No abstract

Ensuring product and part quality impacts manufacturing productivity, efficiency and profitability. The goal of every manufacturing company is to quickly identify reduced quality in order to take appropriate measures to improve quality. The use of non-destructive testing methods such as Barkhausen noise in combination with artificial intelligence (AI), which immediately classifies the data, offers a way to implement the desired quality monitoring in a production line. In the present study, the measured data of the Barkhausen signal of surface hardened components with different degrees of tempering were analyzed. For this purpose, suitable AI models were developed and trained with the processed measurement data to generate prediction values for the surface hardness. Data preparation and further processing was carried out using the Spyder development environment with the Python programming language. The following models were applied, tested and optimized during the study: Support vector machine, random forest regression and an artificial neural network. The models were able to predict hardness levels with high accuracy after effective training. Overall, the neural network showed the best results. The applied procedures and methods are fast, non-destructive and provide results with acceptable measurement error, which allows their use in the production environment. Further improvements will be sought in the future, e. g. by applying a larger amount of training data, by changing the features used in the training and by increasing the measurement accuracy when capturing the Barkhausen signal.

The measurement of Barkhausen noise is one of the non-destructive testing methods which allows the use within the production line and within the cycle time at a high production volume. The aim of the present study was to answer the question, whether it is possible to extract the informations that the Barkhausen noise includes, concerning work-piece conditions, from the signal characteristic and more important assigning these findings. Therefore, soft machined and heat treated shaft components made of the ferromagnetic material Cf53 (1.1213) were analyzed to find characteristics in the Signal that allow to separate clearly an increase in temperature of the tested area from a change in the microstructure. For this purpose the shafts were analyzed at higher temperatures (up to 80 °C) and after an additional annealing process (to change the microstructure specifically). Both investigated situations (higher temperature and modified microstructure) showed different characteristic in the Barkhausen signal, thus an assigning is possible. Metallographic investigation and hardness measurements has been carried out to support the results.

Inductive surface hardening falls under the standard heat treatment of automobile drive train components. Wheel hubs, kingpins and various axle shafts will, for instance, be hardened. Two different inductor concepts are generally used for such processes: ring or line inductors. Many geometric boundary conditions must be taken into account when line inductors are used. The adjustment of the hardness transitions of a component includes the length of the inductor and also, for instance, the arrangement of the supply leads. The use of field concentrators will also have a significant effect on the result. This article deals with tests and numerical calculations for a sample component on which these effects were examined.