Workpiece Storage Device Sensor Data Machine Learning Loading State
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing workpiece storage systems face challenges in reliably determining the presence and location of workpieces in receptacles due to incorrect sensor signal evaluations, especially with capacitive or inductive sensors, which can lead to inaccurate assessments of the loading state.
Innovation Solution
A workpiece storage device equipped with sensors that transmit data to a control device, which feeds the data into a machine learning model to generate binary output values indicating the loading state, accounting for physical changes in the environment and ambient conditions, and uses multiple sensors and machine learning models to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If capacitive or inductive sensors are used to monitor workpiece presence, then automation and monitoring capability are improved, but measurement precision deteriorates due to physical changes in the sensor environment
Solution Approach 1:
The patent introduces an intermediary evaluation system that processes sensor signals through multiple sensors and machine learning models. This intermediary layer mediates between the raw sensor data and the final loading state assessment, filtering out environmental interference and improving measurement precision while maintaining automation.
Solution Approach 2:
The system implements feedback by continuously monitoring sensor signals and using machine learning models to assess the loading state. The system learns from environmental changes and adjusts its evaluation criteria, providing feedback loops that improve measurement precision over time while maintaining automatic monitoring capability.
2Device complexity
If simple sensor evaluation is used, then device complexity is reduced, but reliability deteriorates due to incorrect assessment of loading state
Solution Approach 1:
The patent segments the sensor evaluation system into multiple independent sensors and separate machine learning models for different loading state assessments. This segmentation allows each component to specialize in specific aspects of detection, improving overall reliability while managing complexity through modular architecture.
Solution Approach 2:
The machine learning models serve multiple functions: they evaluate sensor signals, determine loading states, and adapt to environmental changes. This multi-functionality improves reliability by using the same robust evaluation framework for various assessment tasks, reducing the need for separate complex systems.
3Device complexity
If environmental changes are not compensated, then device complexity is reduced, but measurement precision deteriorates due to physical changes in sensor environment
Solution Approach 1:
The patent uses parameter changes by training machine learning models with varying environmental conditions as input parameters. The models learn to distinguish between environmental parameter changes and actual loading state changes, improving measurement precision without requiring complex physical compensation mechanisms.
Solution Approach 2:
The system replaces mechanical or physical environmental compensation mechanisms with a data-driven machine learning approach. Instead of using complex mechanical systems to isolate sensors from environmental changes, the patent substitutes this with software-based evaluation that learns to filter environmental interference from sensor signals.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system provides a reliable assessment of the loading state by accurately determining the presence and location of workpieces, reducing errors caused by environmental changes and improving safety by distinguishing between intended and similar workpieces.
Implementation Method 1
the use of capacitive or inductive sensors, since the sensor data output by the sensors depend on physical changes in their environment
Implementation Method 2
the use of capacitive or inductive sensors, since the sensor data output by the sensors depend on physical changes in their environment
Data Source
AI summary
Workpiece storage device having at least one sensor; a control device; and pick-up device with receptacles individually adapted to shapes of workpieces to be received in the receptacles. The at least one sensor is configured to acquire sensor data to determine the presence and/or location of workpieces in the receptacles, and to transmit the sensor data to the control device. The control device is configured to receive the sensor data of the sensor and to feed the received sensor data as input values to at least one machine learning model, and the machine learning model is trained to calculate at least one binary output value from the input values. The at least one binary output value is indicative of whether a statement about a loading state of the pick-up device is applicable, and the control device is configured to generate a signal including the at least one binary output value.