Abstract: In estimation of a future state of a first product (an estimation-target individual), a first estimated extrapolation value is calculated from data on a past side of data relevant to the first product, and a second estimated extrapolation value is calculated from data relevant to a second product (a same-type different-individual of the estimation-target individual) that is different from the first product. A synthesis ratio between the first estimated extrapolation value and the second estimated extrapolation value is decided from data on a present side of the data relevant to the first product, and an estimation value is calculated by performing synthesis between the first estimated extrapolation value and the second estimated extrapolation value based on the decided synthesis ratio.

Abstract: The driver estimation device includes: a collection unit that collects a plurality of pieces of time series driving data of a vehicle in units from one start point to one end point; a calculation unit that calculates a degree of deviation between a plurality of elements each included in a corresponding one of the pieces of time series driving data and each indicating a location; and a labeling unit that attaches a driver label to each of the pieces of time series driving data by clustering the pieces of time series driving data based on the degree of deviation.

Abstract: The cruising range estimation method includes: a collection step of collecting a plurality of fuel consumption learning values corresponding to a plurality of fuel cell electric vehicle from a plurality of fuel cell electric vehicle; a generation step of generating fuel consumption data indicating a temporal change in fuel consumption based on the plurality of fuel learning values; a calculation step of calculating a correction value for correcting the latest fuel consumption learning value based on the latest fuel consumption learning value of one fuel cell electric vehicle and the fuel consumption data when there is a demand from one of the plurality of fuel cell electric vehicle; a transmission step of transmitting the calculated correction value to one fuel cell electric vehicle; and a correction step of correcting the latest fuel consumption learning value using the correction value by the one fuel cell electric vehicle.

Abstract: A system includes a first storage unit configured to store a result of an endurance test actually carried out over a first period under a first use condition as training data, and a first arithmetic unit having a machine learning model configured to perform machine learning using the training data stored in the first storage unit. The machine learning model is configured to estimate a result when the endurance test is carried out under a second use condition. The first use condition is a use condition in which a predetermined operation parameter that influences degradation of the fuel cell system appears with equal frequency over an entire domain of the operation parameter. The second use condition is a use condition in which the operation parameter appears with unequal frequency in at least part of the domain of the operation parameter.

Abstract: An output voltage prediction system for a fuel cell includes: a storage unit that stores a relationship between a logarithm of a cumulative deterioration index amount and an output voltage of the fuel cell when an output current of the fuel cell is within a predetermined current range, the cumulative deterioration index amount being a cumulative amount of a deterioration index amount related to progress of deterioration of the fuel cell; an input data acquisition unit that acquires the cumulative deterioration index amount of the fuel cell as input data; and a prediction unit that converts the input data acquired by the input data acquisition unit into a logarithm and predicts the output voltage of the fuel cell based on the logarithm of the input data and the relationship stored in the storage unit.

Abstract: In estimation of a future state of a first product (an estimation-target individual), a first estimated extrapolation value is calculated from data (data 2) on a past side of data relevant to the first product, and a second estimated extrapolation value is calculated from data (data 1) relevant to a second product (a same-type different-individual of the estimation-target individual) that is different from the first product. A synthesis ratio between the first estimated extrapolation value and the second estimated extrapolation value is decided from data (data 3) on a present side of the data relevant to the first product, and an estimation value is calculated by performing synthesis between the first estimated extrapolation value and the second estimated extrapolation value based on the decided synthesis ratio.

Abstract: A data collection system for inspection includes a communication unit that communicates with a plurality of vehicles, a selection unit that selects a plurality of target vehicles, and a data collection unit that collects the vehicle data of each target vehicle through the communication unit. The selection unit acquires vehicle environment information for each of the vehicles, assign the vehicle environment information to a plurality of classes, and for each class, obtains a frequency that is the number of the vehicles belonging to the class, and select the target vehicles for each class such that, of the classes, a ratio of the number of vehicles to be selected as the target vehicles to the frequency of each class is smaller in a first class having the frequency equal to or higher than a predetermined reference value than in a second class having the frequency less than the reference value.

Abstract: The data recording apparatus includes a model storage configured to store a model generated by use of sample data indicating a measurement value of a sample and a degree of deterioration of the sample at the time when the measurement value is obtained, and a controller configured to acquire target data indicating a measurement value of a target and a degree of deterioration of the target at the time when the measurement value is obtained. The model storage stores a first model generated by use of the sample data relevant to the degree of deterioration of the sample belonging to a first range, and a second model generated by use of the sample data relevant to the degree of deterioration of the sample belonging to a second range partially overlapping with the first range.

Abstract: A collector plate (14) is connected to an output terminal (16). The collector plate (14) is made such that heat capacity per unit area of a neighboring region (14A) thereof, which is near to a portion where the output terminal (16) is connected, is different to the heat capacity per unit area of other regions (14B, 14C). More specifically, the other regions (14B, 14C) are formed such that the heat capacity per unit area thereof is smaller than that of the neighboring region (14A).

Abstract: A collector plate (14) is connected to an output terminal (16). The collector plate (14) is made such that heat capacity per unit area of a neighboring region (14A) thereof, which is near to a portion where the output terminal (16) is connected, is different to the heat capacity per unit area of other regions (14B, 14C). More specifically, the other regions (14B, 14C) are formed such that the heat capacity per unit area thereof is smaller than that of the neighboring region (14A).