Control apparatus, control method, and recording medium having control program recorded thereon
Provided is a control apparatus, including a control unit, configured to control a control target by a machine learned control model to output an operation amount of the control target according to a state of equipment having the control target provided therein; a prediction unit, configured to predict a future state of the equipment; an adjusting unit, configured to adjust the operation amount based on a predicted result; and an output unit, configured to output an adjusted operation amount to the control target.
1. A control apparatus, comprising:
at least one processor;
a control unit, that uses the at least one processor to control a control target by a machine learned control model to thereby output an operation amount of the control target according to a state of equipment having the control target provided therein;
a prediction unit, that uses the at least one processor to predict a future state of the equipment;
an adjusting unit, that uses the at least one processor to adjust the operation amount based on a predicted result; and
an output unit, that uses the at least one processor to output an adjusted operation amount to the control target;
wherein
the prediction unit uses the at least one processor to predict a future maintenance cost of the equipment;
the adjusting unit uses the at least one processor to avoid operating conditions in which the cost for a suppressant for suppressing deterioration of the equipment increases; and
the operating conditions conducive to the deterioration of the equipment are learned by the machine learned control model.
2. The control apparatus according to claim 1 , wherein
the prediction unit uses the at least one processor to predict a future state of health of the equipment; and
the adjusting unit uses the at least one processor to adjust the operation amount according to the state of health.
3. The control apparatus according to claim 2 , wherein
the state of health includes a remaining thickness of a plumbing in the equipment.
4. The control apparatus according to claim 3 , wherein
the prediction unit uses the at least one processor to predict a future maintenance cost of the equipment; and
the adjusting unit uses the at least one processor to adjust the operation amount according to the maintenance cost.
5. The control apparatus according to claim 3 , further comprising a learning unit that uses the at least one processor to generate the control model by machine learning.
6. The control apparatus according to claim 3 , further comprising
a plan acquisition unit that uses the at least one processor to acquire a production plan in the equipment,
wherein the adjusting unit is that uses the at least one processor to adjust the operation amount based on a predicted result and a production plan.
7. The control apparatus according to claim 2 , wherein
the prediction unit uses the at least one processor to predict a future maintenance cost of the equipment; and
the adjusting unit uses the at least one processor to adjust the operation amount according to the maintenance cost.
8. The control apparatus according to claim 2 , further comprising a learning unit that uses the at least one processor to generate the control model by machine learning.
9. The control apparatus according to claim 2 , further comprising
a plan acquisition unit that uses the at least one processor to acquire a production plan of the equipment,
wherein the adjusting unit is that uses the at least one processor to adjust the operation amount based on a predicted result and a production plan.
10. The control apparatus according to claim 1 , wherein
the prediction unit uses the at least one processor to predict a future maintenance cost of the equipment; and
the adjusting unit uses the at least one processor to adjust the operation amount according to the maintenance cost.
11. The control apparatus according to claim 10 , wherein
the maintenance cost includes a cost of adding a suppressant for suppressing deterioration of the equipment.
12. The control apparatus according to claim 10 , further comprising
a plan acquisition unit that uses the at least one processor to acquire a production plan in the equipment,
wherein the adjusting unit is that uses the at least one processor to adjust the operation amount based on a predicted result and a production plan.
13. The control apparatus according to claim 1 , further comprising a learning unit that uses the at least one processor to generate the control model by machine learning.
14. The control apparatus according to claim 13 , wherein the learning unit is that uses the at least one processor to generate, by reinforcement learning, the control model according to an input of state data indicating a state of the equipment so that an operation amount with a higher reward value determined by a predetermined reward function is output as a recommended operation amount.
15. The control apparatus according to claim 14 , wherein the learning unit uses the at least one processor to further learn a constraint condition in the machine learning based on a history in which the operation amount is adjusted.
16. The control apparatus according to claim 13 , wherein the learning unit uses the at least one processor to further learn a constraint condition in the machine learning based on a history in which the operation amount is adjusted.
17. The control apparatus according to claim 16 , wherein the constraint condition includes at least one of upper or lower limit values of the operation amount.
18. The control apparatus according to claim 1 , further comprising
a plan acquisition unit that uses the at least one processor to acquire a production plan in the equipment,
wherein the adjusting unit is that uses the at least one processor to adjust the operation amount based on a predicted result and a production plan.
19. A control method, comprising:
controlling a control target by a machine learned control model to thereby output an operation amount of the control target according to a state of equipment having the control target provided therein;
predicting a future state of the equipment;
adjusting the operation amount based on a predicted result; and
outputting an adjusted operation amount to the control target;
wherein
the predicting includes predicting a future maintenance cost of the equipment;
the adjusting includes avoiding operating conditions in which the cost for a suppressant for suppressing deterioration of the equipment increases; and
the operating conditions conducive to the deterioration of the equipment are learned by the machine learned control model.
20. A non-transitory recording medium having a control program recorded thereon, when executed by a computer including at least one processor, causing the computer to function as:
a control unit, that uses the at least one processor to control a control target by a machine learned control model to thereby output an operation amount of the control target according to a state of equipment having the control target provided therein;
a prediction unit, that uses the at least one processor to predict a future state of the equipment;
an adjusting unit, configured to adjust the operation amount based on a predicted result; and
an output unit, that uses the at least one processor to output an adjusted operation amount to the control target;
wherein
the prediction unit uses the at least one processor to predict a future maintenance cost of the equipment;
the adjusting unit uses the at least one processor to avoid operating conditions in which the cost for a suppressant for suppressing deterioration of the equipment increases; and
the operating conditions conducive to the deterioration of the equipment are learned by the machine learned control model.