Conveyor Tension Control Using Machine Learning Without Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial machines require a reduction in the number of sensors to lower costs and minimize sensor-related malfunctions, necessitating a method for tension adjustment without relying on tension sensors during operation.
Innovation Solution
A controller utilizing a machine learning device to estimate and adjust conveyor belt tension by learning from data related to the mechanical configuration, workpiece, and operating conditions, eliminating the need for tension sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a tension sensor is used to detect and adjust conveyor belt tension, then tension control precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent replaces the mechanical tension sensor detection system with a machine learning-based estimation system. The machine learning device learns the relationship between motor operation parameters (current, speed, acceleration) and conveyor belt tension, then estimates tension without physical sensors. This substitutes mechanical detection with computational estimation, reducing device complexity while maintaining control precision.
Solution Approach 2:
The patent introduces machine learning processing as an intermediary between motor operation data and tension estimation. Instead of directly measuring tension with a sensor, the system uses machine learning algorithms to process motor parameters and generate tension estimates. This intermediary computational layer enables indirect tension measurement without adding mechanical complexity.
2Reliability
If a tension sensor is installed to monitor conveyor belt tension, then reliability of tension detection is improved, but the number of sensors and potential malfunction points increase
Solution Approach 1:
The patent extracts the tension detection function from the mechanical sensor domain and relocates it to the computational domain. By removing the physical tension sensor and implementing tension estimation through machine learning processing of existing motor data, the system eliminates the sensor while maintaining detection capability. This extraction reduces the quantity of physical components without sacrificing reliability.
Solution Approach 2:
The patent creates a virtual copy of tension information through machine learning estimation rather than using a physical sensor. The machine learning model learns the pattern between motor parameters and tension, then generates estimated tension values that replicate what a sensor would measure. This virtual copying provides reliable tension information without requiring physical sensor hardware.
3Measurement precision
If multiple sensors are used to detect drive status, then measurement accuracy is improved, but cost increases
Solution Approach 1:
The patent makes existing motor operation data serve multiple functions. The same motor current, speed, and acceleration data used for basic motor control are also utilized for tension estimation through machine learning. This multi-functional use of existing data eliminates the need for additional dedicated tension sensors, reducing cost while maintaining measurement accuracy through the learned relationships.
Data Source
AI summary
A controller acquires data related to a mechanical configuration, data related to a workpiece, and data related to an operating condition of an industrial machine, and creates machine learning data used for processing of machine learning based on the acquired data. A command is given to perform processing of machine learning for estimating data related to tension in a conveying section of the industrial machine based on the created machine learning data. Then, processing of machine learning for estimating data related to tension in the conveying section is performed based on this command. In this way, the controller can adjust tension of the conveying section according to a designated condition during actual operation without a tension sensor.