Improving Machined Surface Shape Prediction by Integrating Multi-Task Learning With Cutting Force Variation Modeling

Abstract

The shapes of machined surfaces play a critical role affecting powertrain performance, and therefore, it is necessary to characterize the shapes with high resolution. State-of-the-art approaches for surface shape characterization are mostly data-driven by interpolating and extrapolating the spatial data but its precision is limited by the density of measurements. This paper explores the new opportunity of improving surface shape prediction through considering the similarity of multiple similar manufacturing processes. It is a common scenario when the process of interest lacks sufficient data whereas rich data could be available from other similar-but-not-identical processes. It is reasonable to transfer the insights gained from other relevant processes into the surface shape prediction. This paper develops an engineering-guided multitask learning (EG-MTL) surface model by fusing surface cutting physics in engineering processes and the spatial data from a number of similar-but-not-identical processes. An iterative multitask Gaussian process learning algorithm is developed to learn the model parameters. Compared with the conventional multitask learning, the proposed method has the advantages in incorporating the insights on cutting force variation during machining and is potentially able to improve the prediction performance given limited measurement data. The methodology is demonstrated based on the data from real-world machining processes in an engine plant.

Enhancing Sustainability and Energy Efficiency in Smart Factories: A Review

“…Data mining is a tool that commonly implements machine learning, statistical methods, visualization or other pattern recognition technologies to find useful features or trends. Since it is successful in discovering potential patterns hidden inside big data, data mining can be used to optimize the operation, improve products quality and other aspects, including fault recognition, quality diagnostic, prediction, and scheduling [75,76]. Different from other techniques, data mining does not require specific data collection processes, and because of development of machine learning, especially deep learning, data mining is playing an increasingly important role in big data analytics for manufacturing.…”

“…Lee et al [81,82] used self-organized maps and fuzzy networks to improve the performance of the quality examination. New machine learning and statistical techniques were proposed to achieve a balance between measurement cost and precision or enhance interpolation accuracy for high-resolution 3D measurement tasks [76,[83][84][85]. Applications include high-precision machining and ultrasonic metal welding.…”

Dynamic Field Monitoring Based on Multitask Learning in Sensor Networks

“…However, the spatial information is seldom considered in such a model. Shao et al adopted a multitask learning model to estimate a 2D-machined surface shape using limited sensor observations from related surface shapes [35]. This model considers the spatial correlation of surface shape and improves the modeling accuracy on the basis of the sensor data of related surface shapes.…”

Spatial Interpolation for Periodic Surfaces in Manufacturing Using a Bessel Additive Variogram Model

“…Fine-scale characterization of surface variation is crucial for high-performance quality control of numerous manufacturing processes, such as ultrasonic metal welding and high-precision machining [1,2]. Such information can enhance manufacturers' understanding on the fundamental mechanism underlying the processes, and further assist the monitoring and control tasks [3].…”

“…Spatial interpolation is one possible solution to acquiring high-resolution surface data with relatively low cost [1,7,8]. When using this type of technique, the value of properties, e.g., surface heights and pixel RGB values, at unobserved locations is estimated with measurement data from its vicinal sampled locations based on spatial models.…”