scholarly journals Hybrid Multiple Soft-Sensor Models of Grinding Granularity Based on Cuckoo Searching Algorithm and Hysteresis Switching Strategy

2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Jie-Sheng Wang ◽  
Na-Na Shen
Keyword(s):  
Neural Network ◽  
Soft Sensor ◽  
Grinding Process ◽  
Real Time Control ◽  
Switching Strategy ◽  
Time Control ◽  
Sensor Model ◽  
Optimum Model ◽  
Set Up ◽  
Sampling Instant

According to the characteristics of grinding process and accuracy requirements of technical indicators, a hybrid multiple soft-sensor modeling method of grinding granularity is proposed based on cuckoo searching (CS) algorithm and hysteresis switching (HS) strategy. Firstly, a mechanism soft-sensor model of grinding granularity is deduced based on the technique characteristics and a lot of experimental data of grinding process. Meanwhile, the BP neural network soft-sensor model and wavelet neural network (WNN) soft-sensor model are set up. Then, the hybrid multiple soft-sensor model based on the hysteresis switching strategy is realized. That is to say, the optimum model is selected as the current predictive model according to the switching performance index at each sampling instant. Finally the cuckoo searching algorithm is adopted to optimize the performance parameters of hysteresis switching strategy. Simulation results show that the proposed model has better generalization results and prediction precision, which can satisfy the real-time control requirements of grinding classification process.

scholarly journals Soft-Sensor Modeling of PVC Polymerizing Process Based on F-GMDH-Type Neural Network Algorithm

2017 ◽  
Vol 2017 ◽  
pp. 1-13 ◽  
Author(s):  
Wei-zhen Sun ◽  
Jie-sheng Wang ◽  
Shu-zhi Gao
Keyword(s):  
Neural Network ◽  
Least Squares Method ◽  
Internal Standard ◽  
Soft Sensor ◽  
Polymerization Process ◽  
Group Method ◽  
Real Time Control ◽  
Time Control ◽  
Sensor Model ◽  
Collinearity Problem

For predicting the conversion velocity of the vinyl chloride monomer (VCM) in the polymerization process of polyvinylchloride (PVC), an improved Group Method of Data Handling- (GMDH-) type neural network soft-sensor model is proposed. After analyzing the technique of PVC manufacturing process, the auxiliary variables for setting up the soft-sensor model are selected and the experimental data are normalized. Because the internal standard of the original GMDH-type neural cannot solve the problem of multiple-collinearity problem and the useful variables tend to be prematurely eliminated in the modeling process, a hybrid method combining the regression analysis method and the least squares method is proposed to solve the multiple-collinearity problem. On the same time, by adopting some optimization experiences in genetic algorithm (GA), the generational crossover combination variables method is proposed to solve the shortcoming of useful variable being eliminated prematurely. The simulation results show that the proposed soft-sensor model can significantly improve the prediction accuracy of economic and technical indicators in the PVC polymerization process and can meet the real time control requirements of polymerization reactor production process.

scholarly journals Improved GSO Optimized ESN Soft-Sensor Model of Flotation Process Based on Multisource Heterogeneous Information Fusion

2014 ◽  
Vol 2014 ◽  
pp. 1-12 ◽  
Author(s):  
Jie-sheng Wang ◽  
Shuang Han ◽  
Na-na Shen
Keyword(s):  
Principal Component ◽  
Texture Features ◽  
Soft Sensor ◽  
Kernel Principal Component Analysis ◽  
Real Time Control ◽  
Inertia Moment ◽  
Flotation Process ◽  
Time Control ◽  
Sensor Model ◽  
Froth Image

For predicting the key technology indicators (concentrate grade and tailings recovery rate) of flotation process, an echo state network (ESN) based fusion soft-sensor model optimized by the improved glowworm swarm optimization (GSO) algorithm is proposed. Firstly, the color feature (saturation and brightness) and texture features (angular second moment, sum entropy, inertia moment, etc.) based on grey-level co-occurrence matrix (GLCM) are adopted to describe the visual characteristics of the flotation froth image. Then the kernel principal component analysis (KPCA) method is used to reduce the dimensionality of the high-dimensional input vector composed by the flotation froth image characteristics and process datum and extracts the nonlinear principal components in order to reduce the ESN dimension and network complex. The ESN soft-sensor model of flotation process is optimized by the GSO algorithm with congestion factor. Simulation results show that the model has better generalization and prediction accuracy to meet the online soft-sensor requirements of the real-time control in the flotation process.

Constant Acceleration Control of Valve-Control-Cylinder System Based on Neural Network

2012 ◽  
Vol 430-432 ◽  
pp. 2041-2045
Author(s):  
Jun Gong Ma ◽  
Xian Yang Shang
Keyword(s):  
Neural Network ◽  
Control System ◽  
Pid Controller ◽  
Mathematic Model ◽  
Neural Element ◽  
Real Time Control ◽  
Time Control ◽  
Set Up ◽  
Valve Control ◽  
Control Cylinder

To solve the serious problem of the nonlinear and Time-varying uncertainty of the valve-control-cylinder system, a control system was designed with neural-proportion-integral-differential (PID) theory. Because of the capacity of neural network, the control system showed adaptive capacity in the system of valve-control-cylinder. In this paper, the basic theory of a single neural element self-adaptive PID controller and a model identifier based on Radial Basis Function were described. The mathematic model of the valve-control-cylinder control system was set up. The simulation results prove that the neural-PID system can regulate the PID parameters dynamically by self-learning so that the system with the neural-PID controller showed quick track performance and capacity against the disturbance. The results also prove the validity and applicability of the system. The algorithm is simple, PID initial parameters are easy to adjust, easy in application of the real-time control the valve-control-cylinder system.

Temperature and conductivity as control parameters for pollution-based real-time control

2006 ◽  
Vol 54 (11-12) ◽  
pp. 257-263 ◽  
Author(s):  
R.P.S. Schilperoort ◽  
G. Gruber ◽  
C.M.L. Flamink ◽  
F.H.L.R. Clemens ◽  
J.H.J.M. van der Graaf
Keyword(s):  
Real Time ◽  
Monitoring Network ◽  
Storm Event ◽  
Real Time Control ◽  
Normal Behaviour ◽  
Time Control ◽  
Wastewater Systems ◽  
Typical Behaviour ◽  
Good Relation ◽  
Set Up

Most sewer system performance indicators are not easily measurable online at high frequencies in wastewater systems, which hampers real-time control with those parameters. Instead of using a constituent of wastewater, an alternative could be to use characteristics of wastewater that are relatively easily measurable in sewer systems and could serve as indicator parameters for the dilution process of wastewater. This paper focuses on the possibility to use the parameters of temperature and conductivity. It shows a good relation of temperature and conductivity with the dilution of DWF (dry weather flow) during WWF (wet weather flow) a monitoring station in Graz, Austria, as an example. The simultaneous monitoring of both parameters leads to valuable back-up information in case one parameter (temperature) shows no reaction to a storm event. However, for various reasons, anomalies occur in the typical behaviour of both parameters. The frequency and extent of these anomalies will determine the usefulness of the proposed parameters in a system for pollution-based real-time control. Both the normal behaviour and the anomalies will be studied further by means of trend and correlation analyses of data to be obtained from a monitoring network for the parameters of interest that is currently being set up in the Netherlands.

Soft sensor model for dynamic processes based on multichannel convolutional neural network

2020 ◽  
Vol 203 ◽  
pp. 104050 ◽  
Author(s):  
Xiaofeng Yuan ◽  
Shuaibin Qi ◽  
Yuri A.W. Shardt ◽  
Yalin Wang ◽  
Chunhua Yang ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Soft Sensor ◽  
Dynamic Processes ◽  
Sensor Model

Neural-Network Based Approach for Real-Time Control of BMEP and MFB50 in a Euro 6 Diesel Engine

2017 ◽  
Author(s):  
Roberto Finesso ◽  
Ezio Spessa ◽  
Yixin Yang ◽  
Giuseppe Conte ◽  
Gennaro Merlino
Keyword(s):  
Neural Network ◽  
Diesel Engine ◽  
Real Time ◽  
Real Time Control ◽  
Time Control
Sign in / Sign up

Export Citation Format

Share Document