Comparison of algorithms for error prediction in manufacturing with automl and a cost-based metric

In order to manufacture products at low cost, machine learning (ML) is increasingly used in production, especially in high wage countries. Therefore, we introduce our PREFERML AutoML system, which is adapted to the production environment. The system is designed to predict production errors and to help identifying the root cause. It is particularly important to produce results for further investigations that can also be used by quality engineers. Quality engineers are not data science experts and are usually overwhelmed with the settings of an algorithm. Because of this, our system takes over this task and delivers a fully optimized ML model as a result. In this paper, we give a brief overview of what results can be achieved with a state-of-the-art classifier. Moreover, we present the results with optimized tree-based algorithms based on RandomSearchCV and HyperOpt hyperparameter tuning. The algorithms are optimized based on multiple metrics, which we will introduce in the following sections. Based on a cost-oriented metric we can show an improvement for companies to predict the outcome of later product tests. Further, we compare the results from the mentioned optimization approaches and evaluate the needed time for them.

Improvement of Shape Error for Slender Parts in Cylindrical Traverse Grinding by Part-Deformation Modelling and Compensation

Achieving geometrical accuracy in cylindrical traverse grinding for high-aspect slender parts is still a challenge due to the flexibility of the workpiece and, therefore, the resulting shape error. This causes a bottleneck in production due to the number of spark-out strokes that must be programmed to achieve the expected dimensional and geometrical tolerances. This study presents an experimental validation of a shape-error prediction model in which a distributed load, corresponding to the grinding wheel width, is included, and allows inclusion of the effect of steady rests. Headstock and tailstock stiffness must be considered and a procedure to obtain their values is presented. Validation of the model was performed both theoretically (by comparing with FEM results) and experimentally (by comparing with the deformation profile of the real workpiece shape), obtaining differences below 5%. Having determined the shape error by monitoring the normal grinding force, a solution was presented to correct it, based on a cross-motion of the grinding wheel during traverse strokes, thus decreasing non-productive spark-out strokes. Due to its simplicity (based on the shape-error prediction model and normal grinding force monitoring), this was easily automatable. The corrective compensation cycle gave promising results with a decrease of 77% in the shape error of the ground part, and improvement in geometrically measured parameters, such as cylindricity and straightness.

Research on Thermal Error Modeling of Motorized Spindle Based on BP Neural Network Optimized by Beetle Antennae Search Algorithm

High-speed motorized spindle heating will produce thermal error, which is an important factor affecting the machining accuracy of machine tools. The thermal error model of high-speed motorized spindles can compensate for thermal error and improve machining accuracy effectively. In order to confirm the high precision thermal error model, Beetle antennae search algorithm (BAS) is proposed to optimize the thermal error prediction model of motorized spindle based on BP neural network. Through the thermal characteristic experiment, the A02 motorized spindle is used as the research object to obtain the temperature and axial thermal drift data of the motorized spindle at different speeds. Using fuzzy clustering and grey relational analysis to screen temperature-sensitive points. Beetle antennae search algorithm (BAS) is used to optimize the weights and thresholds of the BP neural network. Finally, the BAS-BP thermal error prediction model is established. Compared with BP and GA-BP models, the results show that BAS-BP has higher prediction accuracy than BP and GA-BP models at different speeds. Therefore, the BAS-BP model is suitable for prediction and compensation of spindle thermal error.