Granted Patent B2

US 12,315,313 · App. 18/146,856 · Granted May 27, 2025

Inventor: Atsushi Moribe (Kariya, JP)

Assignee: DENSO CORPORATION

G07C5/0808G07C5/0825

Abstract

Claims (46)

1. A factor analysis device for analyzing a system that provides an anomaly factor in a vehicle, comprising:

a model acquisition unit configured to acquire a normal model stored in a memory;

a monitoring target data acquisition unit configured to acquire monitoring target data of each of a plurality of systems disposed in a device;

a distance calculation unit configured to calculate a distance between the normal model and a value based on the monitoring target data for each of the plurality of systems; and

a factor analysis unit configured to:

calculate differences between the distance for each system and distances for remaining systems;

add the differences to obtain a sum of the differences;

create a Pareto chart using the sum of the differences; and

identify, from among the plurality of systems, a system that provides an anomaly factor based on the Pareto chart; and

a display unit configured to display the Pareto chart;

wherein the plurality of systems include at least one of: an ignition control system of the vehicle; a fuel control system of the vehicle; an air measurement system of the vehicle; an air-fuel ratio measurement system of the vehicle; a throttle measurement system of the vehicle; an air control system of the vehicle; and a drive measurement system of the vehicle; and

wherein the factor analysis device analyzes anomaly factors with high accuracy and analyzes with high accuracy which system of the plurality of systems of the device has an anomaly or has a possibility for an occurrence of an anomaly.

2. The factor analysis device according to claim 1 , further comprising:

an anomaly degree calculation unit configured to calculate an overall anomaly degree of the plurality of systems based on a sum of distances of the plurality of systems.

3. The factor analysis device according to claim 2 , wherein:

the factor analysis unit is configured to identify a system having a large contribution of the anomaly degree of each system with respect to the overall anomaly degree calculated by the anomaly degree calculation unit.

4. The factor analysis device according to claim 1 , further comprising:

a state observer generator configured to generate a state observer;

a learning target data acquisition unit configured to acquire learning target data of each of the plurality of systems;

a normal model generator configured to generate the normal model by inputting a value obtained by combining a first state observation value obtained by inputting the learning target data into the state observer and the learning target data into a competitive neural network, wherein:

the value based on the monitoring target data corresponds to a value obtained by combining a second state observation value obtained by inputting the monitoring target data into the state observer and the monitoring target data.

5. The factor analysis device according to claim 1 , further comprising:

one or more processors; and

a memory coupled to the one or more processors and storing program instructions that when executed by the one or more processors cause the one or more processors to provide at least: the model acquisition unit; the monitoring target data acquisition unit; the distance calculation unit; and the factor analysis unit.

6. A factor analysis method for analyzing a system that provides an anomaly factor in a vehicle, comprising:

acquiring a normal model from a memory;

acquiring a monitoring target data for each of a plurality of systems;

calculating a distance between the normal model and a value based on the monitoring target data for each of the plurality of systems;

calculating differences between the distance for each system and distances for remaining systems of the plurality of systems;

adding the differences to obtain a sum of the differences;

creating a Pareto chart using the sum of the differences;

identifying a system that provides an anomaly factor from among the plurality of systems based on the Pareto chart;

displaying the Pareto chart; and

analyzing anomaly factors with high accuracy and analyzing with high accuracy which system of the plurality of systems has an anomaly or has a possibility for an occurrence of an anomaly;

wherein the plurality of systems include at least one of: an ignition control system of the vehicle; a fuel control system of the vehicle; an air measurement system of the vehicle; an air-fuel ratio measurement system of the vehicle; a throttle measurement system of the vehicle; an air control system of the vehicle; and a drive measurement system of the vehicle.

7. A non-transitory computer readable storage medium comprising instructions for execution by a computer for analyzing a system that provides an anomaly factor in a vehicle, the instructions including:

acquiring a normal model from a memory;

acquiring a monitoring target data for each of a plurality of systems;

calculating a distance between the normal model and a value based on the monitoring target data for each of the plurality of systems;

calculating differences between the distance for each system and distances for remaining systems;

adding the differences to obtain a sum of the differences;

creating a Pareto chart using the sum of the differences;

identifying a system that provides an anomaly factor from among the plurality of systems based on the Pareto chart;

displaying the Pareto chart; and

analyzing anomaly factors with high accuracy and analyzing with high accuracy which system of the plurality of systems has an anomaly or has a possibility for an occurrence of an anomaly;

wherein the plurality of systems include at least one of: an ignition control system of the vehicle; a fuel control system of the vehicle; an air measurement system of the vehicle; an air-fuel ratio measurement system of the vehicle; a throttle measurement system of the vehicle; an air control system of the vehicle; and a drive measurement system of the vehicle.

Assignments (1)

Priority Claims (1)

Continuity (2)

References Cited (20)