Development of a model selection method based on the reliability of a soft sensor model
نویسندگان
چکیده
Soft sensors are widely used to realize highly efficient operation in chemical process because every important variable such as product quality is not measured online. By using soft sensors, such a difficult-to-measure variable y can be estimated by other process variables which are measured online. In order to estimate values of y without degradation of a soft sensor model, a time difference (TD) model was proposed previously. Though a TD model has high predictive ability, the model does not function well when process conditions have never been observed. To cope with this problem, a soft sensor model can be updated with newest data. But updating a model needs time and effort for plant operators. We therefore developed an online monitoring system to judge whether a TD model can predict values of y accurately or an updating model should be used for both reducing maintenance cost and improving predictive accuracy of soft sensors. The monitoring system is based on support vector machine or standard deviation of y-values estimated from various intervals of time difference. We confirmed that the proposed system has functioned successfully through the analysis of real industrial data of a distillation process. Keyword: soft sensor, process control, model selection, time difference, moving window Songklanakarin J. Sci. Technol. 34 (2), 217-221, Mar. Apr. 2012
منابع مشابه
Online Monitoring for Industrial Processes Quality Control Using Time Varying Parameter Model
A novel data-driven soft sensor is designed for online product quality prediction and control performance modification in industrial units. A combined approach of time variable parameter (TVP) model, dynamic auto regressive exogenous variable (DARX) algorithm, nonlinear correlation analysis and criterion-based elimination method is introduced in this work. The soft sensor performance validation...
متن کاملDeveloping a Local Model of Leadership Based on Soft Power in Iran Sport Federations
The aim of this study was to develop a local model of leadership based on soft power in Iran sport federations. This study had a qualitative approach and the method of grounded theory was used as the research methodology. The data were collected by library resources, field observation, audio media and in-depth and open interviews with 23 elite experts. The validity of this study was investigate...
متن کاملAn Aggregated Supplier Selection Method Based on QFD and TOPSIS (Case Study: A Financial Institution)
With daily development of information technology supply chain of service-based organizations like financial institutions and the increased value of outsourced activities, also the importance of customer satisfaction, outsourced affairs must have done by the suppliers who have the ability of accomplishing the organizational demands. To mitigate the risk of invalid supplier selections, verificati...
متن کاملEnergy Efficiency and Reliability in Underwater Wireless Sensor Networks Using Cuckoo Optimizer Algorithm
Energy efficiency and reliability are widely understood to be one of the dominant considerations for Underwater Wireless Sensor Networks (UWSNs). In this paper, in order to maintain energy efficiency and reliability in a UWSN, Cuckoo Optimization Algorithm (COA) is adopted that is a combination of three techniques of geo-routing, multi-path routing, and Duty-Cycle mechanism. In the proposed alg...
متن کاملA New Fault Tolerant Nonlinear Model Predictive Controller Incorporating an UKF-Based Centralized Measurement Fusion Scheme
A new Fault Tolerant Controller (FTC) has been presented in this research by integrating a Fault Detection and Diagnosis (FDD) mechanism in a nonlinear model predictive controller framework. The proposed FDD utilizes a Multi-Sensor Data Fusion (MSDF) methodology to enhance its reliability and estimation accuracy. An augmented state-vector model is developed to incorporate the occurred senso...
متن کاملEnergy-Saving in Wireless Sensor Networks Based on Optimization Sink Movement Control
A sensor network is made up of a large number of sensors with limited energy. Sensors collect environmental data then send them to the sink. Energy efficiency and thereby increasing the lifetime of sensor networks is important. Direct transfer of the data from each node to the central station will increase energy consumption. Previous research has shown that the organization of nodes in cluster...
متن کامل