The trend of recent years in all industrial sectors and, above all, in the manufacturing one, is to move towards green policies, whether it is eco-sustainability or pure energy saving. Constant monitoring solutions, advanced diagnostic tools, efficient data storage, processing and consequent intelligent automation allow you to optimize existing processes and obtain flawless products by consuming the least amount of energy possible.
The Distributed Control System
Data analysis and performance monitoring are fundamental and basic parts for the implementation of Industry 4.0 processes. This data driven approach is based on cloud technology and allows production plants to be kept fully operational, with the possibility of monitoring them even remotely.
The starting point is always the Distributed Control System (DCS), a system capable of managing all the automation needs of the plant. The data coming from the various plants will be collected in real time, constantly analyzed and inserted in a historical archive. From here, the data will subsequently be collected and processed by dedicated software for machine learning purposes.
Thanks to a special dashboard, both the on-site operator and the off-site manager will have a clear overview of the data acquired in real time and their expected trend based on the progress of the ongoing process. The DCS, which governs the plant, will constantly provide a high data flow which, once reprocessed, can be compared with ideal values in order to achieve the optimization of production processes.
The five fundamental parameters on which to act
With the aim of saving energy, the macro parameters of a tissue machine we can act on are the following:
1 – Degree of refining, on which we will intervene by setting the related parameters
2 – Stock concentration in the headbox
3 – Vacuum level on the suction press and on the suction boxes
4 – Steam temperature and pressure inside the Yankee Dryer
5 – Temperature of the air emitted by the extractor hood
The main targets that are taken as a reference for the setting of the tissue machine are the daily quantity and the quality of the paper to be produced. Once these two objectives have been defined, the plant can be optimally set in order to obtain the greatest energy savings and maximum efficiency by combining the five variables above, which are able to directly affect the consumption of electricity and fuels.
The benefits of Machine Learning and Predictive Maintenance
Thanks to machine learning, the plant software will be able to pursue the set objectives by modifying the process control strategy, limiting or even eliminating both out-of-specification production and excessive consumption of chemical additives, energy and variable sources. The final result will be greater operational stability and a reduction in waste.
The intelligent controls and assistance provided to the operator in the execution of his tasks will be able to facilitate a series of diagnostic sequences that will result in adaptive setpoints and predictive controls, with scheduled maintenance proposals aimed at minimizing downtime.
A.Celli Industry 4.0 solution
In 2016 the A.Celli Group established its first department entirely dedicated to the development of innovative solutions for the analysis and management of the data of its machines. The business unit, called Extreme Automation, is a start-up specialized in Big Data Analysis, IT infrastructures, Machine Learning and Artificial Intelligence that offers cutting-edge Industry 4.0 solutions capable of bringing significant benefits to tissue paper production plants, such as example:
— Improvement of efficiency and energy saving opportunities
— Product optimization and relative standardization
— Reduction in the number of out-of-specification products
— Reduction of raw material waste
— Reduction of downtimes
— Implementation of predictive maintenance processes
— Constant software updating