Remaining useful life (RUL) prediction for condition-based maintenance decision making plays a key role in prognostics and health management (PHM). Accurately predicting RUL of the rotating components of complex machines becomes a challenging task for PHM. For many existing methods, the current prediction error of RUL prediction may be accumulated into the future predictions, and thus can lead to a prediction error superposition problem. In this article, the formation mechanism of prediction error superposition is analyzed, and for the first time a deep adversarial long short-term memory (LSTM) prognostic framework is proposed to overcome the major issue related to prediction error superposition. In the proposed framework, a generative adversarial network (GAN) architecture combining the LSTM network and autoencoder (AE) is investigated for bearing RUL monitoring. In the proposed deep adversarial learning prediction framework, due to the potential involvement of long-term and complex tasks, the LSTM network (generator) is used to predict the degradation process of rolling bearings based on available historical data, and a simple but useful AE (discriminator) is used to determine and refine the accuracy of the prediction. Therefore, the AE plays the adversarial role of the LSTM network, and the prediction accuracy of the LSTM network can be significantly improved. For illustration purpose, two practical case studies, which use a series of bearing degradation data and the IEEE PHM 2012 PRONOSTIA datasets, respectively, are presented to show the prediction performance of the proposed method. Experimental results show that the proposed method works very well for vibration monitoring and performs better in comparison with the reference machine learning and deep learning approaches. Impact Statement—The damage of rolling bearing usually leads to a significant consequence to industrial production process. However, the existing remaining useful life (RUL) prediction methods for rolling bearing have a prediction error superposition problem that can affect the multistep prediction performance. The new adversarial learning prognostics model proposed in this article can overcome the problem. The proposed method uses LSTM network as a generator to predict RUL life for rolling bearing, and uses AE as a discriminator to estimate the prediction accuracy. The method can significantly improve the multistep prediction accuracy of RUL for rolling bearing, and provides reliable and scientific strategy in PHM of mechatronics equipment.

As a core tool, anomaly detection based on a generative adversarial network (GAN) is showing its powerful potential in protecting the safe and stable operation of industrial control systems (ICS) under the Internet of Things (IoT). However, due to the long-tailed distribution of operating data in ICS, existing GAN-based anomaly detection models are prone to misjudging an unseen marginal sample as an outlier. Moreover, it is difficult to collect abnormal samples from ICS. To solve these challenges, a dual auto-encoder GAN-based anomaly detection model is proposed for the industrial control system, simply called the DAGAN model, to achieve an accurate and efficient anomaly detection without any abnormal sample. First, an “encoder–decoder–encoder” architecture is used to build a dual GAN model for learning the latent data distribution without any anomalous sample. Then, a parameter-free dynamic strategy is proposed to robustly and accurately learn the marginal distribution of the training data through dynamic interaction between two GANs. Finally, based on the learned normal distribution and marginal distribution, an optimized anomaly score is used to measure whether a sample is an outlier, thereby reducing the probability of a marginal sample being misjudged. Extensive experiments on multiple datasets demonstrate the advantages of our DAGAN model.

Regarding the issue of high dependency on odometry in the adaptive Monte Carlo localization (AMCL) algorithm, an improved AMCL algorithm based on the normal distributions transform (NDT) and extended Kalman filter (EKF) is proposed. A virtual motion model is introduced into the AMCL framework to enable pose updates even when the robot has not moved. NDT is used for point cloud matching to estimate virtual displacement and calculate virtual control quantities, which are then fed into the motion model to predict and update particle states when the robot has not moved. Additionally, to avoid the negative impacts of encoder errors and wheel slippage on motion state estimation, the EKF algorithm integrates information from the wheel odometer and inertial measurement unit to estimate the robot’s displacement, thereby improving localization accuracy and stability. The performance of the proposed algorithm was experimentally validated in both simulated and real environments and compared with other localization algorithms. Experimental results show that the proposed algorithm can effectively improve localization speed during the cold start phase and enhances localization accuracy and stability throughout the localization process. The proposed method is a potential method for improving the performance of mobile robot localization.

This paper aims to tackle the problem of multiobjective search for swarms of UAVs in unknown complex environments and proposes a multiobjective coordinated search algorithm based on a 3D-simplified virtual forced model (MOCS-3D-SVFM). First, it decomposes the search behaviour into the roaming search state and coordinated search state based on the detection of target signals by a swarm of UAVs. Second, a nearest neighbour exclusion diffusion (NNED) algorithm is introduced for the UAV of the wander search state, and a 3D adaptive inertia weight extended particle swarm algorithm (IAEPSO) is proposed by combining the motion characteristics of UAV with a 3D particle swarm algorithm aiming at the UAV with coordinated search state. Finally, the 3D-simplified virtual force model proposed based on the concept of the 2D-simplified virtual force model by the rotation matrix is introduced to solve the model parameters and the control strategy under the UAV of wander search state and coordinated search state is established, which effectively solves the real-time obstacle avoidance problem. Moreover, this paper sets the comparison mode of the three search methods; compared to Mode1, the search time T and energy consumption S can be significantly reduced, and the numerical simulations verify its effectiveness.

This study presents a novel cooperative bird-driving strategy utilizing unmanned aerial vehicles (UAV) swarms, specifically designed for airport environments, to mitigate the risks posed by bird interference with aircraft operations. Our approach introduces a target trajectory prediction framework that integrates Long Short-Term Memory (LSTM) networks with Kalman Filter algorithms (KF), improves the response speed of UAV swarms in bird-driving tasks, optimizes task allocation, and improves the accuracy and precision of trajectory prediction, making the entire bird-driving process more efficient and accurate. Within this framework, UAV swarms collaborate to drive birds that encroach upon designated protected areas, thereby optimizing bird-driving operations. We present a distributed collaborative bird-driving strategy to ensure effective coordination among UAV swarm members. Simulation experiments demonstrate that our strategy effectively drives dynamically changing targets, preventing them from remaining within the protected area. The proposed solution integrates dynamic target trajectory prediction using LSTM and Kalman Filter, task assignment optimization through the Hungarian algorithm, and 3D Dubins path planning. This innovative approach not only improves the operational efficiency of bird-driving in airport environments but also highlights the potential of UAV swarms to perform airborne missions in complex scenarios. Our work makes a significant contribution to the field of UAV swarm collaboration and provides practical insights for real-world applications.