EDM Filter Lifetime Prediction Using Pressure Regression

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for predicting the lifetime of dielectric filters in EDM machines require extensive database construction and knowledge of specific machining conditions, material compositions, and physical constants, making them complex and unreliable, especially when the workpiece material is unknown to the manufacturer.

Innovation Solution

A method that uses regression analysis to determine the filter lifetime by measuring and storing filter pressure over time, employing an exponential function to fit the pressure measurements, allowing for continuous prediction of filter lifetime and residual time to replacement without requiring historical data or specific machining condition knowledge.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If existing methods use factor tables and database construction to predict filter lifetime, then prediction accuracy may be improved, but device complexity and ease of manufacture deteriorate due to extensive data collection requirements

Engineering Contradiction:
Improvefilter lifetime prediction accuracyVSAvoiddatabase construction complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The invention extracts only the essential parameter (filter pressure) needed for prediction, eliminating the need for extensive databases containing machining conditions, material compositions, and physical constants. By focusing solely on pressure measurements over time, the method achieves prediction capability without the complexity of comprehensive data collection and factor table construction.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The filter itself provides the prediction information through its own pressure characteristics. By monitoring how filter pressure evolves over time during operation, the system uses the filter's inherent behavior to predict its own remaining lifetime, eliminating the need for external databases or manufacturer-specific characterization data.

Inventive Principle:
Principle #25Self-service

2Measurement precision

If existing methods require knowledge of workpiece material composition and machining conditions, then prediction accuracy may be improved, but adaptability deteriorates when material information is unknown to the manufacturer

Engineering Contradiction:
Improvefilter lifetime prediction accuracyVSAvoidapplicability to unknown materials
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The invention creates a universal prediction method that works across different workpiece materials, machining conditions, and filter types without requiring material-specific calibration. The approach uses only filter pressure measurements, making it applicable to any EDM machine regardless of the manufacturer or material being processed, thereby achieving broad adaptability.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The filter provides its own prediction data through pressure measurements, eliminating the need for external information about workpiece material composition or machining conditions. This self-service approach allows the system to adapt to any material automatically without requiring pre-programmed knowledge or manufacturer-specific data.

Inventive Principle:
Principle #25Self-service

3Ease of operation

If simple pressure monitoring is used to predict filter lifetime, then ease of operation is improved, but measurement precision may deteriorate compared to comprehensive database methods

Engineering Contradiction:
Improveprediction method simplicityVSAvoidfilter lifetime prediction accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The invention uses feedback from continuous filter pressure measurements to dynamically predict remaining filter lifetime. By monitoring the rate of pressure increase over time and comparing it against the maximum allowable pressure, the system achieves accurate prediction while maintaining operational simplicity. The feedback loop continuously updates the prediction based on actual filter behavior.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The invention transforms the simple pressure parameter into a predictive tool by analyzing its temporal evolution. Instead of using a single pressure value, the method examines how pressure changes over time, extracting lifetime information from the pressure trajectory. This parameter transformation maintains ease of operation while achieving prediction accuracy.

Inventive Principle:
Principle #35Parameter changes

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

This approach provides a simple, universal, and reliable method for predicting filter lifetime, improving accuracy and reliability by using logged historical pressure values to estimate the time remaining before filter replacement, regardless of the material being machined, and is robust against incorrect configuration or varying consumable quality.

Implementation Method 1

The pressure transducer is connected with the control unit so that the filter pressure value is constantly monitored

Methodology Applied
Scientific EffectPressure differential measurement: Pressure Drop

Data Source

PatentEP3375556B1Self-learning filter lifetime estimation method
Publication Date: 2023.02.22 AGIE CHARMILLES SA
  • EP3375556B1 patent drawingFigure 1
  • EP3375556B1 patent drawingFigure 2a~4
  • EP3375556B1 patent drawingFigure 5

AI summary

Method for the determination of lifetime of a filter of an electric discharge machine the electrical discharge machine in consideration of a maximum allowable filter pressure, wherein the time measuring unit counts the machining time ts during which an electric discharge machining process is running, a filter pressure sensor measures the filter pressure p(k), preferably with a predetermined sampling interval, the pressure measurement p(k) and the respective sampling time t(k) are stored, and the sampled measurements p(k) and the respective sampling times t(k) are used to determine the parameters of an exponential function which best fits to the plurality of sampled measurements regression analysis. The determined parameters include the filter lifetime tf, which serves to determine the residual time to the filter replacement tr and/or the calendar deadline of filter expiration.