Deep Learning–Based Soft Sensors for Improving the Flexibility for Automation of Industry

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Automation in industries offers the benefits of enhancing quality and productivity while minimizing waste and errors, raising safety and adds stability to the production process. Industrial automation offers high profitability, reliability, and safety. It is beneficial to employ machine learning in the field of industrial automation as it helps in monitoring and performing maintenance on industrial machinery. Rational industrial development is closely associated with efforts for automating industrial techniques in all existing ways. Latest improvements in the automation of industrial systems resulted in decrease in cost of energy consumption and hardware. The proposed system is dealt with deep learningbased soft sensors for automation of industrial processes. The eminent benefits of soft sensors are versatility, flexibility, and low cost. With deep learning, many number of features could be processed. Thus, deep learningbased soft sensor encapsulates the above benefits. Soft sensors offer another way for the measurement of process variables, which are measured offline. Deep learning techniques are famous in the design of soft sensors for tough nonlinear systems due to the robustness and accuracy. The work depicted here designs a soft sensor based on deep learning algorithm for automation of industry. In the proposed system, a soft sensor contemplated on deep learning such as the deep neural network (DNN) is presented. The application of deep learningbased soft sensors in the automation of some industrial processes is also discussed here. The proposed system is tested on automatic control on solar power plants and in the measurement of reactive energy in industries. It was found that the proposed system yielded better results with its application in the automated industrial processes.
Funding Information
  • Princess Nourah bint Abdulrahman University Researchers (PNURSP2022R54)

This publication has 12 references indexed in Scilit: