A device for a vehicle including: a memory configured to store mapping data including machine learning data defining a mapping that uses an estimation variable that is a variable indicating a vehicle operation status of the vehicle and a detection value of a sensor detecting an oil temperature of a power transmission device as input variables, and uses an element corresponding to the input variables as an output variable; and a processor configured to: acquire the input variables; use the mapping to acquire the element as the output variable of the mapping corresponding to the input variables; and determine based on the element whether the detection value becomes equal to or higher than a threshold value due to occurrence of an abnormality in the power transmission device or a mode of vehicle operation by the driver of the vehicle.

An output is calculated using, as an input, a measured value of a pump discharge pressure in a neural network having the pump discharge pressure as the input and a pump rotational speed as the output. A leakage degree of oil of the hydraulic circuit of a transmission is estimated based on a difference obtained by subtracting a measured value of the pump rotational speed from the calculated value of the output. Learning of the neural network is performed using, as teacher data, the measured values of the pump discharge pressure and the pump rotational speed in the transmission in which the leakage degree of oil is within an allowable range.

A device for a vehicle including: a memory configured to store mapping data including machine learning data defining a mapping that uses an estimation variable that is a variable indicating a vehicle operation status of the vehicle and a detection value of a sensor detecting an oil temperature of a power transmission device as input variables, and uses an element corresponding to the input variables as an output variable; and a processor configured to: acquire the input variables; use the mapping to acquire the element as the output variable of the mapping corresponding to the input variables; and determine based on the element whether the detection value becomes equal to or higher than a threshold value due to occurrence of an abnormality in the power transmission device or a mode of vehicle operation by the driver of the vehicle.

An output is calculated using, as an input, a measured value of a pump discharge pressure in a neural network having the pump discharge pressure as the input and a pump rotational speed as the output. A leakage degree of oil of the hydraulic circuit of a transmission is estimated based on a difference obtained by subtracting a measured value of the pump rotational speed from the calculated value of the output. Learning of the neural network is performed using, as teacher data, the measured values of the pump discharge pressure and the pump rotational speed in the transmission in which the leakage degree of oil is within an allowable range.

A method for determining a state of a transmission for a vehicle, including providing an input for a first generative model depending on a route information, a vehicle speed, a probabilistic variable, and an output of a second physical model, and determining an output of the first model characterizing the state in response to the input for the first model. The first model comprises a first layer trained to map input to an intermediate state. The first model comprises a second layer trained to map the intermediate state to the state depending on the output of the second model. The method includes providing an input for the second physical model depending on at least one vehicle state and/or the route information, and determining an output of the second model in response to the input for the second model. The output of the second model characterizes limit(s) for the intermediate state.