Max Schleier

Mr. Max Schleier

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 December 2017 in IEEE Sensors Journal
Verified
Journal Article
Closed access
MSMax Schleier
Max Schleier
BABenedikt Adelmann
Benedikt Adelmann
CECemal Esen
Cemal Esen
Ralf HellmannRalf Hellmann
Ralf Hellmann
We report on an innovative algorithm for an InGaAs and Si photodiode based sensor system to detect incomplete cuts during high-power near infrared fiber laser cutting. Using such dual photodiode based sensor, the thermal radiation from the process zone is measured with the diode current being digitalized with a sampling rate of 20 kHz. The algorithm encompasses a normalization of the measured current, digital filtering and cross-correlation calculation of both filtered diode signals. This sensor approach allows us to successfully detect cut interruptions in a series of more than 100 cuts in stainless steel, mild steel and aluminum of different thicknesses with a type I and type II error of 0 %. The underlying physics of the detection scheme based on the changes of the dynamic melt flow in the cut kerf from a complete cut to an incomplete cut is discussed.

19 January 2021 in Sensors
Verified
Journal Article
Open access
PDF file
BABenedikt Adelmann
Benedikt Adelmann
MSMax Schleier
Max Schleier
Ralf HellmannRalf Hellmann
Ralf Hellmann
In this publication, we use a small convolutional neural network to detect cut interruptions during laser cutting from single images of a high-speed camera. A camera takes images without additional illumination at a resolution of 32 × 64 pixels from cutting steel sheets of varying thicknesses with different laser parameter combinations and classifies them into cuts and cut interruptions. After a short learning period of five epochs on a certain sheet thickness, the images are classified with a low error rate of 0.05%. The use of color images reveals slight advantages with lower error rates over greyscale images, since, during cut interruptions, the image color changes towards blue. A training set on all sheet thicknesses in one network results in tests error rates below 0.1%. This low error rate and the short calculation time of 120 µs on a standard CPU makes the system industrially applicable.

8 April 2022 in Sensors
Verified
Journal Article
Open access
PDF file
MSMax Schleier
Max Schleier
BABenedikt Adelmann
Benedikt Adelmann
CECemal Esen
Cemal Esen
Ralf HellmannRalf Hellmann
Ralf Hellmann
We present an in situ process monitoring approach for remote fiber laser cutting, which is based on evaluating images from a high-speed camera. A specifically designed image processing algorithm allows the distinction between complete and incomplete cuts by analyzing spectral and geometric information of the melt pool from the captured images of the high-speed camera. The camera-based monitoring system itself is fit to a conventional laser deflection unit for use with high-power fiber lasers, with the optical detection path being coaxially aligned to the incident laser. Without external illumination, the radiation of the melt from the process zone is recorded in the visible spectral range from the top view and spatially and temporally resolved. The melt pool size and emitted sparks are evaluated in dependence of machining parameters such as feed rate, cycles, and focus position during cutting electrical sheets.

9 September 2015 in Applied Sciences
Verified
Journal Article
Open access
PDF file
BABenedikt Adelmann
Benedikt Adelmann
MSMax Schleier
Max Schleier
BNBenedikt Neumeier
Benedikt Neumeier
EWEugen Wilmann
Eugen Wilmann
Ralf HellmannRalf Hellmann
Ralf Hellmann
We report on an optical sensor system attached to a 4 kW fiber laser cutting machine to detect cutting interruptions. The sensor records the thermal radiation from the process zone with a modified ring mirror and optical filter arrangement, which is placed between the cutting head and the collimator. The process radiation is sensed by a Si and InGaAs diode combination with the detected signals being digitalized with 20 kHz. To demonstrate the function of the sensor, signals arising during fusion cutting of 1 mm stainless steel and mild steel with and without cutting interruptions are evaluated and typical signatures derived. In the recorded signals the piercing process, the laser switch on and switch off point and waiting period are clearly resolved. To identify the cutting interruption, the signals of both Si and InGaAs diodes are high pass filtered and the signal fluctuation ranges being subsequently calculated. Introducing a correction factor, we identify that only in case of a cutting interruption the fluctuation range of the Si diode exceeds the InGaAs diode. This characteristic signature was successfully used to detect 80 cutting interruptions of 83 incomplete cuts (alpha error 3.6%) and system recorded no cutting interruption from 110 faultless cuts (beta error of 0). This particularly high detection rate in combination with the easy integration of the sensor, highlight its potential for cutting interruption detection in industrial applications.

14 June 2021 in Journal of Laser Applications
Verified
Journal Article
Closed access
PDF file
MSMax Schleier
Max Schleier
BABenedikt Adelmann
Benedikt Adelmann
CECemal Esen
Cemal Esen
UGUwe Glatzel
Uwe Glatzel
RHRalf Hellmann
Ralf Hellmann
The authors report on a monitoring system for fiber laser fusion cutting based on a high-speed camera with spectral sensitivity in the visible spectral range. Without external illumination, the monitoring system is applied to a conventional cutting head with the optical detection path being coaxially aligned to the incident laser. It thus allows for the direct, spatially, and temporally resolved detection of the melt pool area in the cut kerf from the top view. The dependencies of the melt pool geometry on laser machining parameters can hence be evaluated. With different laser powers, feed rates, and assist gas pressures, incomplete cuts are forced in mild steel with sheet thicknesses ranging from 1 to 10 mm. The measured signal characteristics of the images captured from the melt pool are examined in the visible spectral range of the emitted, secondary thermal radiation from the process zone. Based on a specifically developed algorithm applied to the captured images, the authors are able to differentiate between complete and incomplete cuts with a distinguished detection probability of 94%.

1 February 2025 in Journal of Laser Applications
Verified
Journal Article
Open access
MSMax Schleier
Max Schleier
CECemal Esen
Cemal Esen
Ralf HellmannRalf Hellmann
Ralf Hellmann
Incomplete cuts during laser fusion cutting result in a closed kerf, preventing the workpiece from detaching from the sheet and resulting in rework or rejection. We demonstrate the approach of a vision transformer, used for image classification, to detect cut interruption during laser fusion cutting in steel and aluminum. With events impending an incomplete cut in steel, we attempt to predict cut interruption before they even occur. To build a data set for training, cutting experiments are carried out with a 4 kW fiber laser, forcing incomplete cuts by varying the process parameters such as laser power and feed rate. The thermal radiation from the process zone during the cutting process is captured with a size of 256 × 256 px2 at sample rates of 20 × 103 fps. The kerf is recorded with a spectral sensitivity between 400 and 700 nm, without external illumination, which enables the melt to be observed in the range of the visual spectrum. The vision transformer model, which is used for image classification, splits the image into patches, linearly embedded with an added position embedding, and fed to a standard transformer encoder. For training the model, a set of images was labeled for the respective classes of a complete, incomplete, and impending incomplete cut. With the trained model, incomplete cuts in steel and aluminum can then be recognized and impending incomplete cuts in steel can be predicted in advance.