Prediction apparatus, prediction method, and program
To improve prediction accuracy of a process including a reaction in a chemical plant. A prediction apparatus includes a process data processing unit that performs a predetermined processing process on process data obtained from a chemical plant, and a prediction model generation unit that generates a prediction model having learned features of the process data obtained from the chemical plant, on the basis of causality information that defines a combination of first process data and second process data or a value corresponding to the second process data among the process data obtained from the chemical plant or the process data processed by the process data processing unit. The first process data is used as an explanatory variable. The second process data or the value corresponding to the second process data is used as a response variable. Furthermore, the process data processing unit obtains a value corresponding to a reaction rate of a processing target in a predetermined period by using the process data.
1 . A prediction apparatus including:
a process data processing unit configured to perform a predetermined processing process on process data obtained from a chemical plant;
a prediction model generation unit configured to generate a prediction model having learned features of the process data obtained from the chemical plant, on the basis of causality information that defines a combination of first process data and second process data or a value corresponding to the second process data among the process data obtained from the chemical plant or the process data processed by the process data processing unit, the first process data being used as an explanatory variable, the second process data or the value corresponding to the second process data being used as a response variable; and
a quality prediction unit configured to calculate a predicted value by using the prediction model and to output the predicted value,
wherein
the process data processing unit obtains a value corresponding to a reaction rate of a processing target in a predetermined period by using the process data including a temperature in a corresponding step representing the predetermined interval in a stage, and
the value corresponding to the reaction rate is an integral value of the reaction rate.
2 . The prediction apparatus according to claim 1 , wherein the value corresponding to the reaction rate is calculated by using an Arrhenius equation, and a frequency factor and activation energy of a reaction rate constant are determined according to a type of chemical reaction and a processing target in the chemical plant.
3 . The prediction apparatus according to claim 1 , wherein the process data processing unit further obtains an integral value, a differential value, an average value, a maximum value, or a minimum value of the process data in a predetermined period, or an instantaneous value of the process data at a predetermined time point according to a type of the process data.
4 . The prediction apparatus according to claim 1 , wherein the prediction model has a hierarchical structure including a plurality of prediction equations, and includes a second prediction equation in which a predicted value calculated by a first prediction equation is included as an explanatory variable.
5 . The prediction apparatus according to claim 1 , wherein
the value corresponding to the second process data is a value obtained by sampling a plurality of second process data by a sample size reduction method, and
the prediction model generation unit generates the prediction model by correlating a range of acquisition timing of the first process data with calculation timing of the value corresponding to the second process data in the chemical plant, on the basis of a residence time of the processing target in the chemical plant.
6 . The prediction apparatus according to claim 1 , wherein
the chemical plant performs a batch stage of sequentially processing a processing target on a transaction-to-transaction basis using a predetermined transaction and a subsequent continuous stage of continuously processing the processing target, and
the prediction model generation unit generates the prediction model by correlating a range of completion timing of the batch stage and the calculation timing of the value corresponding to the second process data on the basis of the residence time of the processing target in the chemical plant.
7 . A prediction method performed by a prediction apparatus, the prediction method comprising:
performing a predetermined processing process on process data obtained from a chemical plant;
generating a prediction model having learned features of the process data obtained from the chemical plant, on the basis of causality information that defines a combination of first process data and second process data or a value corresponding to the second process among the process data obtained from the chemical plant or the process data processed in the performing of the predetermined processing process, the first process data being used as an explanatory variable, the second process data or the value corresponding to the second process being used as a response variable; and
calculating a predicted value by using the prediction model, and
outputting the predicted value,
wherein
in the performing of the predetermined processing process, a value corresponding to a reaction rate of a processing target in a predetermined period is obtained by using the process data including a temperature in a corresponding step representing the predetermined interval in a stage, and
the value corresponding to the reaction rate is an integral value rate of the reaction rate.
8 . A non-transitory storage medium storing a program that causes a computer to:
perform a predetermined processing process on process data obtained from a chemical plant;
generate a prediction model having learned features of the process data obtained from the chemical plant, on the basis of causality information that defines a combination of first process data and second data or a value corresponding to the second process data among the process data obtained from the chemical plant or the process data processed in the performing of the predetermined processing process, the first process data being used as an explanatory variable, the second process data or the value corresponding to the second process data being used as a response variable; and
calculate a predicted value by using the prediction model, and
output the predicted value,
wherein
in the performing of the predetermined processing process, a value corresponding to a reaction rate of a processing target in a predetermined period is obtained by using the process data data including a temperature in a corresponding step representing the predetermined interval in a stage, and
the value corresponding to the reaction rate is an integral value rate of the reaction rate.