Numerical simulation of coal particle motion characteristics in the envelope region of spiral drum based on discrete element method.

In order to study the movement characteristics of coal particles in the coal loading process of spiral drums, the spiral drum of a certain type of shearer was taken as the research object, and the intrinsic parameters of the materials were calibrated through the determination results of coal sample properties, the relevant parameters of coal particle adhesion were determined, and a discrete element model of spiral drum coal loading was established. The distribution of coal particle movement subsequent to the fracture of the coal wall was derived through simulation. By spatially dividing the envelope region of the spiral drum along the radial and axial directions, the number and velocity distribution of coal particles in different envelope regions were obtained.

Nonlinear Dynamic Soft Sensor Development with a Supervised Hybrid CNN-LSTM Network for Industrial Processes.

A soft sensor is a key component when a real-time measurement is unavailable for industrial processes. Recently, soft sensor models based on deep-learning techniques have been successfully applied to complex industrial processes with nonlinear and dynamic characteristics. However, the conventional deep-learning-based methods cannot guarantee that the quality-relevant features are included in the hidden states when the modeling samples are limited.

Integrated analysis of lncRNA, miRNA and mRNA profiles reveals potential lncRNA functions during early HIV infection.

Background: Long noncoding RNAs (lncRNAs) can regulate gene expression in a cis-regulatory fashion or as "microRNA sponges". However, the expression and functions of lncRNAs during early human immunodeficiency virus (HIV) infection (EHI) remain unclear.

Methods: 3 HAART-naive EHI patients and 3 healthy controls (HCs) were recruited in this study to perform RNA sequencing and microRNA (miRNA) sequencing.

A neural-network-based hysteresis model for piezoelectric actuators.

In this paper, a new neural network based hysteresis model is presented. First of all, a variable-order hysteretic operator (VOHO) is proposed via the characteristics of the motion point trajectory. Based on the VOHO, a basic hysteresis model (BHM) is constructed.

Adaptive Neural Network Dynamic Surface Control for a Class of Time-Delay Nonlinear Systems With Hysteresis Inputs and Dynamic Uncertainties.

In this paper, an adaptive neural network (NN) dynamic surface control is proposed for a class of time-delay nonlinear systems with dynamic uncertainties and unknown hysteresis. The main advantages of the developed scheme are: 1) NNs are utilized to approximately describe nonlinearities and unknown dynamics of the nonlinear time-delay systems, making it possible to deal with unknown nonlinear uncertain systems and pursue the L∞ performance of the tracking error; 2) using the finite covering lemma together with the NNs approximators, the Krasovskii function is abandoned, which paves the way for obtaining the L∞ performance of the tracking error; 3) by introducing an initializing technique, the L∞ performance of the tracking error can be achieved; 4) using a generalized Prandtl-Ishlinskii (PI) model, the limitation of the traditional PI hysteresis model is overcome; and 5) by applying the Young's inequalities to deal with the weight vector of the NNs, the updated laws are needed only at the last controller design step with only two parameters being estimated, which reduces the computational burden. It is proved that the proposed scheme can guarantee semiglobal stability of the closed-loop system and achieves the L∞ performance of the tracking error.