Industrial Internet of Things (IoT) enables distributed intelligent services varying with the dynamic and realtime industrial devices to achieve Industry 4.0 benefits. In this paper, we consider a new architecture of digital twin empowered Industrial IoT where digital twins capture the characteristics of industrial devices to assist federated learning. Noticing that digital twins may bring estimation deviations from the actual value of device state, a trusted based aggregation is proposed in federated learning to alleviate the effects of such deviation. We adaptively adjust the aggregation frequency of federated learning based on Lyapunov dynamic deficit queue and deep reinforcement learning, to improve the learning performance under the resource constraints. To further adapt to the heterogeneity of Industrial IoT, a clustering-based asynchronous federated learning framework is proposed. Numerical results show that the proposed framework is superior to the benchmark in terms of learning accuracy, convergence, and energy saving.

Efficient deadlock control policies are very important in the operation of flexible manufacturing systems (FMS). This work focuses on deadlock control problems for a general class of FMS. They have three interesting characteristics from the application point of view. First, flexible routes of parts and assembly operations are allowed. Second, the number of parts of the same type in a product may be more than one. Third, an operation may require multiple resources. To characterize such FMS, a Petri net model that can well deal with all FMS characteristics is developed. Based on it, this work proposes a Banker's algorithm-like deadlock avoidance policy. The proposed policy is proved to be polynomial in the model size. Moreover, experimental results indicate its effectiveness and superiority over the state-of-the-art policies.

As a key technology of 6G, integrated sensing and communication (ISAC) has attracted much attention, and its security issues are becoming increasingly severe. In this letter, we enhance the physical layer security (PLS) of ISAC systems using rate-splitting multiple access (RSMA). To ensure specific security requirements, we formulate a joint optimization problem that involves the precoding matrix and the common rate. The goal is to maximize the communication-sensing weighted secure sum rate (SSR), thereby enhancing the overall system performance while maintaining security. To solve the non-convex optimization problem, we adopt the staged algorithm named successive convex approximation with penalty (SCA-P) algorithm. Firstly, the original non-convex problem is transformed into a series of more tractable convex problems. Then, penalty terms are introduced to deal with complex constraints. Finally, we gradually approach the optimal solution of the original problem by iteratively solving these convex problems. Simulation results show that the proposed scheme has better security performance than the state-of-the-art schemes.

This article proposes hybrid branch and bound algorithms to minimise the makespan for the two-stage assembly scheduling problem with separated setup times. In the studied problem, there are multiple machines at the first stage, each of which produces a component of a job. When all components are available, a single assembly machine at the second stage completes the job. Existing algorithms are based on the state space search and hence suffer from the state space explosion problem. In order to reduce the search space, lower and upper bounds for a partial schedule are proposed. Also, a heuristic function and a dominance rule are developed to guide the search process. Moreover, accelerated factors are introduced to increase the speed of the search. Experimental results indicate that our algorithms outperform an existing method, and can find the optimal or near-optimal schedules in a short time for all tested problems with up to ten thousand jobs and nine first-stage machines.

The fault detection of turboshaft engines is very important to ensure the flight safety of helicopters. Because there are few fault data in engine historical operation data, engine fault detection is often regarded as an anomaly detection problem, which is solved by the one-class classification (OCC) method. However, previous studies on fault detection usually ignored the difference between engine data caused by different engine states and operating conditions. Therefore, this paper considers the existence of these differences and introduces transfer learning to solve the problem. In this paper, based on one-class support vector machines (OC-SVM) and transfer learning (TL), an algorithm named OC-SVM-TL is proposed to detect turboshaft engine faults. In this algorithm, the hyperplane of the OC-SVM is transferred from the source domain to the target domain as a knowledge structure to help the target domain to establish a fault detection model with high accuracy. The training process is divided into two steps. The first step is to train the OC-SVM model with the data of the source domain, and the second step is to train the OC-SVM model with the data of the target domain, and the hyperplane difference between the source domain and the target domain is considered in the training process. Finally, the fault detection experiment of turboshaft engine was designed, and the fault detection of turboshaft engine was carried out under different working conditions and different engine states. The experimental results showed that the proposed algorithm has good fault detection performance when the target domain data are few or the amount of target domain data changes.