AUTOMATED ROOT CAUSE ANALYSIS OF NON-CONFORMITIES WITH MACHINE LEARNING ALGORITHMS
Journal Title: Journal of Machine Engineering - Year 2018, Vol 18, Issue 4
Abstract
To detect root causes of non-conforming parts - parts outside the tolerance limits - in production processes a high level of expert knowledge is necessary. This results in high costs and a low flexibility in the choice of personnel to perform analyses. In modern production a vast amount of process data is available and machine learning algorithms exist which model processes empirically. Aim of this paper is to introduce a procedure for an automated root cause analysis based on machine learning algorithms to reduce the costs and the necessary expert knowledge. Therefore, a decision tree algorithm is chosen. A procedure for its application in an automated root cause analysis is presented and simulations to prove its applicability are conducted. In this paper influences affecting the success of detection are identified and simulated e.g. the necessary amount of data dependent on the amount of variables, the ratio between categories of non-conformities and OK parts as well as detectable root causes. The simulations are based on a regression model to determine the roughness of drilling holes. They prove the applicability of machine learning algorithms for an automated root cause analysis and indicate which influences have to be considered in real scenarios.<br/><br/>
Authors and Affiliations
Tobias MUELLER, Jonathan GREIPEL, Robert H. SCHMITT
Keywords
Related Articles
- EP ID EP416478
- DOI 10.5604/01.3001.0012.7633
- Views 58
- Downloads 0
INCREASING PRODUCTIVITY OF CUTTING PROCESSES BY REAL-TIME COMPENSATION OF TOOL DEFLECTION DUE TO PROCESS FORCES
The Internet of Production (IoP) describes a vision in which a broad range of different production data is available in real-time. Based on this data, for example, new control types can be implemented, which improve indi...
HYBRID ADDITIVE AND SUBTRACTIVE MANUFACTURING PROCESSES AND SYSTEMS: A REVIEW
This review paper highlights the hybrid manufacturing processes which integrate the additive and subtractive processes performing on one hybrid platform consisting of the LMD (laser metal deposition) unit and CNC machine...
UTILISATION OF IOT AND SENSING FOR MACHINE TOOLS
Strong requirements for automation in the production processes using machine tools have been increasing due to lack of high-skilled machining engineers. Automation used to be utilised in mass production, but it is also n...
Modular intelligent fixture system for flexible clamping of large parts
In this work a modular intelligent fixture system for flexible clamping of large parts is presented. The fixture modules consist of a hybrid material structure involving metal frame elements and mineral casting. These mo...
COMPENSATION OF SYSTEMATIC ERRORS OF DAMAGED PROBE FOR ON-MACHINE MEASUREMENT
Spatial characteristic of triggering radius of the damaged probe for the CNC machine tools has been presented. In such case a clear distortion of the probe performance characteristic and a significant increase in probe e...