Search

Purposes Bearing is one of the core components in the manufacturing industry. Its health status determines the safety of the host. Short-term failure prediction can effectively ensure the smooth progress of the industrial production process. Methods In order to solve the end-to-end problem, a temporal convolutional network (TCN) based short-term fault prediction strategy was proposed. The network could directly output the types of failure that would eventually occur in the bearing and the degradation stage that would be in the next moment through the data monitored at the current moment. In addition, soft threshold with attention mechanism is proposed to solve the problem of background noise in the working environment of bearings or noise interference in the process of data acquisition. During the short-term fault prediction process, the attention mechanism adaptively generates a soft threshold according to the prediction target of the TCN network, and the soft threshold acts on the spatiotemporal features extracted by the TCN to achieve the purpose of reducing noise impact. Findings The experimental results show that the proposed algorithm has high accuracy, which verifies the effectiveness and high practical engineering application value of the proposed algorithm.

Purposes In navigation and positioning system, the multipath estimation algorithms based on Kalman filter framework can effectively improve the positioning accuracy. When the initial value of the process noise and observation noise covariance of such algorithms is improperly selected, a large error or even divergence of the estimation results may occur. In addition, because the algorithm is based on the minimum mean squared error criterion, it is susceptible to non-Gaussian noise, especially under heavy-tailed non-Gaussian noise, which has the problem of significant degradation of estimation accuracy. Methods In order to maintain good multipath estimation results under both Gaussian noise and non-Gaussian noise and improve positioning accuracy, an adaptive maximum correntropy unscented Kalman Filter (AMCUKF) multipath estimation algorithm is proposed in this paper. The AMCUKF algorithm introduces the maximum correntropy as an optimization criterion in the process of observation update to solve the problem of estimation accuracy degradation under non-Gaussian noise. In the process of noise covariance update, the residual sequence of the observed quantity is used to recursively update the noise covariance to solve the improper initial value selection of the process noise and the observed noise covariance. Findings Simulation experiments are carried out under Gaussian noise and non-Gaussian noise, and by comparing with two estimation algorithms based on Kalman filter framework, it is shown that AMCUKF multipath algorithm can not only maintain better multipath estimation results under Gaussian noise, but also maintain higher multipath estimation accuracy under non-Gaussian noise, effectively suppressing the interference of non-Gaussian noise.

This paper uses the adaptive dynamic programming (ADP) method to achieve optimal trajectory tracking control for quadrotors. Relying on an established mathematical model of a quadrotor, the approximate optimal trajectory tracking control, which consists of the steady-state control input and the approximate optimal feedback control input, is designed for a nominal system. Considering the compound disturbances in position and attitude dynamic models, disturbance observers are introduced. The estimated values are used to design robust compensation inputs to suppress the effect of the compound disturbances for good trajectory tracking performance. Theoretically, the Lyapunov theorem demonstrates the stability of a closed-loop system. The robustness and effectiveness of the proposed controller are confirmed by the simulation results.

To address the problem of low pose estimation accuracy of traditional filtering algorithm for mobile robots in non-Gaussian noises, a pose estimation algorithm based on the combination of iterative unscented Kalman filter (IUKF) and maximum correntropy (MC), named as MCIUKF, was proposed for the application of simultaneous localization and mapping(SLAM). MC is used to deal with non-Gaussian noise, a cost function based on MC is constructed, and then the Levenberg-Marguardt method (LM) is used to optimize the cost function. On this basis, the iterative updating process of state and covariance is derived, and the updating steps of IUKF are improved. The simulation shows that the proposed algorithm has better estimation accuracy than traditional filtering algorithm in the non-Gaussian noise environments, and has favorable stability.

This paper presents a practical study on how to improve the ℋ∞ performance and meet the input–output constraints of the two-degrees-of-freedom (DOF) flexible-joint manipulator system (FJMS) with parameter uncertainties and external disturbances. For this reason, a robust constrained moving-horizon ℋ∞ controller is designed to improve the system ℋ∞ performance while still satisfying the input–output constraints of the uncertain system. First, the uncertain controlled system model of the two-DOF FJMS is established via the Lagrange equation method, Spong’s assumption, and the linear fractional transformation (LFT) technique. Then, the control requirements and input–output constraints of the uncertain system are transformed into the linear matrix inequality (LMI) via the theory of ℋ∞ control and the full-block multiplier technique. Next, the LMI optimization problem refreshed by the current state is addressed at each sample moment with the idea of the moving-horizon control of the model predictive control (MPC), and the calculated gain is implemented to the nonlinear closed-loop system under the state feedback structure. The validity and feasibility of the designed control scheme is finally verified via the results of simulation experiments.

A prediction method for NOx emission of coal-fired utility boiler based on FAR-HK-ELM was proposed by combining the Fast Attribute Reduction (FAR) and Hybrid Kernel Extreme Learning Machine (HK-ELM) algorithms. First, the main influencing attributes of NOx emission are selected by FAR algorithm, and the redundant information of high-dimensional characteristics is eliminated; Then, HK-ELM based on global polynomial kernel and local gaussian radial basis function is constructed to model NOx emission, and the optimal parameters of the model are obtained through the constrained weight linear decreasing particle swarm optimization algorithm and cross validation. By taking a coal-fired utility boiler operation system as an example, the model was applied to the real operation data for prediction analysis and verification. Compared with BP, SVM, PK-ELM, GK-ELM and HK-ELM models, the proposed method further improves the generalization ability of the model. This study lays a foundation for the combustion optimization of coal-fired utility boiler system.

Nuclear safety has always been a focal point in the field of nuclear applications. Mobile robots carrying specific sensors for nuclear-radiation detection have become an alternative to manual detection. This work presents an autonomous α/β radiation mapping framework, using a mobile robot carrying a light detection and ranging (LiDAR) and a nuclear-radiation-detection sensor. The method employs simultaneous localization and mapping (SLAM) techniques and radiation-detection sensors. Cartographer is adopted as a demonstration example to map the unknown environment. Radiation data are obtained through the radiation detection sensor and projected onto the environment map after coordinate alignment. The color-coded radiation map is shown on the environment map according to the dose rate. The simulation and real-environment experiments in a robot-operating system (ROS) validate the effectiveness of the proposed method in different radiation scenarios for both indoor and outdoor environments.

Abstract Infrared and visible light image fusion technology is a hot spot in the research of multi-sensor fusion technology in recent years. Existing infrared and visible light fusion technologies need to register before fusion because of using two cameras. However, the application effect of the registration technology has yet to be improved. Hence, a novel integrative multi-spectral sensor device is proposed for infrared and visible light fusion, and by using the beam splitter prism, the coaxial light incident from the same lens is projected to the infrared charge coupled device (CCD) and visible light CCD, respectively. In this paper, the imaging mechanism of the proposed sensor device is studied with the process of the signals acquisition and fusion. The simulation experiment, which involves the entire process of the optic system, signal acquisition, and signal fusion, is constructed based on imaging effect model. Additionally, the quality evaluation index is adopted to analyze the simulation result. The experimental results demonstrate that the proposed sensor device is effective and feasible.

In this paper, a generalized correntropy filter-based fault diagnosis (FD) and fault tolerant control (FTC) strategy is proposed for stochastic systems with heavy-tailed distributed noises. In order to deal with the non-Gaussian noises involved in the stochastic systems, a generalized correntropy criterion (GCC) is reviewed first. Then, based on this criterion, an output feedback controller is designed for the healthy stochastic system to make the system output track the set-point as closely as possible. Considering the sensor fault, a GCC filter-based FD method is established, where residuals are used to detect and isolate the sensor fault. Moreover, when the sensor fault is diagnosed, normal signals are used to reconstruct the system so that the system can maintain run normally. Finally, the wind energy conversion system with three types of sensor faults is used to verify the feasibility and efficiency of the proposed FD and FTC method.

Existing key-frame extraction methods are basically video summary oriented; yet the index task of key-frames is ignored. This paper presents a novel key-frame extraction approach which can be available for both video summary and video index. First a dynamic distance separability algorithm is advanced to divide a shot into subshots based on semantic structure, and then appropriate key-frames are extracted in each subshot by SVD decomposition. Finally, three evaluation indicators are proposed to evaluate the performance of the new approach. Experimental results show that the proposed approach achieves good semantic structure for semantics-based video index and meanwhile produces video summary consistent with human perception.