# US 2016/0253442 A1 · Model generating device and method

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2016/0253442 A1
- Document ID: US20160253442A1
- Status: Published application
- Kind: A1
- Application number: 15/006,874
- Filed: 2016-01-26
- Published: 2016-09-01
- Earliest claimed: 2015-02-27
- Assignees: Fujitsu Limited
- Applicants: Fujitsu Limited
- Inventors: Yuhei UMEDA
- Web page: https://patentgrep.com/patent/US20160253442A1

## CPC

- G05B 17/02: electric
- G05B 13/04: involving the use of models or simulators
- F02D 41/2438: {Active learning methods}
- F02D 2041/1433: {using a model or simulation of the system}
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- F02D: CONTROLLING COMBUSTION ENGINES (vehicle fittings, acting on a single sub-unit only, for automatically controlling vehicle speed B60K31/00; conjoint control of vehicle sub-units of different type or different function, road vehicle drive control systems for purposes other than the control of a single sub-unit B60W)

## Abstract

A model generating device for generating model data regarding an operation state of a target object to be controlled, includes a memory and a processor coupled to the memory and configured to acquire first measurement data regarding the operation state of the target object under each of a plurality of measurement conditions set in a first sequence, acquire second measurement data regarding the operation state of the target object under each of the plurality of measurement conditions set in a second sequence different from the first sequence, estimate third measurement data indicating the operation state in a case where the target object enters a steady state in each of the plurality of measurement conditions, based on the first measurement data and the second measurement data, generate the model data regarding the operation state of the target object based on the third measurement data, and output the model data.

## Claims

### Claim 1

A model generating device for generating model data regarding an operation state of a target object to be controlled, the model generating device comprising:
a memory; and
a processor coupled to the memory and configured to:
acquire first measurement data regarding the operation state of the target object under each of a plurality of measurement conditions set in a first sequence,
acquire second measurement data regarding the operation state of the target object under each of the plurality of measurement conditions set in a second sequence different from the first sequence,
estimate third measurement data indicating the operation state in a case where the target object enters a steady state in each of the plurality of measurement conditions, based on the first measurement data and the second measurement data,
generate the model data regarding the operation state of the target object based on the third measurement data, and
output the model data.

### Claim 2 (depends on 1)

The model generating device according to claim 1, wherein the second sequence is a reverse sequence of the first sequence.

### Claim 3 (depends on 2)

The model generating device according to claim 2, wherein
the processor is configured to set a first measurement condition lastly in the first sequence,
the first measurement condition is added by doubling a difference between a second measurement condition set to precede the first measurement condition and a third measurement condition set to precede the second measurement condition,
the first measurement condition, the second measurement condition and the third measurement condition are included in the plurality of measurement conditions.

### Claim 4 (depends on 1)

The model generating device according to claim 1, wherein the first measurement data and the second measurement data relate to the operation state before the target object entering the steady state when operated under each of the plurality of measurement conditions.

### Claim 5 (depends on 1)

The model generating device according to claim 1, wherein the processor is configured to estimate the third measurement data using a prediction equation with which the first measurement data acquired in the first sequence and the second measurement data acquired in the second sequence exponentially converge on the steady state identical over time for each of the plurality of measurement conditions.

### Claim 6 (depends on 5)

The model generating device according to claim 5, wherein the processor is configured to estimate the third measurement data by solving an optimization problem for minimizing an error between fourth measurement data predicted from the prediction equation, and the first measurement data and the second measurement data.

### Claim 7

A model generating method for generating model data regarding an operation state of a target object to be controlled, the model generating method comprising:
operating the target object while changing a plurality of measurement conditions set for the target object in a first sequence;
acquiring first measurement data regarding the operation state of the target object under each of the plurality of measurement conditions set in the first sequence;
operating the target object while changing the plurality of measurement conditions in a second sequence different from the first sequence,
acquiring second measurement data regarding the operation state of the target object under each of the plurality of measurement conditions set in the second sequence;
estimating, by a processor, third measurement data indicating the operation state in a case where the target object enters a steady state in each of the plurality of measurement conditions, based on the first measurement data and the second measurement data;
generating the model data regarding the operation state of the target object based on the third measurement data; and
outputting the model data.

### Claim 8 (depends on 7)

The model generating method according to claim 7, wherein the second sequence is a reverse sequence of the first sequence.

### Claim 9 (depends on 8)

The model generating method according to claim 8, further comprising:
setting a first measurement condition lastly in the first sequence, and
wherein the first measurement condition is added by doubling a difference between a second measurement condition set to precede the first measurement condition and a third measurement condition set to precede the second measurement condition, and
the first measurement condition, the second measurement condition and the third measurement condition are included in the plurality of measurement conditions.

### Claim 10 (depends on 7)

The model generating method according to claim 7, wherein the first measurement data and the second measurement data relate to the operation state before the target object entering the steady state when operated under each of the plurality of measurement conditions.

### Claim 11 (depends on 7)

The model generating method according to claim 7, wherein the third measurement data is estimated using a prediction equation with which the first measurement data acquired in the first sequence and the second measurement data acquired in the second sequence exponentially converge on the steady state identical over time for each of the plurality of measurement conditions.

### Claim 12 (depends on 11)

The model generating method according to claim 11, wherein the third measurement data is estimated by solving an optimization problem for minimizing an error between fourth measurement data predicted from the prediction equation, and the first measurement data and the second measurement data.

### Claim 13

A non-transitory computer-readable storage medium storing a model generating program for generating model data regarding an operation state of a target object to be controlled, the model generating program causing a computer to execute a process, the process comprising:
operating the target object while changing a plurality of measurement conditions set for the target object in a first sequence;
acquiring first measurement data regarding the operation state of the target object under each of the plurality of measurement conditions set in the first sequence;
operating the target object while changing the plurality of measurement conditions in a second sequence different from the first sequence,
acquiring second measurement data regarding the operation state of the target object under each of the plurality of measurement conditions set in the second sequence;
estimating, by a processor, third measurement data indicating the operation state in a case where the target object enters a steady state in each of the plurality of measurement conditions, based on the first measurement data and the second measurement data;
generating the model data regarding the operation state of the target object based on the third measurement data; and
outputting the model data.

### Claim 14 (depends on 13)

The non-transitory computer-readable storage medium according to claim 13, wherein the second sequence is a reverse sequence of the first sequence.

### Claim 15 (depends on 14)

The non-transitory computer-readable storage medium according to claim 14, wherein the process further comprising:
setting a first measurement condition lastly in the first sequence, and
wherein the first measurement condition is added by doubling a difference between a second measurement condition set to precede the first measurement condition and a third measurement condition set to precede the second measurement condition, and
the first measurement condition, the second measurement condition and the third measurement condition are included in the plurality of measurement conditions.

### Claim 16 (depends on 13)

The non-transitory computer-readable storage medium according to claim 13, wherein the first measurement data and the second measurement data relate to the operation state before the target object entering the steady state when operated under each of the plurality of measurement conditions.

### Claim 17 (depends on 13)

The non-transitory computer-readable storage medium according to claim 13, wherein the third measurement data is estimated using a prediction equation with which the first measurement data acquired in the first sequence and the second measurement data acquired in the second sequence exponentially converge on the steady state identical over time for each of the plurality of measurement conditions.

### Claim 18 (depends on 17)

The non-transitory computer-readable storage medium according to claim 17, wherein the third measurement data is estimated by solving an optimization problem for minimizing an error between fourth measurement data predicted from the prediction equation, and the first measurement data and the second measurement data.
