Involute gear calibration using tactile CMMs in scanning mode

Stein, Martin; Wedmann, Achim; Jantzen, Stephan; Hierse, Konrad; Kniel, Karin

doi:10.1088/1361-6501/ab7bfe

Cited by 4 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The field of optical inspection methods and specifically laser triangulation measurements has developed immensely as it enables fast data acquisition times [1,2]; however, problems remain concerning the accuracy and the reliability of the measurements [3]. The main advantages over tactile measurements [4] include their contactless measurement and high sampling rate [5][6][7].…”

Section: Introductionmentioning

confidence: 99%

Machine learning method for predicting the influence of scanning parameters on random measurement error

Urbas

Vlah

Vukašinović

2021

Meas. Sci. Technol.

View full text Add to dashboard Cite

Measurements of technical objects can be done with contact and non-contact approaches. Contact methods are accurate but slow. On the other hand, non-contact methods deliver rapid point acquisition and are increasingly being used as their precision mounts. However, multiple scanning parameters such as the incident angle, object colour and scanning distance influence the measurement error and uncertainty when capturing the geometry of the object. With the aim of creating a generalised model that considers the influence of the aforementioned scanning parameters with satisfactory accuracy, a model for predicting the random measurement error based on machine learning (ML) is proposed in this study. Data acquired from measurements with varying scanning distances, incident angles and surface colours were used to train ML models. The tested ML methods included linear regression, support vector machine, neural network, k-nearest neighbour, AdaBoost and random forest. The best-performing trained model was the random forest, with a standard deviation of relative differences of 1.46% for the case of red surfaces, and 5.2% for the case of an arbitrarily coloured surface, which is comparable to results achieved with model-based methods. The trained models and the data are available online.

show abstract