Machine Tool State Detection from Tool Position and Speed Changes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for identifying the operating states of machine tools, such as CNC machines, are complex and require extensive training data and neural networks, making it difficult to efficiently analyze non-productive times and distinguish between different operating states, especially for unambiguous identification of individual sequences and elements within the machine tool.
Innovation Solution
A method that detects the spatially and time-resolved positions and speed changes of tool and tool holder positions using existing sensor data, converting them into series of position and speed changes without requiring complex transformations or neural network training, allowing for real-time determination of operating states and analysis of machining processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If neural networks and extensive training data are used for state identification, then the accuracy of fault state detection is improved, but the device complexity and data requirements increase significantly
Solution Approach 1:
The patent extracts only the essential features needed for state identification from the complex sensor data stream. Instead of using comprehensive neural networks, it selectively extracts position changes and speed changes of the tool holder, which are the critical indicators for distinguishing between machining processes, travel movements, and standstill phases. This extraction principle reduces data complexity while maintaining identification accuracy.
Solution Approach 2:
The patent segments the continuous sensor data into discrete, meaningful phases by analyzing position and speed changes. It divides the operating cycle into distinct segments (machining, travel, standstill) based on threshold comparisons of position change ratios and speed change ratios. This segmentation approach simplifies the analysis by breaking down complex continuous data into manageable discrete states without requiring complex training data.
2Reliability
If complex transformations and neural network training are applied to sensor data, then the reliability of state identification is improved, but the loss of time for data processing and training increases
Solution Approach 1:
The patent implements a self-service approach where the system uses its own operational data (position and speed measurements) to automatically identify and classify its own states without requiring external training or complex processing. The method compares position changes and speed changes against predefined thresholds to autonomously determine whether the machine is in machining, travel, or standstill phase. This self-service mechanism ensures reliable real-time state identification without time-consuming training processes.
3Ease of operation
If manual or estimated recording of non-productive times is used, then the ease of operation is improved, but the measurement precision and completeness of operating state documentation deteriorate
Solution Approach 1:
The patent replaces manual estimation methods with an automated electronic detection system that continuously monitors position and speed data. Instead of relying on operator judgment or simple timers, the system automatically calculates non-productive times by detecting standstill phases through position change ratios and speed change ratios. This substitution of manual mechanical recording with automated sensor-based detection maintains operational simplicity while dramatically improving measurement precision and completeness.
4Productivity
If continuous documentation of all events is implemented, then the productivity through optimized machine utilization is improved, but the device complexity and data processing requirements increase
Solution Approach 1:
The patent extracts only the critical information needed for productivity optimization from the continuous sensor data stream. It focuses specifically on detecting and documenting standstill phases, travel movements, and machining phases by analyzing position and speed changes. This selective extraction of essential operational phases enables continuous documentation without requiring complex processing of all possible sensor data, thereby improving machine utilization efficiency while maintaining system simplicity.
Data Source
AI summary
A machine tool includes a tool and a workpiece machined by the tool, and sensors configured to detect a position of the tool and/or the tool holder holding the tool in a spatially and time resolved manner A method for offline and/or online identification of a state of the machine tool includes: a) detecting or providing positions pi of the tool and/or of the tool holder at a series of points in time i, i=1 . . . n; b) determining for the series of points in time i a series of position changes Δmi according to the formula Δmi=pi/pi-1 and a series of speed changes Δvi according to the formula Δvi=vi/vi-1 withvi=Pi-Pi-1ti-ti-1and formulavi-1=Pi-1-Pi-2ti-1-ti-2;c) identifying the state of the tool, the tool holder, the machine tool and/or the workpiece machined in the machine tool based on the position changes Δmi and the speed changes Δvi.