Machine Tool Parameter Proposal Using Historic Data and Operator Feedback

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for determining operational parameters for machine tools are inflexible and not adaptable to varying application scenarios, leading to reduced performance when applied to new or unknown manufacturing scenarios.

Innovation Solution

An interactive proposal system that combines human and machine intelligence to determine operational parameters, utilizing a parameter determination unit that analyzes historic data and operator inputs to adapt to diverse job requirements, with features like probabilistic analysis and artificial neural networks to enhance flexibility and precision.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If known methods and systems are used for determining operational parameters, then performance is acceptable in specific application scenarios, but flexibility and adaptability to new or unknown manufacturing scenarios are reduced

Engineering Contradiction:
ImproveperformanceVSAvoidflexibility and adaptability
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system dynamically adapts to different application scenarios by learning from historic data and operator interactions. The parameter determination unit evolves its decision-making capabilities through machine learning algorithms that process historic job descriptions, operational parameters, and operator corrections, enabling the system to maintain high performance across varying manufacturing scenarios rather than being static and scenario-specific

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system incorporates feedback loops where operator ratings and corrections of determined parameters are fed back into the learning mechanism. This feedback enables the system to continuously improve its adaptability by learning from human expertise and actual operational outcomes, resolving the contradiction between maintaining reliable performance and adapting to new scenarios

Inventive Principle:
Principle #23Feedback

2Productivity

If a data processing means determines operational parameters alone, then high speed and precision are achieved, but flexibility and adaptability are reduced

Engineering Contradiction:
Improvespeed and precisionVSAvoidflexibility and adaptability
Core Design Contradiction:
ProductivityVSAdaptability or versatility

Solution Approach 1:

The system merges the strengths of data processing means (speed and precision in analyzing historic data) with human operator capabilities (flexibility, creativity, and pattern recognition based on experience). The parameter determination unit processes historic data rapidly while operator feedback and corrections introduce adaptability, creating a hybrid system that achieves both high productivity and flexibility

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The machine learning framework acts as an intermediary between raw historic data and operational decision-making. It processes data at high speed with precision while learning from operator feedback to develop adaptive capabilities, serving as a bridge that combines computational efficiency with human-like flexibility in determining operational parameters

Inventive Principle:
Principle #24Intermediary (Mediator)

3Adaptability or versatility

If human operators determine operational parameters alone, then flexibility and adaptability are maintained, but analysis speed and precision with large amounts of data are reduced

Engineering Contradiction:
Improveflexibility and adaptabilityVSAvoidanalysis speed and precision
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The system segments the parameter determination process into distinct functional components: the parameter determination unit handles high-speed data analysis and initial parameter determination using machine learning, while the operator handles feedback, rating, and correction tasks. This segmentation allows each component to operate at its optimal capability level, with the system overall achieving both speed and flexibility

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4231104B1Interactive proposal system for determining a set of operational parameters for a machine tool, control system for a machine tool, machine tool and method for determining a set of operational parameters
Publication Date: 2026.04.01 UNITED MACHINING SOLUTIONS MANAGEMENT AG
  • EP4231104B1 patent drawingFigure 1
  • EP4231104B1 patent drawingFigure 2

AI summary

An interactive proposal system (34) for determining a set (P) of operational parameters for at least one machine tool (10) is described. The proposal system (34) comprises a parameter determination unit (40) which is configured for determining a set (P) of operational parameters for the performance a job according to a job description (J) received via a first communication interface (36). The set (P) of parameters is determined based on the job description (J), at least one historic job description (HJ), a set of historic operational parameters (HP), a historic operator input (HI), a parameter determination history (HD), and a historic result assessment (HA). The determined set (P) of operational parameters may be provided to an operator (28) for review, rating and/or correction. Furthermore, a control system (22) for a machine tool (10) is presented, which comprises such a proposal system (34). Additionally, a corresponding machine tool (10), especially a grinding machine, is explained. Moreover, a method for determining a set (P) of operational parameters for performing a job on at least one machine tool (10) is described.