# US 10,768,590 B2 · Plant operation support device, plant operation support method, and a program device

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

- Number: US 10,768,590 B2
- Document ID: US10768590B2
- Status: Granted
- Kind: B2
- Application number: 15/176,543
- Filed: 2016-06-08
- Published: 2016-12-15
- Granted: 2020-09-08
- Earliest claimed: 2015-06-11
- Assignees: Yokogawa Electric Corporation
- Applicants: Yokogawa Electric Corporation
- Inventors: Ryosuke Kashiwa; Azusa Takenaka; Toshiaki Omata; Shin Ishimaru; Makoto Nakaya
- Web page: https://patentgrep.com/patent/US10768590B2

## CPC

- G05B 17/02: electric
- 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)

## Abstract

A plant operation support device for simulating an operation of a plant based on information obtained from the plant, includes: an operation condition setting part that sets an operation condition of the plant and a timing for applying the operation condition; and a transient state prediction part that predicts a transient state of the plant from a specific time point to the future in a case in which the operation condition of the plant set by the operation condition setting part is applied at the timing.

## Claims

### Claim 1

A plant operation support device for predicting a concentration of components that determines quality of a product to be produced in a plant by a simulation based on measurement data obtained from a field device arranged in the plant, comprising:
at least one memory storing instructions, and
at least one processor configured to execute the instructions to:
operate in parallel synchronizing with the plant and perform a simulation with obtaining the measurement data from the field device to estimate a state quantity that has not been measured in the plant;
estimate periodically performance parameter of devices used for the estimation of the state quantity based on the measurement data obtained from the field device;
set beforehand a plurality of operation conditions of the plant in a case in which the plant is operated near a limit of a product specification of the product and a plurality of timings for applying each of the plurality of operation conditions, the plurality of operation conditions being setting values relating to control of the plant;
predict, based on the estimated state quantity, a transient state of the plant from a specific time point to a future time point by the simulation in a case in which the plurality of operation conditions set beforehand are applied at the plurality of timings, the specific time point being selectable between a present time and a previous time when a previous transient state prediction is performed, a present operating state being made to be an initial state in a case in which the present time is selected, an operating state used by the previous transient state prediction being made to be an initial state in a case in which the previous time is selected;
set a re-setting value input by a user as at least one of the plurality of operation conditions at a timing input by the user in the middle of one processing of the transient state prediction and continue the one processing of the transient state prediction;
predict, by the simulation based on the estimated state quantity, a stationary state that is a final destination of an operating state of the plant in a case where the plurality of operation conditions set beforehand are applied at the plurality of timings,
generate a trend graph that is made from time series of a prediction result of the concentration in the transient state and the stationary state; and
display the generated trend graph and the limit of the product specification of the product in a screen.

### Claim 2 (depends on 1)

The plant operation support device according to claim 1, wherein the at least one processor is further configured to:
set a time range when the transient state is predicted; and
predict the transient state in the set time range.

### Claim 3 (depends on 1)

The plant operation support device according to claim 1, wherein the at least one processor is further configured to:
set the plurality of operation conditions of the plant and the plurality of timings for applying the each of the plurality of operation conditions for each of a plurality of cases, and
predict the transient state for each of the plurality of cases.

### Claim 4 (depends on 3)

The plant operation support device according to claim 3, wherein the at least one processor is further configured to:
generate a plurality of trend graphs, which are different between each of the plurality of cases, from each prediction result of the transient state corresponding to each of the plurality of cases.

### Claim 5 (depends on 3)

The plant operation support device according to claim 3, wherein the at least one processor is further configured to:
generate a combined trend graph from each prediction result of the transient state corresponding to each of the plurality of cases.

### Claim 6 (depends on 1)

The plant operation support device according to claim 1, wherein
a plurality of scenarios are previously set, each of which indicates an operation to the plant and registers a predetermined tag indicating a control target in the plant, and
the at least one processor is further configured to:
set an operation condition of the predetermined tag, which is registered in a scenario selected from the plurality of scenarios, and a timing for applying the operation condition in accordance with an operation input by the user; and
predict the transient state in a case in which the operation condition of the predetermined tag, which is registered in a scenario selected from the plurality of scenarios, is applied at the timing.

### Claim 7 (depends on 1)

The plant operation support device according to claim 1, wherein
the plant operation support device is for predicting a concentration of impurity components that determines the quality of the product to be produced in the plant by a simulation based on measurement data of a feed flow rate of a distillation column obtained from the field device arranged in the distillation column in the plant,
the at least one processor is configured to:
operate in parallel synchronizing with the plant and perform a simulation with obtaining the feed flow rate from the field device to estimate the concentration of impurity components that has not been measured in the plant;
estimate periodically the performance parameter of devices used for the estimation of the concentration of impurity components based on the feed flow rate obtained from the field device;
predict the transient state by the simulation based on the estimated concentration of impurity components; and
predict the stationary state by the simulation based on the estimated concentration of impurity components.

### Claim 8

A plant operation support method using a plant operation support device, having a processor and memory, for predicting a concentration of components that determines quality of a product to be produced in a plant by a simulation based on measurement data obtained from a field device arranged in the plant, comprising:
operating with said processor in parallel synchronizing with the plant and performing with said processor a simulation with obtaining the measurement data from the field device to estimate a state quantity that has not been measured in the plant;
estimating periodically with said processor performance parameter of devices used for the estimation of the state quantity based on the measurement data obtained from the field device;
setting beforehand with said processor a plurality of operation conditions of the plant in a case in which the plant is operated near a limit of a product specification of the product and a plurality of timings for applying each of the plurality of operation conditions, the plurality of operation conditions being setting values relating to control of the plant;
predicting with said processor, based on the estimated state quantity, a transient state of the plant from a specific time point to a future time point by the simulation in a case in which the plurality of operation conditions that have been set beforehand are applied at the plurality of timings, the specific time point being selectable between a present time and a previous time when a previous transient state prediction is performed, a present operating state being made to be an initial state in a case in which the present time is selected, an operating state used by the previous transient state prediction being made to be an initial state in a case in which the previous time is selected;
setting with said processor a re-setting value input by a user as at least one of the plurality of operation conditions at a timing input by the user in the middle of one processing of the transient state prediction and continuing the one processing of the transient state prediction;
predict, by the simulation based on the estimated state quantity, a stationary state that is a final destination of an operating state of the plant in a case where the plurality of operation conditions set beforehand are applied at the plurality of timings,
generating with said processor a trend graph that is made from time series of a prediction result of the concentration in the transient state and the stationary state; and
displaying the generated trend graph and the limit of the product specification of the product in a screen.

### Claim 9 (depends on 8)

The plant operation support method according to claim 8, wherein
the plant operation support method is for predicting a concentration of impurity components that determines the quality of the product to be produced in the plant by a simulation based on measurement data of a feed flow rate of a distillation column obtained from the field device arranged in the distillation column in the plant,
the plant operation support method comprises:
operating in parallel synchronizing with the plant and performing a simulation with obtaining the feed flow rate from the field device to estimate the concentration of impurity components that has not been measured in the plant;
estimating periodically the performance parameter of devices used for the estimation of the concentration of impurity components based on the feed flow rate obtained from the field device;
predicting the transient state by the simulation based on the estimated concentration of impurity components; and
predicting the stationary state by the simulation based on the estimated concentration of impurity components.

### Claim 10

A non-transitory computer-readable storage medium storing a program for causing a computer of a plant operation support device for predicting a concentration of components that determines quality of a product to be produced in a plant by a simulation based on measurement data obtained from a field device arranged in the plant to execute:
operating in parallel synchronizing with the plant and performing a simulation with obtaining the measurement data from the field device to estimate a state quantity that has not been measured in the plant;
estimating periodically performance parameter of devices used for the estimation of the state quantity based on the measurement data obtained from the field device;
setting beforehand a plurality of operation conditions of the plant in a case in which the plant is operated near a limit of a product specification of the product and a plurality of timings for applying each of the plurality of operation conditions, the plurality of operation conditions being setting values relating to control of the plant;
predicting, based on the estimated state quantity, a transient state of the plant from a specific time point to a future time point by a simulation in a case in which the plurality of operation conditions that have been set beforehand are applied at the plurality of timings, the specific time point being selectable between a present time and a previous time when a previous transient state prediction is performed, a present operating state being made to be an initial state in a case in which the present time is selected, an operating state used by the previous transient state prediction being made to be an initial state in a case in which the previous time is selected;
setting a re-setting value input by a user as at least one of the plurality of operation conditions at a timing input by the user in the middle of one processing of the transient state prediction and continuing the one processing of the transient state prediction;
predict, by the simulation based on the estimated state quantity, a stationary state that is a final destination of an operating state of the plant in a case where the plurality of operation conditions set beforehand are applied at the plurality of timings,
generating a trend graph that is made from time series of a prediction result of the concentration in the transient state and the stationary state; and
displaying the generated trend graph and the limit of the product specification of the product in a screen.

### Claim 11 (depends on 10)

The non-transitory computer-readable storage medium according to claim 10, wherein
the program is for causing the computer of the plant operation support device for predicting a concentration of impurity components that determines the quality of the product to be produced in the plant by a simulation based on measurement data of a feed flow rate of a distillation column obtained from the field device arranged in the distillation column in the plant to execute:
operating in parallel synchronizing with the plant and performing a simulation with obtaining the feed flow rate from the field device to estimate the concentration of impurity components that has not been measured in the plant;
estimating periodically the performance parameter of devices used for the estimation of the concentration of impurity components based on the feed flow rate obtained from the field device;
predicting the transient state by the simulation based on the estimated concentration of impurity components; and
predicting the stationary state by the simulation based on the estimated concentration of impurity components.