Web Break Position Prediction in Paper Machine Roller Lines
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial installations that produce or process fibrous material webs, such as paper-making machines, experience frequent web breaks, leading to costly downtime, and existing methods lack efficiency in predicting and determining the exact position of these breaks.
Innovation Solution
A method and apparatus that utilize sensors and learning-capable algorithms to monitor parameters like rotary speed and torque of rollers, identifying deviations from normal distributions to predict and determine the position of imminent or occurred web breaks, by checking for first and second deviations and associating them with specific rollers, thereby reducing downtime.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If web breaks are prevented or detected early, then downtime is reduced, but measurement precision and detection complexity increase
Solution Approach 1:
The system segments the web break detection problem into multiple monitoring zones along the fibrous material web path, with sensors positioned at different locations to detect breaks at various stages. This segmentation allows earlier detection without requiring a single highly precise measurement point, thus reducing downtime while managing detection complexity.
Solution Approach 2:
The system performs preliminary detection of web breaks before they completefully occur or propagate. By monitoring parameters such as tension, speed, and position of the fibrous material web in advance, the system can predict and alert to impending breaks, allowing preventive action before actual breakage occurs, thereby reducing downtime.
2Measurement precision
If multiple parameters are monitored to improve detection accuracy, then web break position determination improves, but device complexity increases
Solution Approach 1:
The system merges multiple sensor types (position sensors, speed sensors, tension sensors) into an integrated monitoring platform that processes data from all sources through a unified algorithm. This consolidation achieves high detection accuracy while managing device complexity by providing a single point of contact for control and data management.
Solution Approach 2:
The control device is designed with multi-functionality, serving as both a data acquisition system, a processing unit for analyzing temporal progressions and distributions, and a communication interface. This universal device reduces overall system complexity by eliminating the need for separate specialized components for each function.
3Reliability
If real-time monitoring of roller parameters is implemented, then web break prediction improves, but energy consumption increases
Solution Approach 1:
The system implements periodic monitoring of roller parameters rather than continuous monitoring. Sensors take measurements at predetermined time intervals or based on roller position milestones, which maintains web break prediction capability while significantly reducing energy consumption compared to continuous real-time monitoring.
Solution Approach 2:
The system uses the existing operational data from roller motors (current, speed, torque) that is already being generated during normal operation. By analyzing this self-generated data without requiring additional active sensors or external energy sources, the system maintains prediction capability while minimizing additional energy consumption.
Data Source
AI summary
A computer program product, an industrial installation in particular a paper-making machine, an apparatus and method for predicting a position of a web break of a fibrous material web that has occurred or is imminent, wherein the method includes capturing parameters, in particular speeds of rollers for transporting the fibrous material web or a web tension thereof, where the parameters are advantageously stored in the form of time series, a self-learning algorithm is used to detect the imminent web break and to determine the position of the web break which is imminent and/or has occurred, where the basis for the detection or the determination is a deviation of the respective parameter, such as from a temporal mean of the respective parameter.