufacturing in estimating the quality-related process variables. As an effective inferential model, probabilistic slow feature analysis (PSFA) has gained attention in regression tasks to interpret dynamic properties with a slowness preference. However, PSFA is often challenged by the nonlinear sequential data due to its linear state-space structure. In this article, a new nonlinear extension of PSFA is proposed under the deep learning framework to enhance the dynamic feature extraction with limited labels, incorporating variational inference and Monte Carlo inference to derive the objective function. The proposed model considers the relevance of inputs with outputs as the input weights to upgrade prediction performance. The proposed model is verified through an industrial hydrocracking process to predict diesel yield with missing labels ranged from 0% to 50%, and the root mean squared error is reduced by at least 8.78% compared to PSFA.

Human activity recognition (HAR) applications have received much attention due to their necessary implementations in various domains, including Industry 5.0 applications such as smart homes, e-health, and various Internet of Things applications. Deep learning (DL) techniques have shown impressive performance in different classification tasks, including HAR. Accordingly, in this article, we develop a comprehensive HAR system based on a novel DL architecture called Multi-ResAtt (multilevel residual network with attention). This model incorporates initial blocks and residual modules aligned in parallel. Multi-ResAtt learns data representations on the inertial measurement units level. Multi-ResAtt integrates a recurrent neural network with attention to extract time-series features and perform activity recognition. We consider complex human activities collected from wearable sensors to evaluate the Multi-ResAtt using three public datasets, Opportunity; UniMiB-SHAR; and PAMAP2. Additionally, we compared the proposed Multi-ResAtt to several DL models and existing HAR systems, and it achieved significant performance.

Vision-based location of industrial chips is crucial for high-speed and high-precision mounting in surface mount technology (SMT) applications. The conventional general location method requires numerous details of the chips’ physical characteristics, making it unsuitable for unknown chip locations and offline learning. In this article, we propose a general chip detection algorithm based on subpixel features from accelerated segment test (FAST) points that offers strong applicability, high precision, and high speed. The core part of our method is the extraction of subpixel boundary FAST points. The conventional subpixel calculation method uses a single-edge model that results in large deviations between calculated and actual positions when applied to actual FAST points. We propose a dual-edge subpixel model containing two groups of edges to reduce this error. Compared with the iterative calculation method in OpenCV, this method has a closing solution and faster performance. We determine model parameters using spatial moments, and present the relationship between the model and subpixel positions. Our experiments on the SMT hardware platform demonstrate that our method is robust to noise, illumination, position, and chip type, and is faster, more accurate, and more reliable than the Hanwha SM481-Plus placement machine and point registration method.

The inverse calculation of burden distribution matrix (BDM) is one of the most important challenges in the blast furnace operation in iron-making processes. In general, blast furnace consumes 65% of the total energy for the whole steel-making. Focusing on this practical challenge, this article proposes a new burden distribution spatial model in calculating burden charging process, and develops a B-spline approximation-based probability density function (PDF) control algorithm to assign the expected thickness distribution of burden layer and, thus, develops a new method for the required inverse calculation of BDM. First, a novel method for the thickness distribution of burden layer is given using B-spline model to produce an expected distribution shape subjected to a desired tracking within a specific spatial constraint. Then, according to the coexistence of continuous and bounded discrete variables in BDM, a novel hybrid optimization control method by combining integer programming and PDF tracking is further established for the effective inverse calculation of BDM. Finally, the proposed PDF-based iterative inverse calculation of BDM using B-spline models are tested using various data from industrial examples. The simulation results show that the proposed method is well suited to solve the BDM inverse calculation problem in practice.

The anomaly detection in photovoltaic (PV) cell electroluminescence (EL) image is of great significance for the vision-based fault diagnosis. Many researchers are committed to solving this problem, but a large-scale open-world dataset is required to validate their novel ideas. We build a PV EL Anomaly Detection (PVEL-AD^{1, 2, 3}) dataset for polycrystalline solar cell, which contains 36 543 near-infrared images with various internal defects and heterogeneous background. This dataset contains anomaly free images and anomalous images with ten different categories. Moreover, 37 380 ground truth bounding boxes are provided for eight types of defects. We also carry out a comprehensive evaluation of the state-of-the-art object detection methods based on deep learning. The evaluation results on this dataset provide the initial benchmark, which is convenient for follow-up researchers to conduct experimental comparisons. To the best of our knowledge, this is the first public dataset for PV solar cell anomaly detection that provides box-wise ground truth. Furthermore, this dataset can also be used for the evaluation of many computer vision tasks such as few-shot detection, one-class classification, and anomaly generation.

Owing to network function virtualization (NFV), each industrial application is constructed as a service function chain (SFC), concatenating the ordered service functions, to offer applications more flexibly in industrial Internet of Things (IIoT). When it comes to the emerging edge intelligence, the integration of NFV with edge in IIoT would enable more close-proximity services, yet also posing new challenges owing to more complicated environment. Although some efforts have been made to service function chaining in IIoT, the radio resource dynamics are not fully perceived. In this article, we investigate the radio-aware SFC deployment in the edge-enabled IIoT. First, a radio-aware deployment formulation is exhibited, steering the flow traversing both wireless and wired links. Next, Markov decision process is exhibited to track dynamics in both IIoT and radio resources. Afterwards, the natural gradient-based actor-critic SFC paradigm is introduced to adapt to network variation, by incorporating the curvature of parameter space into gradient information. To resolve the high-dimensionality in action space, we then recur to the norm penalty approach, reducing the space size by two orders of magnitude. Finally, numerical experiments are executed to uncover superiority of presented method, disclosing that the latency performance benefits from both the SFC routing between IIoT servers and elaborated wireless resource orchestration.