公开(公告)号：US20250076249A1

公开(公告)日：2025-03-06

申请号：US18457143

申请日：2023-08-28

Applicant: STMicroelectronics International N.V.

Inventor： Marco Maria Branciforte ,  Fabrizio La Rosa

IPC: G01N27/60 ,  G01N33/24

Abstract: A soil sensor includes a signal generator, and a transmitter coupled to the signal generator, the transmitter configured to transmit a signal from the signal generator, the signal having a fixed frequency, the transmitter including a transmit electrode embedded within a first dielectric material. The soil sensor includes a receiver, the receiver being configured to electrostatically couple to the transmitter through a channel including soil, the receiver including a charge variation (QVAR) electrode embedded within a second dielectric material. The soil sensor includes a charge variation (QVAR) sensor coupled to the QVAR electrode, the QVAR sensor configured to detect a variation in charge detected at the QVAR electrode in response to the signal from the signal generator and output a digital signal including the charge detected. And the soil sensor further includes a processing circuit coupled to the QVAR sensor and configured to determine a level of moisture in the channel based on the digital signal.

公开(公告)号：US20250102593A1

公开(公告)日：2025-03-27

申请号：US18472684

申请日：2023-09-22

Applicant: STMicroelectronics International N.V.

Inventor： Francesco Rundo ,  Michele Calabretta ,  Marco Maria Branciforte ,  Concetto Spampinato ,  Salvatore Coffa

IPC: G01R31/40 ,  G06N3/084

Abstract: A method of characterizing a parameter (e.g., threshold voltage) of a power electronic device using an artificial intelligence (AI) model includes sampling measured parameter values (e.g., voltage, current) of the power electronic device during operation and characterizing the parameter of the power electronic device using the AI model in inference mode with the measured parameter values as inputs. The AI model is trained using a joint loss function including a Jacobian regularization term. The Jacobian regularization term may depend on the norm of at least one Jacobian of a corresponding set of training inputs. A power electronics system configured to perform the method includes the power electronic device and a computing system with a processor and memory storing the AI model. The computing system may be a microcontroller. The system may also include an analog-to-digital converter (ADC) circuit, such as in the microcontroller.