Micromagnetic and Robust Evaluation of Surface Hardness in Cr12MoV Steel Considering Repeatability of the Instrument

Abstract

The combination of multifunctional micromagnetic testing and neural network-based prediction models is a promising way of nondestructive and quantitative measurement of steel surface hardness. Current studies mainly focused on improving the prediction accuracy of intelligent models, but the unavoidable and random uncertainties related to instruments were seldom explored. The robustness of the prediction model considering the repeatability of instruments was seldom discussed. In this work, a self-developed multifunctional micromagnetic instrument was employed to perform the repeatability test with Cr12MoV steel. The repeatability of the instrument in measuring multiple magnetic features under both static and dynamic conditions was evaluated. The magnetic features for establishing the prediction model were selected based on the consideration of both the repeatability of the instrument and the ability of magnetic features in surface hardness evaluation. To improve the robustness of the model in surface hardness prediction, a modelling strategy considering the repeatability of the instrument was proposed. Through removing partial magnetic features with higher mean impact values from input nodes, robust evaluation of surface hardness in Cr12MoV steel was realized with the multifunctional micromagnetic instrument.

Micromagnetic and quantitative prediction of yield strength and tensile strength in DP590 steels based on ReliefF + Clustering feature selection method

“…The whole system is composed of detection circuits encased in the main body of the instrument, a sensor, and a computer for supporting control software. The reliability of the used micro-magnetic testing system had been verified in our previous work [19,21].…”

“…In micromagnetic testing, the physical mechanism is treated as a black box, so it was performed by experimental calibration. Both the reliability and repeatability of the used system had been proved to be good enough for performing micro-magnetic testing [21]. Thus, the data in figure 8 indicate the complex effects of microstructures (such as grain boundary and dislocation) on magnetic domains and their walls.…”

“…Sheng et al [17] and Mirzaee et al [18] employed the generalized regression neural network model and radialbasis function neural networks in model training and successfully realized nondestructive evaluation of mechanical properties of cold-rolled steel strips. We [17,[19][20][21] also proved that the micro-magnetic testing method combined with feedforward neural network (FF-NN) models outperformed the conventional ways in quantitatively predicting the surface hardness, case depth, and stress.…”

Quantitative Prediction of Surface Hardness in Cr12MoV Steel and S136 Steel with Two Magnetic Barkhausen Noise Feature Extraction Methods

“…In micromagnetic detection methods, multiple magnetic signals (magnetic Barkhausen noise, tangential magnetic field (TMF), and magnetic incremental permeability (EIP)) are combined together to characterize the mechanical properties of materials [20,25]. In this paper, a sensor (Figure 1a) was developed to simultaneously detect two types of magnetic signals (TMF and MBN).…”