{ "types" : { "Bookmark" : { "pluralLabel" : "Bookmarks" }, "Publication" : { "pluralLabel" : "Publications" }, "GoldStandardPublication" : { "pluralLabel" : "GoldStandardPublications" }, "GoldStandardBookmark" : { "pluralLabel" : "GoldStandardBookmarks" }, "Tag" : { "pluralLabel" : "Tags" }, "User" : { "pluralLabel" : "Users" }, "Group" : { "pluralLabel" : "Groups" }, "Sphere" : { "pluralLabel" : "Spheres" } }, "properties" : { "count" : { "valueType" : "number" }, "date" : { "valueType" : "date" }, "changeDate" : { "valueType" : "date" }, "url" : { "valueType" : "url" }, "id" : { "valueType" : "url" }, "tags" : { "valueType" : "item" }, "user" : { "valueType" : "item" } }, "items" : [ { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/235c7e2feecb203afc29ed828b23bc4ae/michaelhaas", "tags" : [ "Ablation","BayesianOptimization","GaussianProcesses","Laser","MachineLearning","Optimization","Welding","myown" ], "intraHash" : "35c7e2feecb203afc29ed828b23bc4ae", "interHash" : "4ea9784e293ac172887a2bd6105b0af2", "label" : "Advanced laser processing and its optimization with machine learning", "user" : "michaelhaas", "description" : "", "date" : "2026-04-20 16:13:31", "changeDate" : "2026-04-20 16:13:31", "count" : 5, "pub-type": "presentation", "year": "2023", "url": "https://www.spiedigitallibrary.org/conference-proceedings-of-spie/12408/2653604/Advanced-laser-processingand-its-optimizationwith-machine-learning/10.1117/12.2653604.full", "author": [ "Andreas Michalowski","Alexander Ilin","Alexander Kroschel","Stephanie Karg","Peter Stritt","Adina Dais","Sebastian Becker","Gerhard Kunz","Steffen Sonntag","Martin Lustfeld","Petru Tighineanu","Volkher Onuseit","Michael Haas","Thomas Graf","Heiko Ridderbusch" ], "authors": [ {"first" : "Andreas", "last" : "Michalowski"}, {"first" : "Alexander", "last" : "Ilin"}, {"first" : "Alexander", "last" : "Kroschel"}, {"first" : "Stephanie", "last" : "Karg"}, {"first" : "Peter", "last" : "Stritt"}, {"first" : "Adina", "last" : "Dais"}, {"first" : "Sebastian", "last" : "Becker"}, {"first" : "Gerhard", "last" : "Kunz"}, {"first" : "Steffen", "last" : "Sonntag"}, {"first" : "Martin", "last" : "Lustfeld"}, {"first" : "Petru", "last" : "Tighineanu"}, {"first" : "Volkher", "last" : "Onuseit"}, {"first" : "Michael", "last" : "Haas"}, {"first" : "Thomas", "last" : "Graf"}, {"first" : "Heiko", "last" : "Ridderbusch"} ], "editor": [ "Laura Gemini","Aiko Narazaki","Jan Kleinert" ], "editors": [ {"first" : "Laura", "last" : "Gemini"}, {"first" : "Aiko", "last" : "Narazaki"}, {"first" : "Jan", "last" : "Kleinert"} ], "abstract": "The flexibility of new laser sources and process-monitoring enables new possibilities in laser-based production technology, for instance the combination of different laser processes with many adjustable parameters. The fusion of domain knowledge and probabilistic models in the form of hybrid models allows an efficient optimization of these processes with machine learning. This can be a key technology to realize self-learning laser-based universal machines in the future. The article discusses some examples where algorithm-based optimization, partly supported by hybrid models, can already greatly reduce the effort required to find suitable process parameters.", "eventtitle" : "Laser Applications in Microelectronic and Optoelectronic Manufacturing (LAMOM) XXVIII", "bibtexKey": "Michalowski.2023.Advanced" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/28c14d621fac5e000d2c65e9a33485af6/michaelhaas", "tags" : [ "Ablation","BayesianOptimization","GaussianProcesses","Laser","MachineLearning","Optimization","Welding","myown" ], "intraHash" : "8c14d621fac5e000d2c65e9a33485af6", "interHash" : "4ea9784e293ac172887a2bd6105b0af2", "label" : "Advanced laser processing and its optimization with machine learning", "user" : "michaelhaas", "description" : "", "date" : "2026-04-20 16:09:36", "changeDate" : "2026-04-20 16:09:36", "count" : 5, "pub-type": "proceedings", "publisher":"SPIE", "year": "2023", "url": "https://www.spiedigitallibrary.org/conference-proceedings-of-spie/12408/2653604/Advanced-laser-processingand-its-optimizationwith-machine-learning/10.1117/12.2653604.full", "author": [ "Andreas Michalowski","Alexander Ilin","Alexander Kroschel","Stephanie Karg","Peter Stritt","Adina Dais","Sebastian Becker","Gerhard Kunz","Steffen Sonntag","Martin Lustfeld","Petru Tighineanu","Volkher Onuseit","Michael Haas","Thomas Graf","Heiko Ridderbusch" ], "authors": [ {"first" : "Andreas", "last" : "Michalowski"}, {"first" : "Alexander", "last" : "Ilin"}, {"first" : "Alexander", "last" : "Kroschel"}, {"first" : "Stephanie", "last" : "Karg"}, {"first" : "Peter", "last" : "Stritt"}, {"first" : "Adina", "last" : "Dais"}, {"first" : "Sebastian", "last" : "Becker"}, {"first" : "Gerhard", "last" : "Kunz"}, {"first" : "Steffen", "last" : "Sonntag"}, {"first" : "Martin", "last" : "Lustfeld"}, {"first" : "Petru", "last" : "Tighineanu"}, {"first" : "Volkher", "last" : "Onuseit"}, {"first" : "Michael", "last" : "Haas"}, {"first" : "Thomas", "last" : "Graf"}, {"first" : "Heiko", "last" : "Ridderbusch"} ], "editor": [ "Laura Gemini","Aiko Narazaki","Jan Kleinert" ], "editors": [ {"first" : "Laura", "last" : "Gemini"}, {"first" : "Aiko", "last" : "Narazaki"}, {"first" : "Jan", "last" : "Kleinert"} ], "volume": "Laser Applications in Microelectronic and Optoelectronic Manufacturing (LAMOM) XXVIII","abstract": "The flexibility of new laser sources and process-monitoring enables new possibilities in laser-based production technology, for instance the combination of different laser processes with many adjustable parameters. The fusion of domain knowledge and probabilistic models in the form of hybrid models allows an efficient optimization of these processes with machine learning. This can be a key technology to realize self-learning laser-based universal machines in the future. The article discusses some examples where algorithm-based optimization, partly supported by hybrid models, can already greatly reduce the effort required to find suitable process parameters.", "doi" : "10.1117/12.2653604", "bibtexKey": "Michalowski.2023.Advanced" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/21842f79aca312e73b8c33b4e193fd6ca/michaelhaas", "tags" : [ "Ablation","BayesianOptimization","Cutting","DesignOfExperiments","Laser","Welding","myown","peer" ], "intraHash" : "1842f79aca312e73b8c33b4e193fd6ca", "interHash" : "dd9a2ff6d0d49434e0466f2dd16ab815", "label" : "Laser material processing optimization using bayesian optimization: a generic tool", "user" : "michaelhaas", "description" : "", "date" : "2026-04-20 10:38:18", "changeDate" : "2026-04-20 10:38:18", "count" : 4, "pub-type": "article", "journal": "Light: Advanced Manufacturing", "year": "2024", "url": "http://dx.doi.org/10.37188/lam.2024.032", "author": [ "Tobias Menold","Volkher Onuseit","Matthias Buser","Michael Haas","Nico Bär","Andreas Michalowski" ], "authors": [ {"first" : "Tobias", "last" : "Menold"}, {"first" : "Volkher", "last" : "Onuseit"}, {"first" : "Matthias", "last" : "Buser"}, {"first" : "Michael", "last" : "Haas"}, {"first" : "Nico", "last" : "Bär"}, {"first" : "Andreas", "last" : "Michalowski"} ], "volume": "5","number": "3","pages": "32", "issn" : "2831-4093", "doi" : "10.37188/lam.2024.032", "bibtexKey": "Menold.2024.Laser" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/212b1bf1a3f2309bd0a79a04adff1e1ce/michaelhaas", "tags" : [ "Aluminum","BayesianOptimization","Optimization","Welding","X-ray","myown","peer" ], "intraHash" : "12b1bf1a3f2309bd0a79a04adff1e1ce", "interHash" : "8306d0818308eb273c5e8b7e216c83de", "label" : "Efficient parameter selection in laser welding via Bayesian optimization", "user" : "michaelhaas", "description" : "", "date" : "2026-04-10 15:59:18", "changeDate" : "2026-04-10 15:59:18", "count" : 2, "pub-type": "article", "journal": "Journal of Intelligent Manufacturing", "year": "2026", "url": "https://doi.org/10.1007/s10845-026-02799-2", "author": [ "Michael Haas","Robert Steinhoff","John Powell","Felix Zaiß","Johannes Wahl","Christian Hagenlocher","Andreas Michalowski" ], "authors": [ {"first" : "Michael", "last" : "Haas"}, {"first" : "Robert", "last" : "Steinhoff"}, {"first" : "John", "last" : "Powell"}, {"first" : "Felix", "last" : "Zaiß"}, {"first" : "Johannes", "last" : "Wahl"}, {"first" : "Christian", "last" : "Hagenlocher"}, {"first" : "Andreas", "last" : "Michalowski"} ], "abstract": "Identifying suitable process parameters is essential for developing effective laser welding processes. Traditionally, this involves extensive experimentation and relies heavily on expert knowledge. Bayesian optimization can be used to minimize both the experimental effort and the need for expert information. This study demonstrates the merit of Bayesian optimization for laser welding and explains the methodology for implementing the optimization technique. A strategy for selecting evaluation methods and the design of a suitable cost function to meet specific quality criteria is proposed. For the experimental demonstration, butt joint laser welding of AA1050 aluminum alloy was performed with options to adapt the laser power, welding speed, focus position, and the intensity distribution of the laser beam by changing the power distribution in a multi-core fiber. The success of the optimization was validated by finding several parameter sets producing welds that met the defined quality levels. Furthermore, the properties of the underlying surrogate model of the Bayesian optimizer generated further information that helped to improve the welding process.", "issn" : "1572-8145", "doi" : "10.1007/s10845-026-02799-2", "bibtexKey": "Haas.2026.Efficient" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/2155f6c41af538ddfb9505e482c5b03b4/michaelhaas", "tags" : [ "BayesianOptimization","Laser","Welding","X-ray","myown" ], "intraHash" : "155f6c41af538ddfb9505e482c5b03b4", "interHash" : "22e6c5992b446d3c9991215364a70849", "label" : "Improving the weld seam quality in laser welding processes by means of Bayesian optimization", "user" : "michaelhaas", "description" : "", "date" : "2024-09-23 09:27:54", "changeDate" : "2024-09-23 09:27:54", "count" : 5, "pub-type": "presentation", "year": "2024", "url": "", "author": [ "Michael Haas","Volkher Onuseit","John Powell","Felix Zaiß","Johannes Wahl","Tobias Menold","Christian Hagenlocher","Andreas Michalowski" ], "authors": [ {"first" : "Michael", "last" : "Haas"}, {"first" : "Volkher", "last" : "Onuseit"}, {"first" : "John", "last" : "Powell"}, {"first" : "Felix", "last" : "Zaiß"}, {"first" : "Johannes", "last" : "Wahl"}, {"first" : "Tobias", "last" : "Menold"}, {"first" : "Christian", "last" : "Hagenlocher"}, {"first" : "Andreas", "last" : "Michalowski"} ], "abstract": "The determination of appropriate process parameters is crucial for the development of laser welding processes. This usually requires extensive\r\nand time-consuming experimentation combined with expert knowledge. To reduce the number of experiments required to determine appropriate\r\nprocess parameters, Bayesian optimization was used in this work. Bead on plate laser welding of AA5754 samples was performed while\r\noptimizing the laser power, the welding speed, the focus position and the power distribution in the core-ring fiber laser system with the objective\r\nof achieving welds with a specific weld depth and low number of defects at high welding speeds. The welds were evaluated using X-ray imaging\r\nand height measurements. A cost function was developed to quantify the overall weld quality based on the weld properties. It is demonstrated\r\nthat the Bayesian optimizer can determine appropriate process parameters for the given objective, based on a cost function, within a comparatively\r\nsmall number of 29 experiments.", "eventtitle" : "13th CIRP Conference on Photonic Technologies [LANE 2024]", "venue" : "Fürth, Germany", "language" : "English", "eventdate" : "15-19 September 2024", "bibtexKey": "Haas.2024.Improving" } , { "type" : "Publication", "id" : "https://puma.ub.uni-stuttgart.de/bibtex/21f3011175c22622eb1ed4f9624cd89e5/michaelhaas", "tags" : [ "BayesianOptimization","Laser","Welding","X-ray","myown","peer" ], "intraHash" : "1f3011175c22622eb1ed4f9624cd89e5", "interHash" : "22e6c5992b446d3c9991215364a70849", "label" : "Improving the weld seam quality in laser welding processes by means of Bayesian optimization", "user" : "michaelhaas", "description" : "", "date" : "2024-09-23 09:21:21", "changeDate" : "2024-09-23 09:21:21", "count" : 5, "pub-type": "inproceedings", "journal": "Procedia CIRP","publisher":"Elsevier BV", "year": "2024", "url": "http://dx.doi.org/10.1016/j.procir.2024.08.222", "author": [ "Michael Haas","Volkher Onuseit","John Powell","Felix Zaiß","Johannes Wahl","Tobias Menold","Christian Hagenlocher","Andreas Michalowski" ], "authors": [ {"first" : "Michael", "last" : "Haas"}, {"first" : "Volkher", "last" : "Onuseit"}, {"first" : "John", "last" : "Powell"}, {"first" : "Felix", "last" : "Zaiß"}, {"first" : "Johannes", "last" : "Wahl"}, {"first" : "Tobias", "last" : "Menold"}, {"first" : "Christian", "last" : "Hagenlocher"}, {"first" : "Andreas", "last" : "Michalowski"} ], "volume": "124","pages": "772\u2013775","abstract": "The determination of appropriate process parameters is crucial for the development of laser welding processes. This usually requires extensive\r\nand time-consuming experimentation combined with expert knowledge. To reduce the number of experiments required to determine appropriate\r\nprocess parameters, Bayesian optimization was used in this work. Bead on plate laser welding of AA5754 samples was performed while\r\noptimizing the laser power, the welding speed, the focus position and the power distribution in the core-ring fiber laser system with the objective\r\nof achieving welds with a specific weld depth and low number of defects at high welding speeds. The welds were evaluated using X-ray imaging\r\nand height measurements. A cost function was developed to quantify the overall weld quality based on the weld properties. It is demonstrated\r\nthat the Bayesian optimizer can determine appropriate process parameters for the given objective, based on a cost function, within a comparatively\r\nsmall number of 29 experiments.", "issn" : "2212-8271", "doi" : "10.1016/j.procir.2024.08.222", "bibtexKey": "Haas.2024.Improving" } ] }