No 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.

No abstract

Micro-magnetic testing technology is capable of non-destructively evaluating the mechanical properties and residual stress in ferromagnetic components. In the applications of micro-magnetic testing technology, several types of magnetic signals, such as magnetic Barkhausen noise, incremental permeability, tangential magnetic field and eddy current, etc., are used to characterize the target properties (mechanical properties and residual stress). In this paper, a unique framework for multifunctional micro-magnetic sensor design is proposed. Accordingly, a multifunctional micro-magnetic instrument is developed. Intermittently superimposed magnetic fields of high (several kHz) and low frequencies (several Hz) are used for material magnetization. Combined magnetic sensors are employed to measure a total of five types of signals, including the magnetic Barkhausen noise, incremental permeability, eddy currents, tangential magnetic field and main flux. Especially, twisted-pair wiring was used for winding two identical sensing coils. One of the sensing coils is used for eddy current or incremental permeability detection and the rest one acts as a compensatory coil to suppress the strong mutual induction voltage in detection coil. The entire instrument is composed of a multi-channel signal generator, a power amplifier, signal processing circuits embedded into the multifunctional sensor and a four-channel signal acquisition device. The multi-channel signal generator is constructed based on FPGA and high speed D/A converters. The direct digital synthesizer and state machine are programed in FPGA to enable the excitation of intermittently superimposed signals of high and low frequencies. Carefully experiments were performed to test the performances of the developed instrument. The results obtained from different types of steels proved that the developed instrument can acquire five types of magnetic signals with high SNR. The features of the five types of magnetic signals can used to distinguish the material and its mechanical properties such as surface hardness.

BACKGROUND Postoperative pancreatic fistula (PF) is a serious life-threatening complication after pancreaticoduodenectomy (PD). Our research aimed to develop a machine learning (ML)-aided model for PF risk stratification. AIM To develop an ML-aided model for PF risk stratification. METHODS We retrospectively collected 618 patients who underwent PD from two tertiary medical centers between January 2012 and August 2021. We used an ML algorithm to build predictive models, and subject prediction index, that is, decision curve analysis, area under operating characteristic curve (AUC) and clinical impact curve to assess the predictive efficiency of each model. RESULTS A total of 29 variables were used to build the ML predictive model. Among them, the best predictive model was random forest classifier (RFC), the AUC was [0.897, 95% confidence interval (CI): 0.370–1.424], while the AUC of the artificial neural network, eXtreme gradient boosting, support vector machine, and decision tree were between 0.726 (95%CI: 0.191–1.261) and 0.882 (95%CI: 0.321–1.443). CONCLUSION Fluctuating serological inflammatory markers and prognostic nutritional index can be used to predict postoperative PF.