In order to improve the diagnosis accuracy and solve the weak fault signal of rolling element of rolling bearings due to long transmission path, a novel fault diagnosis method based on variational mode decomposition (VMD) and maximum correlation kurtosis deconvolution (MCKD), namely VMD-MCKD-FD is proposed for rolling elements of rolling bearings in this paper. In the proposed VMD-MCKD-FD, the vibration signal of rolling element of rolling bearings is decomposed into a series of Intrinsic Mode Functions (IMFs) by using VMD method. Then the number of modes with outstanding fault information is determined by Kurtosis criterion in order to calculate the deconvolution period T. The periodic fault component of reconstructed signal is enhanced by using sensitivity MCKD method. Finally, the power spectrum of the reconstructed signal is analyzed in detail in order to obtain the fault frequency and diagnose the rolling element fault of rolling bearings. The simulation signal and actual vibration signal are selected to verify the effectiveness of the VMD-MCKD-FD method. The experimental results show that the VMD-MCKD-FD method can effectively diagnose the rolling element fault of rolling bearings and obtain better fault accuracy.

Rolling Element Fault Diagnosis Based on VMD and Sensitivity MCKD

Unmanned Aerial Vehicles (UAVs) are increasingly being used in many challenging and diversified applications. These applications belong to the civilian and the military fields. To name a few; infrastructure inspection, traffic patrolling, remote sensing, mapping, surveillance, rescuing humans and animals, environment monitoring, and Intelligence, Surveillance, Target Acquisition, and Reconnaissance (ISTAR) operations. However, the use of UAVs in these applications needs a substantial level of autonomy. In other words, UAVs should have the ability to accomplish planned missions in unexpected situations without requiring human intervention. To ensure this level of autonomy, many artificial intelligence algorithms were designed. These algorithms targeted the guidance, navigation, and control (GNC) of UAVs. In this paper, we described the state of the art of one subset of these algorithms: the deep reinforcement learning (DRL) techniques. We made a detailed description of them, and we deduced the current limitations in this area. We noted that most of these DRL methods were designed to ensure stable and smooth UAV navigation by training computer-simulated environments. We realized that further research efforts are needed to address the challenges that restrain their deployment in real-life scenarios.

Drone Deep Reinforcement Learning: A Review

A path planning strategy unified with a COLREGS collision avoidance function based on deep reinforcement learning and artificial potential field

In recent years, methods for detecting motor bearing faults have attracted increasing attention. However, it is very difficult to detect the faults from weak motor bearing signals under the strong noise. Stochastic resonance (SR) is a popular signal processing method, which can process weak signals with the noise, but the traditional SR is burdensome in determining its parameters. Therefore, in this paper, a new advancing coupled multi-stable stochastic resonance method, with two first-order multi-stable stochastic resonance systems, namely CMSR, is proposed to detect motor bearing faults. Firstly, the effects of the output signal-to-noise ratio (SNR) for system parameters and coupling coefficients are analyzed in-depth by numerical simulation technology. Then, the SNR is considered as the fitness function for the seeker optimization algorithm (SOA), which can adaptively optimize and determine the system parameters of the SR by using the subsampling technique. An advancing coupled multi-stable stochastic resonance method is realized, and the pre-processed signal is input into the CMSR to detect the faults of motor bearings by using Fourier transform. The faults of motor bearings are determined according to the output signal. Finally, the actual vibration data of induction motor bearings are used to prove the effectiveness of the proposed CMSR. The comparison results with the MSR show that the CMSR can obtain a higher output SNR, which is more beneficial to extract weak signal features and realize fault detection. At the same time, this method also has practical application value for engineering rotating machinery.

A Novel Advancing Signal Processing Method Based on Coupled Multi-Stable Stochastic Resonance for Fault Detection

Due to rapid development of sensor technology, human activity recognition (HAR) using wearable inertial sensors has recently become a new research hotspot. Deep learning, especially convolutional neural network (CNN) that can automatically learn intricate activity features have gained a lot of attention in ubiquitous HAR task. Most existing CNNs process sensor input by extracting channel-wise features, and the information from each channel can be separately propagated in a hierarchical way from lower layers to higher layers. As a result, they typically overlook information exchange among channels within the same layer. In this article, we first propose a shallow CNN that considers cross-channel communication in HAR scenario, where all channels in the same layer have a comprehensive interaction to capture more discriminative features of sensor input. One channel can communicate with all other channels by graph neural network to remove redundant information accumulated among channels, which is more beneficial for deploying lightweight deep models. Extensive experiments are conducted on multiple benchmark HAR datasets, namely UCI-HAR, OPPORTUNITY, PAMAP2 and UniMib-SHAR, which indicates that the proposed method enables shallower CNNs to aggregate more useful information, and surpasses baseline deep networks and other competitive methods. The inference speed is evaluated via deploying the HAR systems on an embedded system.

Shallow Convolutional Neural Networks for Human Activity Recognition Using Wearable Sensors

Deep reinforcement learning (DRL) has excellent performance in continuous control problems and it is widely used in path planning and other fields. An autonomous path planning model based on DRL is proposed to realize the intelligent path planning of unmanned ships in the unknown environment. The model utilizes the deep deterministic policy gradient (DDPG) algorithm, through the continuous interaction with the environment and the use of historical experience data; the agent learns the optimal action strategy in a simulation environment. The navigation rules and the ship's encounter situation are transformed into a navigation restricted area, so as to achieve the purpose of planned path safety in order to ensure the validity and accuracy of the model. Ship data provided by ship automatic identification system (AIS) are used to train this path planning model. Subsequently, the improved DRL is obtained by combining DDPG with the artificial potential field. Finally, the path planning model is integrated into the electronic chart platform for experiments. Through the establishment of comparative experiments, the results show that the improved model can achieve autonomous path planning, and it has good convergence speed and stability.

An Autonomous Path Planning Model for Unmanned Ships Based on Deep Reinforcement Learning

Path planning is a key issue in the field of coastal ships, and it is also the core foundation of ship intelligent development. In order to better realize the ship path planning in the process of navigation, this paper proposes a coastal ship path planning model based on the optimized deep Q network (DQN) algorithm. The model is mainly composed of environment status information and the DQN algorithm. The environment status information provides training space for the DQN algorithm and is quantified according to the actual navigation environment and international rules for collision avoidance at sea. The DQN algorithm mainly includes four components which are ship state space, action space, action exploration strategy and reward function. The traditional reward function of DQN may lead to the low learning efficiency and convergence speed of the model. This paper optimizes the traditional reward function from three aspects: (a) the potential energy reward of the target point to the ship is set; (b) the reward area is added near the target point; and (c) the danger area is added near the obstacle. Through the above optimized method, the ship can avoid obstacles to reach the target point faster, and the convergence speed of the model is accelerated. The traditional DQN algorithm, A* algorithm, BUG2 algorithm and artificial potential field (APF) algorithm are selected for experimental comparison, and the experimental data are analyzed from the path length, planning time, number of path corners. The experimental results show that the optimized DQN algorithm has better stability and convergence, and greatly reduces the calculation time. It can plan the optimal path in line with the actual navigation rules, and improve the safety, economy and autonomous decision-making ability of ship navigation.

https://www.mdpi.com/2077-1312/9/2/210/pdf

Path Planning of Coastal Ships Based on Optimized DQN Reward Function

In the process of ship collision avoidance decision making, steering collision avoidance is the most frequently adopted collision avoidance method. In order to obtain an effective and reasonable steering angle, this paper proposes a decision-making method for ship collision avoidance based on improved cultural particle swarm. Firstly, the ship steering angle direction is to be determined. In this stage, the Kalman filter is used to predict the ship’s trajectory. According to the prediction parameters, the collision risk index of the ship is calculated and the situation with the most dangerous ship is judged. Then, the steering angle direction of the ship is determined by considering the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs). Secondly, the ship steering angle is to be calculated. In this stage, the cultural particle swarm optimization algorithm is improved by introducing the index of population premature convergence degree to adaptively adjust the inertia weight of the cultural particle swarm so as to avoid the algorithm falling into premature convergence state. The improved cultural particle swarm optimization algorithm is used to find the optimal steering angle within the range of the steering angle direction. Compared with other evolutionary algorithms, the improved cultural particle swarm optimization algorithm has better global convergence. The convergence speed and stability are also significantly improved. Thirdly, the ship steering angle direction decision method in the first stage and the ship steering angle decision method in the second stage are integrated into the electronic chart platform to verify the effectiveness of the decision-making method of ship collision avoidance presented in this paper. Results show that the proposed approach can automatically realize collision avoidance from all other ships and it has an important practical application value.

/pdf/a-decision-making-method-for-ship-collision-avoidance-based-213aermuz1.pdf

A Decision-Making Method for Ship Collision Avoidance Based on Improved Cultural Particle Swarm

In this paper, periodic motions and homoclinic orbits in a discontinuous dynamical system on a single domain with two vector fields are discussed. Constructing periodic motions and homoclinic orbits in discontinuous dynamical systems is very significant in mathematics and engineering applications, and how to construct periodic motions and homoclinic orbits is a central issue in discontinuous dynamical systems. Herein, how to construct periodic motions and homoclinic orbits is presented through studying a simple discontinuous dynamical system on a domain confined by two prescribed energies. The simple discontinuous dynamical system has energy-increasing and energy-decreasing vector fields. Based on the two vector fields and the corresponding switching rules, periodic motions and homoclinic orbits in such a simple discontinuous dynamical system are studied. The analytical conditions of bouncing, grazing, and sliding motions at the two energy boundaries are presented first. Periodic motions and homoclinic orbits in such a discontinuous dynamical system are determined through the specific mapping structures, and the corresponding stability is also presented. Numerical illustrations of periodic motions and homoclinic orbits are given for constructed complex motions. Through this study, using discontinuous dynamical systems, one can construct specific complex motions for engineering applications, and the corresponding mathematical methods and computational strategies can be developed.

Siyu Guo

Papers

An Autonomous Path Planning Model for Unmanned Ships Based on Deep Reinforcement Learning

Path Planning of Coastal Ships Based on Optimized DQN Reward Function

A Decision-Making Method for Ship Collision Avoidance Based on Improved Cultural Particle Swarm

Periodic motions and homoclinic orbits in a discontinuous dynamical system on a single domain with multiple vector fields.

To infinitely many spiral homoclinic orbits from periodic motions in the Lorenz system